No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Implementation and analysis of QUIC for MQTT
Abstract
Transport and security protocols are essential to ensure reliable and secure communication between two parties. For IoT applications, these protocols must be lightweight, since IoT devices are usually resource constrained. Unfortunately, the existing transport and security protocols – namely TCP/TLS and UDP/DTLS – fall short in terms of connection overhead, latency, and connection migration when used in IoT applications. In this paper, after studying the root causes of these shortcomings, we show how utilizing QUIC in IoT scenarios results in a higher performance. Based on these observations, and given the popularity of MQTT as an IoT application layer protocol, we integrate MQTT with QUIC. By presenting the main APIs and functions developed, we explain how connection establishment and message exchange functionalities work. We evaluate the performance of MQTTw/QUIC versus MQTTw/TCP using wired, wireless, and long-distance testbeds. Our results show that MQTTw/QUIC reduces connection overhead in terms of the number of packets exchanged with the broker by up to 56%. In addition, by eliminating half-open connections, MQTTw/QUIC reduces processor and memory usage by up to 83% and 50%, respectively. Furthermore, by removing the head-of-line blocking problem, delivery latency is reduced by up to 55%. We also show that the throughput drops experienced by MQTTw/QUIC when a connection migration happens is considerably lower than that of MQTTw/TCP.
... 53 To address the issue of high energy consumption, it is necessary to avoid 54 inefficiencies and wastage caused by inefficient way of delivering electrical energy 55 to the computing resources and the methodologies used by computing resources 56 to handle the application workloads. Improving upon resource management and 57 resource allocation policies, and reconfiguration of physical infrastructure paves 58 way to reduce inefficiencies. It is evident from a report Open Compute project, AQ2 59 Facebook Oregon data center achieved the Power Usage Effectiveness (PUE) ratio 60 to be 1.08 which indicates computing resources of the data center alone consumed 61 91% of electricity supplied and signifies upon advancement in data center's design 62 to achieve efficiency. ...
... 55 In this paper we explored a novel approach, in which we forecasted the par-56 ticulate concentration of an industrial-grade costly air pollution monitoring system 57 using a low-cost IoT-based air pollution monitoring system. Both the systems were 58 deployed at a cement factory, and the data were collected over a period of 1 day 59 at a frequency of one reading per hour from both systems simultaneously. First, 60 we investigated the VAR, VARMA, and SARIMAX models individually to forecast 61 the values of the costly system from the values of the low-cost system. ...
... The existing chapter of the application of the 55 Internet of Things explores a limited number of applications of IoT. The proposed 56 chapter instead of discussing the same, explore the smart home, smart cities, smart 57 railways, smart health care, intelligent agriculture, smart military applications of 58 IoT in recital. The chapter also narrates the commitment of IoT, phases, and its 59 deployment in all fields. ...
https://www.springer.com/gp/book/9783030738846
DOI 10.1007/978-3-030-73885-3
Contribución de dos capítulos al libro:
11. A Literature Review on Lean Manufacturing in the Industry 4.0: From Integrated Systems to IoT and Smart Factories . . . . . pág. 181
G. Turconi, G. Ventola, V. González-Prida, C. Parra, and A. Crespo
13 Calculating the Optimal Frequency of Maintenance for the Improvement of Risk Management: Plausible Models for the Integration of Cloud and IoT . . . . . . .pág.209
E. Fuenmayor, C. Parra, V. González-Prida, A. Crespo, F. Kristjanpoller, and P. Viveros
... Our previous work [55] explains the internal workings of quic-server and quic-client. In [55], QUIC was implemented for MQTT in IoT scenarios, where it was divided into serverclient agents and common APIs. ...
... Our previous work [55] explains the internal workings of quic-server and quic-client. In [55], QUIC was implemented for MQTT in IoT scenarios, where it was divided into serverclient agents and common APIs. The server-agent APIs are responsible for serving requests from clients, invoking common if (recvfrom(this→fp_ofl, buf_ofl.data, ...
... The long header is used for QUIC version [56] and 1-RTT keys negotiations and the short header is used for subsequent data communications. crypt_quic_message [55] (A5: L6) parses the packet and performs all necessary QUIC related operations such as connection establishment and key management. ...
Transport and security layer protocols make up the backbone of communication between end point devices. In Software Defined Networking (SDN), these protocols play a crucial role in both control-plane and data-plane communications. However, the current transport and security layer protocols: TCP and TLS, are unable to keep up with the pace of SDN application development. For these applications, the TCP/TLS protocol suite generates excessive network overhead. After identifying the main overhead origins, we demonstrate that using QUIC as the SDN transport layer protocol significantly reduces the overhead and improves the efficiency of the network. In this paper, we introduce quicSDN to enable robust, low-overhead communication between the controller and switches. We ran a variety of experiments to highlight quicSDN's benefits, and compared experimental results with transport-layer overhead prediction models. quicSDN's performance is evaluated in terms of network overhead reduction and we also demonstrated quicSDN's connection migration capabilities. First, we compare the differences in controller-switch communication overhead between tcpSDN(SDN over TCP) and quicSDN. Overhead reduction was measured in three scenarios: flow rule installation, queue configuration, and flow rule statistics polling. Second, we compare the connection migration of quicSDN and tcpSDN; QUIC's ability to quickly migrate connections allows for reduced total traffic in comparison to TCP. Overall, our results show that quicSDN outperformed tcpSDN in our SDN scenarios, and as such, QUIC is a promising candidate as an SDN transport layer protocol in the future.
... at the transport layer to leverage the advantages outlined above. For instance, the authors of [128] present a QUICbased implementation of MQTT implemented using the GO language. Through extensive experiments conducted on various wired and wireless communication scenarios, the authors demonstrate outstanding results in terms of security and communication latency. ...
... A standardized solution is given by Datagram Transport Layer Security (DTLS), a datagram- Paper Implementation Type of work Appl. protocol [128] GO Experimental MQTT [129] GO Experimental MQTT [130] GO & ns-3 Simulation MQTT [131], [132] GO & ns-3 Simulation MQTT [133] GO Experimental HTTP/3 & MQTT [134] C Sim./Exp. HTTP/3 [135] GO Simulation HTTP/3 [136] Python Simulation HTTP/3 [137] ns-3 Simulation HTTP/3 [138] VPS+ Simulation CoAP [139] GO Experimental CoAP [140] Python Experimental WebSocket [141], [142] GO Experimental AMQP [143] Quant Experimental built-in Quant based equivalent of TLS. ...
The last years have been characterized by strong market exploitation of the Internet of Things (IoT) technologies in different application domains, such as Industry 4.0, smart cities, and eHealth. All the relevant solutions should properly address the security issues to ensure that sensor data and actuators are not under the control of malicious entities. Additionally, many applications should at the same time provide low-latency communications, as in the case for instance of remote control of industrial robots. Low latency and security are two of the most important challenges to be addressed for the successful deployment of IoT applications. These issues have been analyzed by several scientific papers and surveys that appeared in the last decade. However, few of them consider the two challenges jointly. Moreover, the security aspects are primarily investigated only in specific application domains or protocol levels and the latency issues are typically investigated only at low layers (e.g., physical, access). This paper addresses this shortcoming and provides a systematic review of state-of-the-art solutions for providing fast and secure IoT communications. Although the two requirements may appear to be in contrast to each other, we investigate possible integrated solutions that minimize device connection and service provisioning. We follow an approach where the proposals are reviewed by grouping them based on the reference architectural layer, i.e., access, network, and application layers. We also review the works that propose promising solutions that rely on the exploitation of the QUIC protocol at the higher levels of the protocol stack.
... Researchers in past [25] studied the performance of MQTT over QUIC using wireless, wired and long distance test-beds built with Raspberry Pi 3B devices and demonstrated that MQTT with QUIC outperforms MQTT with TCP in terms of processor usage, memory usage and latency. Authors in [11] integrated MQTT with QUIC using Go programming language and carried out extensive testing in NS3 simulator. ...
... MQTT and CoAP, which are two widely used protocols in IoT, have already been integrated with QUIC by the researchers in [25,26], respectively. However, AMQP 1.0 which is also an important extensible and inter-operable IoT protocol has not been yet integrated with QUIC. ...
... Kumar and Dezfouli [12] outfitted Chromium's Google QUIC (GQUIC) to carry MQTT. Because MQTT and GQUIC both run in user-space, they had written inter-process communication APIs and redesigned various data structures for their solution. ...
... III. PUBLISH-SUBSCRIBE ARCHITECTURES FOR IOT As a widely used application in IoT, we focus on Machineto-Machine communication (M2M) in our investigation [12]. Particularly, MQTT and our pure-H3 pub-sub implementation. ...
Because of the constrained nature of devices and networks in the Internet of Things (IoT), secure yet lightweight communication protocols are paramount. QUIC is an emerging contender in this arena and it provides several benefits over TCP. Tuning of TCP has been recently studied for IoT and guidelines are provided in RFC 9006. The same is not true of QUIC -- a much newer protocol with a learning curve. The aim of this paper is to provide empirically based insights into parameterization considerations of QUIC for IoT. To this end, we rigorously tested two modes of MQTT-over-QUIC as well as a pure-HTTP/3 publish-subscribe architecture (of our design) under various conditions. A suite of 8 metrics relating to device and network overhead and performance was employed in addition to root cause analysis on a hardware testbed. We identified a number of tuning considerations and concluded that HTTP/3 was more preferable for reliable time-sensitive applications.
... Kumar and Dezfouli evaluated Google QUIC's performance in IoT scenarios [26]. They defined a testbed with Raspberry Pi 3B devices where MQTT over QUIC and TCP performance was assessed. ...
... Lars Eggert studied the feasibility of implementing QUIC in constrained IoT devices [27]. He used more limited devices than those used by Kumar and Dezfouli [26]: Particle Argon and ESP32-DevKitC V4. Since the main objective was to enable the operation of QUIC in low-capable devices, some of the original QUIC features, likely to be impractical for IoT, were changed, or even removed, to reduce the required memory usage. ...
In this paper we analyze the performance of QUIC as a transport alternative for Internet of Things (IoT) services based on the Message Queuing Telemetry Protocol (MQTT). QUIC is a novel protocol promoted by Google, and was originally conceived to tackle the limitations of the traditional Transmission Control Protocol (TCP), specifically aiming at the reduction of the latency caused by connection establishment. QUIC use in IoT environments is not widespread, and it is therefore interesting to characterize its performance when in over such scenarios. We used an emulation-based platform, where we integrated QUIC and MQTT (using GO-based implementations) and compared their combined performance with the that exhibited by the traditional TCP/TLS approach. We used Linux containers as end devices, and the ns-3 simulator to emulate different network technologies, such as WiFi, cellular, and satellite, and varying conditions. The results evince that QUIC is indeed an appropriate protocol to guarantee robust, secure, and low latency communications over IoT scenarios.
... Such conditions are present in resourceconstrained IoT. Researchers [4], [5] have thus mapped MQTT to run over QUIC and evaluated it against MQTT-over-TCP. ...
... Kumar and Dezfouli [4] outfitted Chromium's GQUIC to carry MQTT. Because MQTT and QUIC both run in userspace, they had written inter-process communication APIs and redesigned various data structures to make their solution functional. ...
In this letter, we address the issue of scalable and timely dissemination of information in resource-constrained IoT networks. The scalability is addressed by adopting a publishsubscribe architecture. To address the timely dissemination, we propose an HTTP/3 (H3) publish-subscribe solution that exploits the wide-ranging improvements offered by H3. We evaluated our solution by comparing it to a state-of-the-art work which maps MQTT to QUIC. Because QUIC and H3 have been developed in tandem, we hypothesized that H3 would take better advantage of QUIC transport than an MQTT mapping would. Performance, network overhead, and device overhead were investigated for both implementations. Our H3-based solution satisfied our timely dissemination requirement by offering a key performance savings of 1 RoundTrip Time (RTT) for publish messages to arrive at the broker. In IoT networks, with typically high RTT, this savings is significant. On the other hand, we found that MQTT-over-QUIC put marginally less strain over the network.
... When there are huge message flows exchanged by broker, issue of latency may be inevitable [16]. e latency not only decreases the speed of data transmission but also wastes device battery to decrease the overall device life-span [17][18][19][20]. In this paper, we focus on data exchange efficiency in an environment where there is a limited Internet access or there are serious network jitter problems for several hundred miles around. ...
... for all Adjacent(X) do (8) NodeX ∈ Adjacent(X); (9) if NodeX ∉ Searched Set then (10) NotSearched Set ⟵ NodeX; (11) X⇒subscribing to NodeX; (12) Node X ⟵ subscriping request P; (13) i ⟵ Weight(P); (14) top ⟵ Host Topic(P); (15) if !Match(top) then (16) addItemToRoutingTable(NodeX); (17) Searched Set ⟵ Nodex; (18) else if Weight(Route NodeX(Top)) > i then (19) Rewrite(Route_NodeX(P)); (20) NotSearched Set − X; (21) Searched Set ⟵ X; ...
Data exchange is one of the huge challenges in Internet of Things (IoT) with billions of heterogeneous devices already connected and many more to come in the future. Improving data transfer efficiency, scalability, and survivability in the fragile network environment and constrained resources in IoT systems is always a fundamental issues. In this paper, we present a novel message routing algorithm that optimizes IoT data transfers in a resource constrained and fragile network environment in publish-subscribe model. The proposed algorithm can adapt the dynamical network topology of continuously changing IoT devices with the rerouting method. We also present a rerouting algorithm in Message Queuing Telemetry Transport (MQTT) to take over the topic-based session flows with a controller when a broker crashed down. Data can still be communicated by another broker with rerouting mechanism. Higher availability in IoT can be achieved with our proposed model. Through demonstrated efficiency of our algorithms about message routing and dynamically adapting the continually changing device and network topology, IoT systems can gain scalability and survivability. We have evaluated our algorithms with open source Eclipse Mosquitto. With the extensive experiments and simulations performed in Mosquitto, the results show that our algorithms perform optimally. The proposed algorithms can be widely used in IoT systems with publish-subscribe model. Furthermore, the algorithms can also be adopted in other protocols such as Constrained Application Protocol (CoAP).
... Kumar and Dezfouli studied Google QUIC performance over IoT scenarios in [25]. They compared MQTT performance over QUIC and TCP in different testbeds, built with Raspberri Pi 3B devices. ...
... Lars Eggert has recently analyzed the feasibility of deploying QUIC over constrained IoT devices [26]. He used, for the prelimary evaluation, more constrained devices than those used in [25]: Particle Argon and ESP32-DevKitC V4. In order to reduce QUIC memory usage in low-end devices, some of the original QUIC features, considered impractical for IoT, were changed or removed. ...
... Application layer protocols such as HTTPS and MQTT facilitate data transmission and contribute to data integrity. HTTPS, which is HTTP over TLS connections, and MQTT, which can operate over TLS, rely on underlying transport layer protocols such as SSL / TLS and QUIC for encryption and security [62]. Remote Procedure Calls (RPC) facilitate communication between system components by allowing one program to request a service from a program located on another computer in the network. ...
Public key infrastructures are essential for Internet security, ensuring robust certificate management and revocation mechanisms. The transition from centralized to decentralized systems presents challenges such as trust distribution and privacy-preserving credential management. The transition from centralized to decentralized systems is motivated by addressing the single points of failure inherent in centralized systems and leveraging decentralized technologies' transparency and resilience. This paper explores the evolution of certificate status management from centralized to decentralized frameworks, focusing on blockchain technology and advanced cryptography. We provide a taxonomy of the challenges of centralized systems and discuss opportunities provided by existing decentralized technologies. Our findings reveal that, although blockchain technologies enhance security and trust distribution, they represent a bottleneck for parallel computation and face inefficiencies in cryptographic computations. For this reason, we propose a framework of decentralized technology components that addresses such shortcomings to advance the paradigm shift toward decentralized credential status management.
... En cambio, QUIC puede enviar inmediatamente los paquetes 3 y 4 a HTTP, donde son procesados antes del paquete mencionado En pocas palabras, esta técnica se vuelve ineficaz cuando ocurre una pérdida de paquetes en el flujo del Protocolo de Control de Transmisión (TCP), ya que todas las corrientes independientes se bloquean hasta la retransmisión del paquete perdido. Es decir, si un solo paquete se cae, o se pierde en la red en algún lugar entre dos (2) puntos finales que se comunican por medio HTTP/2 [13] [14], significa que toda la conexión TCP, la cual se encuentra en serie o en secuencia (Figura 5A), se detiene mientras el paquete perdido se retransmite y vuelve a dirigir hacia el destino, teniendo que esperar el resto de paquetes hasta la resolución de dicha eventualidad. Básicamente, el problema surge porque el TCP subyacente no diferencia entre mensajes/corrientes independientes del protocolo de Capa de Aplicación. ...
TCP (Transmission Control Protocol) has been a widely adopted transport protocol on the Internet for many years. However, with the continuous evolution of wireless networks and the ever-growing demand for faster and more efficient connections have highlighted certain limitations of TCP, with one of its major drawbacks being the suboptimal behavior of the protocol over networks, particularly in terms of packet recovery time. As internet traffic rapidly expands, these limitations have become more pronounced, making it necessary to explore alternative solutions. In this context, the QUIC (Quick UDP Internet Connections) protocol has emerged as a promising and innovative approach by Google, in order to address these challenges and improve the management of connections. This research focuses on analyzing the QUIC protocol, employing a documentary research methodology. The results cover a detailed explanation of the protocol's design and the implementation of several of QUIC's mechanisms concerning congestion control, reduced round-trip time and security; focusing at the same time on the integration of the protocol in wireless networks to effectively reduce latency and prevent unnecessary retransmissions in the event of data packets.
... MQTTw/QUIC [12] is an MQTT approach based on QUIC. Two software agents provide the integration between MQTT and QUIC, one located between the broker and the QUIC server, and one other sitting between MQTT clients and the QUIC client. ...
The Publish/Subscribe (P/S) paradigm plays an essential role in developing Internet of Things (IoT) applications. Among the most representative P/S protocols, there is Message Queuing Telemetry Transport (MQTT). Standard implementations employ a single server acting as a broker for client-to-client communication: publishers send messages to the broker, which forwards them to the subscribers. A single server is a single point of failure and a potential bottleneck. Most IoT applications require a reliable and scalable communication system. MQTT systems can evolve in such requirements through clustering or federation of brokers, resulting in more complex communication architectures. This work presents an overview of current issues and solutions for addressing MQTT scalability in the IoT context.
... Generally, different protocols are used for network transportation, such as TLS/TCP or UDP protocols. However, with the rapid growth of Internet users around the globe, some of these protocols may suffer from some limitations, such as latency in TLS/TCP [1]. Therefore, alternative protocols were proposed in the literature to overcome this limitation [2]. ...
The Quick UDP Internet Connections (QUIC) protocol provides advantages over traditional TCP, but its encryption functionality reduces the visibility for operators into network traffic. Many studies deploy machine learning and deep learning algorithms on QUIC traffic classification. However, standalone machine learning models are subject to overfitting and poor predictability in complex network traffic environments. Deep learning on the other hand requires a huge dataset and intensive parameter fine-tuning. On the contrary, ensemble techniques provide reliability, better prediction, and robustness of the trained model, thereby reducing the chance of overfitting. In this paper, we approach the QUIC network traffic classification problem by utilizing five different ensemble machine learning techniques, namely: Random Forest, Extra Trees, Gradient Boosting Tree, Extreme Gradient Boosting Tree, and Light Gradient Boosting Model. We used the publicly available dataset with five different services such as Google Drive, YouTube, Google Docs, Google Search, and Google Music. The models were trained using a different number of features on different scenarios and evaluated using several performance metrics. The results show that Extreme Gradient Boosting Tree and Light Gradient Boosting Model outperform the other models and achieve one of the highest results among the state-of-the-art models found in the literature with a simpler model and features.
... MQTT and CoAP, which are two widely used protocols in IoT, have already been integrated with QUIC by the researchers in Kumar and Dezfouli (2019) and Herrero (2021), respectively. However, AMQP1.0 which is also an important extensible and interoperable IoT protocol has not been yet integrated with QUIC. ...
In today’s world, the use of IoT devices is growing every day. For connecting IoT devices from various vendors and supporting a variety of IoT use cases, an interoperable protocol like AMQP is necessary. Researchers are striving to minimize delay because many IoT applications are sensitive to it. The transport layer protocol that is used underneath, such as TCP or UDP, is one of the main causes of the delay. Although TCP is slower than UDP because to the three-way handshake and the usage of TLS for security, it is more reliable than UDP. The Internet Engineering Task Force has introduced a new transport layer protocol called QUIC that combines the best features of UDP and TCP to offer quick and reliable communication. In this study, we integrated QUIC and AMQP1.0 using the Go programming language. The Docker tool was used to containerize the AMQP1.0 Broker, Sender, and Receiver implementations. The performance of AMQP1.0 over TCP and AMQP1.0 over QUIC was benchmarked in the NS3 simulator over various wireless networks including WiFi, 4G/LTE, and satellite. QUIC showed considerable improvement over lossy networks. The results showed that switching from TCP to QUIC at the transport level lowered Communication Time by 8.57% over Satellite network. Although Round Trip Time was almost same yet Start up Latency showed improvement of 52%, 38% and 34% in case of WiFi, 4G/LTE and Satellite respectively. In addition, the performance of AMQP1.0 over TCP and AMQP1.0 over QUIC has been evaluated over different Packet Loss values, the results show that AMQP1.0 over QUIC outperforms AMQP1.0 over TCP in all the cases. The testing results revealed that TCP performance was degraded by 20%, 16%, and 36% over WiFi, 4G/LTE, and satellite, respectively at Packet loss of 15%, while QUIC performance was only degraded by 4%, 8%, and 9% in each of these cases.
... To the best of our knowledge, this paper is the first to investigate the feasibility of deploying QUIC directly on resource constrained IoT devices. Another recent paper [39] investigated using QUIC to transport Message Queuing Telemetry Transport (MQTT) [40], by running a subset of the Google's original Chromium "gQUIC" code on Raspberry Pi Model 3B devices. However, those are so much more powerful (quad-core ARMv8 Cortex A53 at 1.2 GHz, 1 GB RAM, many GB of storage) than either of the two platforms investigated in this paper that is questionable whether they even qualify as resource-constrained. ...
... " Fig.4." shows the connection transition problem mentioned for TCP. Fig. 4. TCP connection relays problem [21] QUIC keeps the connection ID the same thanks to the CID, and does not break the connection even if there is a change in any of these parameters. If the client's IP address changes, the connection from the old connection ID and the new IP address continues without any interruption. ...
... To ensure an in-order delivery, the transport protocol running on these devices needs to keep the data received out-of-order during at least one round-trip-time, requiring receive buffer sizes to grow to dozens of megabytes for each connection. At the same time, QUIC is also considered for securing connections on IoT devices [52], [62]. Those embedded devices cannot dedicate large buffers for their network connections. ...
Packet losses are common events in today’s networks. They usually result in longer delivery times for application data since retransmissions are the de facto technique to recover from such losses. Retransmissions is a good strategy for many applications but it may lead to poor performance with latency-sensitive applications compared to network coding. Although different types of network coding techniques have been proposed to reduce the impact of losses by transmitting redundant information, they are not widely used. Some niche applications include their own variant of Forward Erasure Correction (FEC) techniques, but there is no generic protocol that enables many applications to easily use them. We close this gap by designing, implementing and evaluating a new Flexible Erasure Correction (FlEC) framework inside the newly standardized QUIC protocol. With FlEC, an application can easily select the reliability mechanism that meets its requirements, from pure retransmissions to various forms of FEC. We consider three different use cases: $(i)$ bulk data transfer, $(ii)$ file transfers with restricted buffers and $(iii)$ delay-constrained messages. We demonstrate that modern transport protocols such as QUIC may benefit from application knowledge by leveraging this knowledge in FlEC to provide better loss recovery and stream scheduling. Our evaluation over a wide range of scenarios shows that the FlEC framework outperforms the standard QUIC reliability mechanisms from a latency viewpoint.
... To ensure an in-order delivery, the transport protocol running on these devices needs to keep the data received out-of-order during at least one round-trip-time, requiring receive buffer sizes to grow to dozens of megabytes for each connection. At the same time, QUIC is also considered for securing connections on IoT devices [52], [62]. Those embedded devices cannot dedicate large buffers for their network connections. ...
Packet losses are common events in today's networks. They usually result in longer delivery times for application data since retransmissions are the de facto technique to recover from such losses. Retransmissions is a good strategy for many applications but it may lead to poor performance with latency-sensitive applications compared to network coding. Although different types of network coding techniques have been proposed to reduce the impact of losses by transmitting redundant information, they are not widely used. Some niche applications include their own variant of Forward Erasure Correction (FEC) techniques, but there is no generic protocol that enables many applications to easily use them. We close this gap by designing, implementing and evaluating a new Flexible Erasure Correction (FlEC) framework inside the newly standardized QUIC protocol. With FlEC, an application can easily select the reliability mechanism that meets its requirements, from pure retransmissions to various forms of FEC. We consider three different use cases: $(i)$ bulk data transfer, $(ii)$ file transfers with restricted buffers and $(iii)$ delay-constrained messages. We demonstrate that modern transport protocols such as QUIC may benefit from application knowledge by leveraging this knowledge in FlEC to provide better loss recovery and stream scheduling. Our evaluation over a wide range of scenarios shows that the FlEC framework outperforms the standard QUIC reliability mechanisms from a latency viewpoint.
... It is an asynchronous publish/subscribe protocol that runs on top of the TCP stack and a typical network configuration consists of a server and several clients [79]. Small modifications on this protocol originated the Message Queuing Telemetry Transport for Sensor Networks (MQTT-SN) [80], MQTT over WebSockets that leverage the use of MQTT on top of WebSockets [81], and MQTTw/QUIC which uses QUIC as the transport protocol [82]. ...
The current complexity of IoT systems and devices is a barrier to reach a healthy ecosystem, mainly due to technological fragmentation and inherent heterogeneity. Meanwhile, the field has scarcely adopted any engineering practices currently employed in other types of large-scale systems. Although many researchers and practitioners are aware of the current state of affairs and strive to address these problems, compromises have been hard to reach, making them settle for sub-optimal solutions. This paper surveys the current state of the art in designing and constructing IoT systems from the software engineering perspective, without overlooking hardware concerns, revealing current trends and research directions.
... rapid development of mobile and web applications shed the light on several limitations in the current transport protocols, such as the latency overhead in TLS/TCP protocol [1]. As a result, many efforts were made to build new transport protocols that reduce latency and provide security mechanisms [2], [3], [4], [5]. ...
Since the introduction of QUIC protocol, a major
change has affected the Internet transport layer, which improves
user experience with some security threats. Developed by Google
in 2012, QUIC provides a low latency, connection-oriented and
encrypted transport. In addition to the encryption capability of
QUIC, it overcomes many issues found in the current transport
protocols, such as the high-latency connection establishment in
TCP. On the other hand, studies on the security analysis of
QUIC’s key establishment showed several drawbacks. Moreover,
the encryption mechanism of the protocol allows adversarial
Command & Control (C2) packets to blind with regular QUIC
traffic without raising any alarms. Therefore, in this study, we
develop a machine learning approach based on fingerprinting that
can be used in intrusion detection systems to detect malicious C2
QUIC traffic. To demonstrate the effectiveness of this approach,
we conducted an experiment and tested the performance of six
machine learning classifiers. The results show that by utilizing
the fingerprint, most of the classifiers recognized malicious C2
traffic with an average accuracy of 98%.
... Understanding how this can undertake more efficiently is also an important approach to reduce energy use. 9 Hotspot and Coldspot Migration: A common approach to reducing power consumption is the dynamic consolidation of virtual machines and containers on a smaller number of physical machines (PMs). This is based on the observation that PMs run at 10-50% of their maximum CPU usage and the majority of PMs are idle while still consuming about 70% of their peak power. ...
Although serverless computing generally involves executing short-lived “functions,” the increasing migration to this computing paradigm requires careful consideration of energy and power requirements. serverless computing is also viewed as an economically-driven computational approach, often influenced by the cost of computation, as users are charged for per-subsecond use of computational resources rather than the coarse-grained charging that is common with virtual machines and containers. To ensure that the startup times of serverless functions do not discourage their use, resource providers need to keep these functions hot, often by passing in synthetic data. We describe the real power consumption characteristics of serverless, based on execution traces reported in the literature, and describe potential strategies (some adopted from existing VM and container-based approaches) that can be used to reduce the energy overheads of serverless execution. Our analysis is, purposefully, biased toward the use of machine learning workloads because: (1) workloads are increasingly being used widely across different applications; (2) functions that implement machine learning algorithms can range in complexity from long-running (deep learning) versus short-running (inference only), enabling us to consider serverless across a variety of possible execution behaviors. The general findings are easily translatable to other domains.
... Kumar and Dezfouli [8] showed how utilizing QUIC [9]) in IoT scenarios. The authors integrated MQTT with QUIC in order to justify the potential benefits of QUIC compared to TCP/TLS and UDP/DTLS in IoT scenarios and presented its integration with MQTT protocol. ...
Internet of Things (IoT) technologies have become a milestone advancement in the digital healthcare domain, since the number of IoT medical devices is grown exponentially, and it is now anticipated that by 2020, there will be over 161 million of them connected worldwide. Therefore, in an era of continuous growth, IoT healthcare faces various challenges, such as the collection over multiple protocols (e.g. Bluetooth, MQTT, CoAP, ZigBEE, etc.) the interpretation, as well as the harmonization of the data format that derive from the existing huge amounts of heterogeneous IoT medical devices. In this respect, this study aims at proposing an advanced Home Gateway architecture that offers a unique data collection module, supporting direct data acquisition over multiple protocols (i.e.BLE, MQTT) and indirect data retrieval from cloud health services (i.e. GoogleFit). Moreover, the solution propose a mechanism to automatically convert the original data format, carried over BLE, in HL7 FHIR by exploiting device capabilities semantic annotation implemented by means of FHIR resource as well. The adoption of such annotation enables the dynamic plug of new sensors within the instrumented environment without the need to stop and adapt the gateway. This simplifies the dynamic devices landscape customization requested by the several telemedicine applications contexts (e.g. CVD, Diabetes) and demonstrate, for the first time, a concrete example of using the FHIR standard not only (as usual) for health resources representation and storage but also as instrument to enable seamless integration of IoT devices. The proposed solution also relies on mobile phone technology which is widely adopted aiming at reducing any obstacle for a larger adoption.
... However, this application can only be used for a particular application, not for all categories. Kumar et al. [96] integrated MQTT with quick UDP Internet connections to reduce connection overhead during the message exchange between IoT devices or other devices and servers. MQTT with TCP takes the additional burden to make the handshake during the transmission. ...
The Internet of Things (IoT) has been growing over the past few years due to its flexibility and ease of use in real-time applications. The IoT's foremost task is ensuring that there is proper communication between different types of applications and devices, and that the application layer protocols fulfill this necessity. However, as the number of applications grows, it is necessary to modify or enhance the application layer protocols according to specific IoT applications, allowing specific issues to be addressed, such as dynamic adaption to network conditions and interoperability. Recently, several IoT application layer protocols have been enhanced and modified according to application requirements. However, no existing survey articles have focused on these protocols. In this article, we survey traditional and recent advances in IoT application layer protocols, as well as relevant real-time applications and their adapted application layer protocols for improving performance. As changing the nature of protocols for each application is unrealistic, machine learning offers means of making protocols intelligent and able to adapt dynamically. In this context, we focus on providing open challenges to drive IoT application layer protocols in such a direction.
... Most IoT devices rely on TCP/IP protocol stack to be able to interact via Internet infrastructure. Although there are special protocols developed for inter-machine communication, such as MQTT -Message Queuing Telemetry Transport (Banks et al., 2019, Kumar & Dezfouli, 2019 or CoAP -Constrained Application Protocol (Shelby et al., 2014), general web protocols are in heavy usage in IoT. Improvement of these protocols can potentially bring benefits to the performance and security of IoT, which has been particularly challenged (Mahmoud et al., 2016). ...
The paper investigates the performance properties of the new HTTP/3 protocol in IoT scenarios, with the focus on fog computing. A specific experimental environment is created, providing realistic IoT conditions. End-to-end delay and three different models for packet loss are introduced using the NetEm simulator in Linux. Three contemporary HTTP protocols are contrasted with two scenarios of IoT use. By comparing the experimental results obtained by the protocols HTTP/1, HTTP/2 and HTTP/3, it can be noticed that the protocol HTTP/3 outperforms the protocol HTTP/2 in 19 cases out of 24, yet it only outperforms HTTP/1 in 12 cases out of 24. Even if HTTP/3 is under development, it fulfils the requirements for performance and security for IoT and fog computing scenarios, involving unconstrained devices. With a lower connection overhead and an inherent security, HTTP/3 has secured a firm place for itself among other specialised IoT protocols.
... However, the flexibility of FFT-RS is constrained by fast Fourier transform (FFT). Previous version of QUIC [30], [31] implements a simple FEC mechanism (i.e., XOR) with a fixed code rate, whose static redundancy is also hard to adapt to varying network conditions [32]. Another type is based on rateless FEC codes, such as fountain codes [12]. ...
Modern mobile wireless networks have been demonstrated to be high-speed but lossy, while mobile applications have more strict requirements including reliability, low latency, goodput guarantee, bandwidth efficiency, and computation efficiency. Such a complicated combination of requirements and conditions in networks pushes the pressure to transport layer protocol design. We analyze and argue that few of existing network transport layer solutions are able to handle all these requirements. We design and implement Sphinx to satisfy the five requirements in high-speed and lossy networks. Sphinx has (1) a proactive coding-based method named semi-random LT codes for loss recovery, which estimates packet loss rate and adjusts the redundancy level accordingly, (2) a reactive retransmission method named Instantaneous Compensation Mechanism (ICM), which retransmits precisely and timely once decoding failure occurs, and (3) a parallel coding architecture, which speeds up coding process by leveraging multi-core, shared memory and kernel-bypass Data Plane Development Kit (DPDK). Prototype and evaluation show that Sphinx outperforms TCP schemes and other coding solutions significantly in microbenchmarks across all five requirements, and improves the performance of the video streaming application.
... The only rival solution widespread in the general networking -QUIC (Quick UDP Internet Connection) -imposes application adjustment [15], which is thus less attractive to adopt in the industrial context. However, from the data flow perspective, both protocols share similar premises [16]. ...
The concurrent use of a few transmission channels offered by the multipath version of the TCP protocol (MPTCP) becomes a widely accepted remedy for the quality of service and reliability issues. However, the common approaches to the multipath transfer organization do not give sufficient attention to the energy aspects, which are crucial for the resource-constrained devices in the Internet of Things domain. In this paper, a systematic tuning methodology of the MPTCP architectural modules – targeting the energy expenditure – is developed. By adopting a formal optimization approach, a new Scheduler, and a new Path Manager that promote conservative energy usage are designed. The proposed ‘green’ modules versions do not augment the protocol complexity. Next, explicit guidelines for the selection of the TCP variant to be used at the individual paths are provided. As confirmed by experiments involving physical devices and real networks, the established framework reduces the amount of dissipated energy by several percent (up to 50%) with respect to the default one. As a beneficial side-effect, the transmission throughput is increased and the protocol delay shortened in the uncertain networking conditions typical of industrial settings.
... The protocol uses in-band signaling. In references [4], discussed the basic of MQTT, IoT [13], [14], [15], and Implementation and Analysis of QUIC for MQTT., MQTT-based IoT was also developed by references [5] which were applied to hospitals, a technology-based IoT will reduce the physical needs especially in health applications in hospitals, for example checking the condition of the patient's body or checking up, to become an IoT-based technology [5]. In addition to the hospital, the MQTT-based IoT application is used to detect motorcycle accidents [6], the sensor used is an accelerator sensor to detect the tilt, and GPS to determine the accident's position in realtime. ...
In this research, remote robot hand control using (Message Queuing Telemetry Transport) MQTT Protocol and M5Stack Board. The purpose of this research is to develop remote control technology on the robotic fingers, the function of the robotic fingers is used as an actuator that works to control or perform certain jobs, for example, a robot that can press buttons automatically with remote control, or can adjust the volume, pressing the lever, catching the ball, giving symbols like counting abacus in mathematics, and other robot arm activities that can be developed remotely using internet technology. In general, the MQTT Protocol works by providing string input. Furthermore, the position of the servo angle is represented by the values x and y or θ1 and θ2. The results of the analysis in this research consisted of blockly programming and python used to control the robot finger and activities on MQTT Brokers which consisted of publish and subscribe and how the packet data was in MQTT Broker.
There has been growing interest in using the QUIC transport protocol for the Internet of Things (IoT). In lossy and high latency networks, QUIC outperforms TCP and TLS. Since IoT greatly differs from traditional networks in terms of architecture and resources, IoT specific parameter tuning has proven to be of significance. While RFC 9006 offers a guideline for tuning TCP within IoT, we have not found an equivalent for QUIC. This paper is the first of our knowledge to contribute empirically based insights towards tuning QUIC for IoT. We improved our pure HTTP/3 publish-subscribe architecture and rigorously benchmarked it against an alternative: MQTT-over-QUIC. To investigate the impact of transport-layer parameters, we ran both applications on Raspberry Pi Zero hardware. Eight metrics were collected while emulating different network conditions and message payloads. We enumerate the points we experimentally identified (notably, relating to authentication, MAX_STREAM messages, and timers) and elaborate on how they can be tuned to improve resource consumption and performance. Our application offered lower latency than MQTT-over-QUIC with slightly higher resource consumption, making it preferable for reliable time-sensitive dissemination of information.
QUIC has drawn extensive attention in supporting low latency and secure Internet of Things (IoT) communications due to its efficient handshake and default end-to-end encryption. However, in Wi-Fi enabled IoT communications with contentions for shared media, QUIC’s inherent acknowledgment (ACK) policy may induce non-negligible control overhead and limited data throughput. To address the problem, this paper designs and implements an ACK frequency optimization scheme for QUIC by exploiting the tailored bandwidth-delay product (BDP) at the receiver, named QUIC-BDP. To accurately estimate real-time BDP, we design an “ACK-PING" strategy to compensate for the accuracy of round-trip timing estimation and utilize exponential averaging and sliding window filtering for stable bandwidth estimation. Experiments results show that our proposed QUIC-BDP balances between the robustness and throughput performance while maintaining stable performance in lossy cases, with a reduced energy cost. Particularly, QUIC-BDP achieves up to a 67% gain in goodput compared to the original QUIC, and it improves goodput by up to 38% and 28% compared to existing solutions MSQUIC and QUIC-1:10, respectively. In addition, QUIC-BDP reduces energy cost by up to 50% compared to the original QUIC.
MQTT is an open standard protocol promoted by OASIS and ISO, which allows devices to transport messages using the publish/subscribe model. MQTT is more prevalent than other application layer protocols of the Internet of Things (IoT) due to its lightweight nature, low bandwidth usage, application demand, etc. It is easy and straightforward to use the protocol, making it optimal for communication in resource-constrained situations such as machine-to-machine (M2M), Wireless Sensor Networks (WSNs), and in IoT circumstances in which the actuator and sensor nodes connect with applications through the MQTT message broker. A few review papers on MQTT protocol are available in the literature that focuses on broker details, comparison of IoT protocols, and limitations. In this paper, an overview of MQTT, existing survey work on MQTT, publication statistics, MQTT protocol performance evaluation, applications of MQTT, security issues of MQTT, comparison between MQTT and MQTT-SN, tools available or MQTT and available MQTT brokers to provide service are discussed. Graphs and comparison tables are presented to show the outcomes of the application and performance evaluation. The scope of this review paper is also to contribute a novel taxonomy of application layer protocols, their merits and demerits, correlation of MQTT with other application layer protocols, existing works of MQTT protocol to improve reliability, efficiency, security, issues, and challenges in MQTT, as well as future directions of MQTT.
Since the Industry 4.0 nature is a world-scale phenomenon, lot of information are available today from several sources, presenting different points of view. From the scientific papers, the research is focused more on the theoretical steps for a future implementation and the benefits achievable, with important information on the development path followed by the industry to reach today’s situation. Other important resources are represented by the companies operating on the consultant and high-tech sectors, because the revolution is completely intertwined with the digital world and their reports can provide interesting information. At the end, the government reports of the most important manufacturing countries have been a good information source for the practical steps and the necessary requirements in order to create a favorable field for the implementation. Therefore, this chapter is intended to contribute over all these mentioned areas of knowledge, providing a brief state of the art regarding the Industry 4.0, the role of IoT and cloud computing in today’s and future factories, as well as a view along all those enabling technologies that complement among each other in the diverse industrial scenarios.
This work presents the analysis, design, development, and validation of a middleware based on the interceptor pattern to provide interoperability among application layer protocols in the context of Internet of Things (IoT) protocol stack. The middleware has been designed considering an analysis of the technical characteristics of the most important IoT protocols. From the design point of view, a modular architectural methodology and a technology-independent approach have been adopted to build the middleware, so that it can be easily deployed and managed in IoT environments with a low integration effort. A first proof of concept of the middleware is presented for two IoT protocols, demonstrating interoperability between them. The results show that the existence of the middleware ensures technical interoperability without a significant impact on the degradation of communications under an unstable network environment and with a large number of nodes transmitting at the same time.
In the coming days, 5G networking needs faster software automation in the existing environment. With this view in this paper, an attempt has been made to formulate an approach for enhancing the HTTP based monitoring without affecting the current services. The automation can be performed using modern web solutions. A node is considered as the smallest host inside an intranet and internet network based on the physical or logical grouping of multiple networks. It acts as host computers when identified by an IP address (ipv4 or ipv6) and when connected with the host to many clients it is identified through its network subnets. The communication among these nodes can be improved by using UDP based HTTP3.0 along with TLS 1.3 for GET or POST requests through UDP streams. The traditional HTTP stack ordinary monitoring can be upgraded through QUIC Protocol for a faster and more efficient approach in future networks and real-time monitoring. In the QUIC based HTTPS scenario, it has been observed that the load time takes less than 200 ms in network latency, which results in a faster approach as compared to handshake between host to client and vice versa during the previous HTTP introduced approaches. The slow response time results in wait, which causes a penalty. The suggested approach can be beneficial at a network node for monitoring the connected nodes in the network by sending QUIC protocol-based transport layer beacons in certain time-lapse, resulting better and faster alerting in information technology infrastructures.
Localization via trilateration determines the location of moving objects using the distances between each object and multiple stations. Since low-power wireless technologies are the primary enablers of these localization methods, the technology’s type and characteristics highly affect trilateration accuracy. In addition, pre-processing the collected data can also be used as an effective method to enhance system accuracy. This paper presents an effective way of tracking objects using trilateration in indoor environments. We analyze the data generated from the stations, including coordinates, timestamps, and identifiers. After running a clustering algorithm on the data, we infer information on the object’s behavior, frequently visited places, and predict objects’ location. Field testing results at Santa Clara University demonstrate that accuracy is increased in the range of 20 to 40% when applying the pre-processing method.
The Internet of things (IoT) is an expansion and extension based on the Internet, from network interconnection to the interrelationship of things. Most of the Internet of Things are using the publish/subscribe model, which stipulates the one-to-many situation of nodes in the Internet of Things’ uses a publish/subscribe model to achieve communication, using Broker as a relay and topic as a designated transmission path to deliver information to subscribers. But when a large amount of data is being transmitted, there will be node congestion. This will not only reduce the efficiency of data transmission, but also increase and waste the energy consumption of the entire Internet of Things. Therefore, this paper proposes topic logistics based on node resource status, and designs a new network data transmission algorithm. Based on the value of node resource status, it realizes the selection of possible data communication paths. It is verified through experiments that this algorithm can realize node resources. The full utilization of, thereby reducing communication energy consumption and improving transmission efficiency.
Abstract. Since the Industry 4.0 nature is a world-scale phenomenon, lot of information
are available today from several sources, presenting different point of view. From the
scientific papers, the research is focused more on the theoretical steps for a future implementation
and the benefits achievable, with important information on the development
path followed by the Industry to reach the today situation. Other important resources are
represented by the companies operating in the consultant and high-tech sectors, because
the revolution is completely intertwined with the digital world and their reports can provide
interesting information. At the end, the government reports of the most important
manufacturing countries have been a good information source for the practical steps and
the necessary requirements in order to create a favorable field for the implementation.
Therefore, this chapter is intended to contribute over all these mentioned areas of
knowledge, providing a brief state of the arts regarding the Industry 4.0, the role of IoT
and Cloud computing in today’s and future factories, as well as a view along all those
enabling technologies that complement among each other in the diverse industrial scenarios.
Keywords: State-of-the-Art, Asset Management, Cloud & IoT, Lean Manufacturing,
Industry 4.0, Maintenance, Uncertainty.
Security has become a critical factor in today's computation systems. The security threats that risk our confidential information can come in form of seemingly legitimate client request to server. While illegitimate requests consume the number of connections a server can handle, no valid new connections can be made. This scenario, named SYN-flooding attacks can be controlled through a fair scheduling algorithm that provides more opportunity to legal requests. This paper proposes a detailed scheduling approach named Largest Processing Time Rejection-Particle Swarm Optimization (LPTR-PSO) that defends the server against varying intensity SYN-flood attack scenarios through a three-phased algorithm. This novel approach considers the number of half-open connections in the server buffer and chooses a phase accordingly. The simulation results show that the proposed defense strategy improves the performance of under attack system in terms of memory occupancy of legal requests and residence time of attack requests.
The proliferation of embedded systems, wireless technologies, and Internet protocols have enabled the Internet of Things (IoT) to bridge the gap between the virtual and physical world through enabling the monitoring and actuation of the phys5 ical world controlled by data processing systems. Wireless tech6 nologies, despite their offered convenience, flexibility, low cost, and mobility pose unique challenges such as fading, interference, energy, and security, which must be carefully addressed when using resource-constrained IoT devices. To this end, the efforts of the research community have led to the standardization of several wireless technologies for various types of application domains depending on factors such as reliability, latency, scalability, and energy efficiency. In this paper, we first overview these standard wireless technologies, and we specifically study the MAC and physical layer technologies proposed to address the requirements and challenges of wireless communications. Furthermore, we explain the use of these standards in various application domains, such as smart homes, smart healthcare, industrial automation, and smart cities, and discuss their suitability in satisfying the requirements of these applications. In addition to proposing guidelines to weigh the pros and cons of each standard for an application at hand, we also examine what new strategies can be exploited to overcome existing challenges and support emerging IoT applications.
The significant growth in the number of WiFi-enabled devices as well as the increase in the traffic conveyed through wireless local area networks (WLANs) necessitate the adoption of new network control mechanisms. Specifically, dense deployment of access points, client mobility, and emerging QoS demands bring about challenges that cannot be effectively addressed by distributed mechanisms. Recent studies show that software-defined WLANs (SDWLANs) simplify network control, improve QoS provisioning, and lower the deployment cost of new network control mechanisms. In this paper, we present an overview of SDWLAN architectures and provide a qualitative comparison in terms of features such as programmability and virtualization. In addition, we classify and investigate the two important classes of centralized network control mechanisms: (i) association control (AsC) and (ii) channel assignment (ChA). We study the basic ideas employed by these mechanisms, and in particular, we focus on the metrics utilized and the problem formulation techniques proposed. We present a comparison of these mechanisms and identify open research problems.
Profiling and minimizing the energy consumption of IoT devices is an essential step towards employing IoT in various application domains. In this paper we propose EMPIOT, an accurate, low-cost, easy to build, and flexible, power measurement platform. We present the hardware and software components of this platform, and study the effect of various design parameters on accuracy. In particular, we analyze the effect of driver, bus speed, input voltage, and buffering mechanism, on sampling rate, measurement accuracy and processing demand. These extensive experimental studies enable us to configure the system in order to achieve its highest performance. We also propose a novel calibration technique and report the calibration parameters under various settings. Using five different IoT devices performing four types of workloads, we evaluate the performance of EMPIOT against the ground truth obtained from high-accuracy devices. Our results show that, for very low-power devices that utilize 802.15.4 wireless standard, measurement error is less than 4%. In addition, for 802.11-based devices that generate short and high power spikes, error is less than 3%.
In order to minimize the downloading time of short-lived applications like web browsing, web application and short video clips, the recently standardized HTTP/2 adopts stream multiplexing on one single TCP connection. However, aggregating all content objects within one single connection suffers from the Head-of-Line blocking issue. QUIC, by eliminating such an issue on the basis of UDP, is expected to further reduce the content downloading time. However, in mobile network environments, the single connection strategy still leads to a degraded and high variant completion time due to the unexpected hindrance of congestion window growth caused by the common but uncertain fluctuations in round trip time and also random loss event at the air interface. To retain resilient congestion window against such network fluctuations, we propose an intelligent connection management scheme based on QUIC which not only employs adaptively multiple connections but also conducts a tailored state and congestion window synchronization between these parallel connections upon the detection of network fluctuation events. According to the performance evaluation results obtained from an LTE-A/Wi-Fi testing network, the proposed multiple QUIC scheme can effectively overcome the limitations of different congestion control algorithms (e.g. the loss-based New Reno/CUBIC and the rate-based BBR), achieving substantial performance improvement in both median (up to 59.1%) and 95th completion time (up to 72.3%). The significance of this piece of work is to achieve highly robust short-lived content downloading performance against various uncertainties of network conditions as well as with different congestion control schemes.
We present our experience with QUIC, an encrypted, multiplexed, and low-latency transport protocol designed from the ground up to improve transport performance for HTTPS traffic and to enable rapid deployment and continued evolution of transport mechanisms. QUIC has been globally deployed at Google on thousands of servers and is used to serve traffic to a range of clients including a widely-used web browser (Chrome) and a popular mobile video streaming app (YouTube). We estimate that 7% of Internet traffic is now QUIC. We describe our motivations for developing a new transport, the principles that guided our design, the Internet-scale process that we used to perform iterative experiments on QUIC, performance improvements seen by our various services, and our experience deploying QUIC globally. We also share lessons about transport design and the Internet ecosystem that we learned from our deployment.
This article is summarized in: the morning paper
an interesting/influential/important paper from the world of CS every weekday morning, as selected by Adrian Colyer
Industrial applications and cyber-physical systems rely on real-time wireless networks to deliver data in a timely and reliable manner. However, existing solutions provide these guarantees only for stationary nodes. In this paper, we present REWIMO, a solution for real-time and reliable communications in mobile net- works. REWIMO has a two-tier architecture composed of (i) infrastructure nodes and (ii) mobile nodes that associate with infrastructure nodes as they move. REWIMO employs an on-join bandwidth reservation ap- proach and benefits from a set of techniques to efficiently reserve bandwidth for each mobile node at the time of its admission and over its potential communication paths. To ensure association of mobile nodes with infrastructure nodes over high-quality links, REWIMO uses the two-phase scheduling technique to coordinate neighbor discovery with data transmission. To mitigate the overhead of handling network dy- namics, REWIMO employs an additive scheduling algorithm, which is capable of additive bandwidth reser- vation without modifying existing schedules. Compared to the algorithms used by static real-time wireless networks, the techniques and the algorithms employed by REWIMO result in a significant increase in real- time capacity, enhanced reliability, and considerably faster handling of network dynamics.
The Stream Control Transmission Protocol (SCTP) is a Transport Layer protocol that has been proposed as an alternative to the Transmission Control Protocol (TCP) for the Internet of Things (IoT). SCTP, with its four-way handshake mechanism, claims to protect the Server from a Denial-of-Service (DoS) attack by ensuring the legitimacy of the Client, which has been a known issue pertaining to the three-way handshake of TCP. This paper compares the handshakes of TCP and SCTP to discuss its shortcomings and strengths. We present an Uppaal model of the TCP three-way handshake and SCTP four-way handshake and show that SCTP is able to cope with the presence of an Illegitimate Client, while TCP fails. The results confirm that SCTP is better equipped to deal with this type of attack.
Representational state transfer (REST) is a wide-spread architecture style for decentralized applications. REST proposes the use of a fixed set of service interfaces to transfer heterogeneous resource representations instead of defining custom interfaces for individual applications. This paper explores the advantages of RESTful architectures, i.e., service-oriented software architectures comprised RESTful services, in industrial settings. These include communication advantages such as reduced communication overhead and the possibility to introduce caching layers, and system design advantages including stable service interfaces across applications and the use of resource-oriented information models in cyber-physical systems. Additionally, a RESTful extension to the open platform communications (OPC) unified architecture (OPC UA) binary protocol is proposed in order to leverage these advantages. It requires only minimal modifications to the existing OPC UA stacks and is fully backward compatible with the standard protocol. Performance benchmarks on industrial hardware show a throughput increase up to a factor of eight for short-lived interactions. This reduction of overhead is especially relevant for the use of OPC UA in the emerging Industrial Internet of Things.
Robot communication is an essential element in robot operation. There are several protocols that serve robot communication applications, but the protocols used are not optimized for mobile and battery-operated robots. To operate in such condition, an optimized protocol for such environment must be used. This paper will evaluate Constrained Application Protocol (CoAP) and MQ Telemetry Transport for Sensor Nodes (MQTT-SN) which are designed for such devices. Result from experiment shows that MQTT-SN performs 30% faster than CoAP when transmitting the same payload.
Message oriented middleware (MOM) refers to the software infrastructure supporting sending and receiving messages between distributed systems. AMQP and MQTT are the two most relevant protocols in this context. They are extensively used for exchanging messages since they provide an abstraction of the different participating system entities, alleviating their coordination and simplifying the communication programming details. These protocols, however, have not been thoroughly tested in the context of mobile or dynamic networks like vehicular networks. In this paper we present an experimental evaluation of both protocols in such scenarios, characterizing their behavior in terms of message loss, latency, jitter and saturation boundary values. Based on the results obtained, we provide criteria of applicability of these protocols, and we assess their performance and viability. This evaluation is of interest for the upcoming applications of MOM, especially to systems related to the Internet of Things.
Wireless sensor networks (WSNs) typically consist of sensor nodes and gateways that operate on devices with limited resources. As a result, WSNs require bandwidth-efficient and energy-efficient application protocols for data transmission. Message Queue Telemetry Transport (MQTT) and Constrained Application Protocol (CoAP) are two such protocols proposed for resource-constrained devices. In this paper, we design and implement a common middleware that supports MQTT and CoAP and provides a common programming interface. We design the middleware to be extensible to support future protocols. Using the common middleware, we conducted experiments to study the performance of MQTT and CoAP in terms of end-to-end delay and bandwidth consumption. Experimental results reveal that MQTT messages have lower delay than CoAP messages at lower packet loss rates and higher delay than CoAP messages at higher loss rates. Moreover, when the message size is small and the loss rate is equal to or less than 25%, CoAP generates lower additional traffic than MQTT to ensure message reliability.
The Internet of Things (IoT) is the next wave of innovation that promises to improve and optimize our daily life based on intelligent sensors and smart objects working together. Through Internet Protocol (IP) connectivity, devices can now be connected to the Internet, thus allowing them to be read, controlled, and managed at any time and at any place. Security is an important aspect for IoT deployments. However, proprietary security solutions do not help in formulating a coherent security vision to enable IoT devices to securely communicate with each other in an interoperable manner. This paper gives an overview of the efforts in the Internet Engineering Task Force (IETF) to standardize security solutions for the IoT ecosystem. We first provide an in-depth review of the communication security solutions for IoT, specifically the standard security protocols to be used in conjunction with the Constrained Application Protocol (CoAP), an application protocol specifically tailored to the needs of adapting to the constraints of IoT devices. Since Datagram Transport Layer Security (DTLS) has been chosen as the channel security underneath CoAP, this paper also discusses the latest standardization efforts to adapt and enhance the DTLS for IoT applications. This includes the use of 1) raw public key in DTLS; 2) extending DTLS record Layer to protect group (multicast) communication; and 3) profiling DTLS for reducing the size and complexity of implementations on embedded devices. We also provide an extensive review of compression schemes that are being proposed in IETF to mitigate message fragmentation issues in DTLS.
Low-power wireless communications have particular characteristics that highly affect the performance of network protocols. However, many of these essential characteristics have not been considered in the existing simulation platforms and analytical performance evaluation models. While this issue invalidates many of the reported evaluation results, it also impedes pre-deployment performance prediction and parameter adjustment. Accordingly, this paper studies, analyzes and proposes models for accurate modeling of low-power wireless communications. Our contributions are six-fold: (i) We investigate the essential characteristics of low-power wireless transceivers, (ii) we present a classified and detailed study on modeling signal propagation, noise floor, system variations and interference, (iii) we highlight the importance and effects of system variations and radio irregularity on the real applications of wireless sensor networks, (iv) we reveal the inaccuracy of the packet reception algorithms used in the existing simulators. Furthermore, we propose an improved packet reception algorithm and we confirm its accuracy through comparison with empirical results, (v) we propose an architecture to integrate and implement the models presented in this paper and (vi) we show that the transitional region can be employed by the simulators to confine the propagation range and improve simulation scalability. To the best of our knowledge this is the first work that reveals the essentials of accurate modeling and evaluation of low-power wireless communications.
Following the vision of an Internet of Things (IoT) real world objects are integrated into the Internet to provide data as sensors and to manipulate the real world as actors. While current IoT approaches focus on the integration of things based on service technologies, scenarios in domains like smart cities, automotive or crisis management require service platforms involving real world objects, backend-systems and mobile devices. In this paper we introduce a service platform based on the Extensible Messaging and Presence Protocol (XMPP) for the development and provision of services for such pervasive infrastructures. We argue for XMPP as protocol for unified, real-time communication and introduce the major concepts of our platform. Based on two case studies we demonstrate real-time capabilities of XMPP for remote robot control and service development in the e-mobility domain.
Cloud computing is among the hottest trends in ICT, aiming at providing on-demand computing and storage resources with guarantees on the quality of service. A limit of current Cloud implementations is the absence of mechanisms to effectively manage inputs from the physical world. Our idea is to move towards a pervasive Cloud, providing facilities and solutions able to interact with the surrounding environment enabling development of new and value added services. In this vision also mobile devices, such as PDAs, usually equipped with several sensors and actuators, have to be included in the overall picture. Mobile devices and their respective owners can decide whether, how and when to contribute to the Cloud, thus introducing further unknowns. In order to deal with all such issues, in this paper we propose a solution that gives way to the Sensing and Actuation as a Service (SAaaS) paradigm, a step towards the creation of a Cloud of sensors and actuators. This paper mainly focuses on the implementation of the underlying infrastructure at the basis of the SAaaS. An ad-hoc architecture and some preliminary background on this challenging vision are provided and discussed.
Web services are designed to provide rich functionality for organizations and support interoperable interactions over a network. Web services are mainly realized in two ways: 1) SOAP-based services and 2) RESTful services. For the service providers, RESTful services can improve system flexibility, scalability, and performance as compared to the SOAP-based Web services. It is equally attractive to end users as it is consume less resources (i.e., battery, processor speed, and memory). Additionally, REST-based services do not include complex standards and heterogeneous operations; and hence are easier to consume and compose as compared to SOAP-based Web services. We provide an approach to migrate SOAP-based services to RESTful services. We identify resources from a SOAP-based Web service by analyzing its service description and mapping the contained operations to resources and HTTP methods. To demonstrate the effectiveness of our approach, we conduct a case study on a set of publicly available SOAP-based Web services. The results of our case study show that our approach can achieve high accuracy of identifying RESTful services from the interfaces of SOAP-based services. Our approach can improve the performance for invoking Web services after SOAP-based services are migrated to RESTful services.
High-speed networks with large delays present a unique environment where TCP may have a problem utilizing the full bandwidth. Several congestion control proposals have been suggested to remedy this problem. The existing protocols consider mainly two properties: TCP friendliness and bandwidth scalability. That is, a protocol should not take away too much bandwidth from standard TCP flows while utilizing the full bandwidth of high-speed networks. This work presents another important constraint, namely, RTT (round trip time) unfairness where competing flows with different RTTs may consume vastly unfair bandwidth shares. Existing schemes have a severe RTT unfairness problem because the congestion window increase rate gets larger as the window grows ironically the very reason that makes them more scalable. RTT unfairness for high-speed networks occurs distinctly with drop tail routers for flows with large congestion windows where packet loss can be highly synchronized. After identifying the RTT unfairness problem of existing protocols, This work presents a new congestion control scheme that alleviates RTT unfairness while supporting TCP friendliness and bandwidth scalability. The proposed congestion control algorithm uses two window size control policies called additive increase and binary search increase. When the congestion window is large, additive increase with a large increment ensures square RTT unfairness as well as good scalability. Under small congestion windows, binary search increase supports TCP friendliness. The simulation results confirm these properties of the protocol.
The stream control transmission protocol (STCP) is being standardized by the IEFT as a reliable transport protocol to transport SS7signaling messages over IP networks. Due to its attractive features such as multistreaming and multihoming, SCTP has received much attention from the network community, in terms of both research and development. This article introduces the main features of SCTP, and discusses the state of the art in SCTP research and development activities. We also provide a survey of the available products that use SCTP. Finally with a view to stimulating further research in this area, the challenges faced by the SCTP research community are identified.
RFC 2001 [RFC2001] documents the following four intertwined TCP congestion control algorithms: Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery. RFC 2581 [RFC2581] explicitly allows certain modifications of these algorithms, including modifications that use the TCP Selective Acknowledgement (SACK) option [MMFR96], and modifications that respond to "partial acknowledgments" (ACKs which cover new data, but not all the data outstanding when loss was detected) in the absence of SACK. This document describes a specific algorithm for responding to partial acknowledgments, referred to as NewReno. This response to partial acknowledgments was first proposed by Janey Hoe in [Hoe95]. 1. Introduction For the typical implementation of the TCP Fast Recovery algorithm described in [RFC2581] (first implemented in the 1990 BSD Reno release, and referred to as the Reno algorithm in [FF96]), the TCP data sender only retransmits a packet after a retransmit timeout has occurred, or afte...
In recent years, Internet of Things (IoT) industry has developed rapidly thanks to the rise of the smart objects and devices with processing, sensing and actuating capabilities. In order to satisfy a broad range of applications, a variety of application layer protocols has been taken into consideration, since IoT still does not have widely accepted standard protocol. One of prime candidate solutions is HTTP, as a well-known, fundamental client-server protocol and the protocol that is the most compatible with existing network infrastructure. Due to strict IoT specific requirements, however, a detailed characterization of the performance of HTTP for IoT applications is required. This paper presents a detailed analysis of throughput and latency for HTTP/1.1 with pipelining, by evaluating the impact that pipelining factor has on the latency. Based on these performance results, we analyze whether this HTTP/1.1 model should be implemented in IoT systems with significant latency constraints.
Advanced Message Queue Protocol (AMQP) is an open-standard application layer protocol for IoT focusing on message-oriented middleware. It provides asynchronous publish/subscribe communication with messaging. It is store-and-forward feature that ensures reliability even after network disruptions, which is its main advantage. When compared all other IoT protocols with AMQP protocol, it gives better performance. In this paper, we provide features for some cases or situations like when any client disconnected ungracefully or when any client connected and subscribed for a particular topic which it is interested in. This is because these features are used to notify other client(s) about disconnected client and help newly subscribed clients to get a status update immediately after subscribing and do not have to wait until the publishing clients send the new update. So AMQP protocol provides the guarantee of message delivery and provides reliable communication even after a network failure.
In today's Internet, there are many challenges such as low-latency support for interactive communication, security and privacy of user data, as well as development and deployment of new transport mechanisms. Quick UDP Internet Connections (QUIC) is a new transport protocol that addresses these challenges, focusing on HTTP/2 transmission as a first use case. The first QUIC working group meeting took place at IETF-97 in November 2016, and it has begun the standardization process. This article introduces the key features of QUIC and discusses the potential challenges that require further consideration.
New paradigms in networking industry, such as Software Defined Networking (SDN) and Network Functions Virtualization (NFV), require the hypervisors to enable the execution of Virtual Network Functions in virtual machines (VMs). In this context, the virtual switch function is critical to achieve carrier grade performance, hardware independence, advanced features and programmability. SnabbSwitch is a virtual switch designed to run in user space with carrier grade performance targets, based on an efficient architecture which has driven the development of vhost-user (now also adopted by OVS-DPDK, the user space implementation of OVS based on Intel DPDK), easy to deploy and to program through its Lua scripting layer. This paper presents the SnabbSwitch virtual switch implementation along with its novelties (the vhost-user implementation and the usage of a trace compiler) and code optimizations, which have been merged in the mainline project repository. Extensive benchmarking activities, whose results are included in this paper, have been carried on to compare SnabbSwitch with other virtual switching solutions (i.e., OVS, OVS-DPDK, Linux Bridge, VFIO and SR-IOV). These results show that SnabbSwitch performs as well as hardware based solutions, such as SR-IOV and VFIO, while allowing for additional functional and flexible operation; they show also that SnabbSwitch is faster than the vhost-user based version (user space) of OVS-DPDK.
CoAP is a lightweight RESTful application layer protocol devised for the IoT. Operating on top of UDP, CoAP must handle congestion control by itself. The core CoAP specification defines a basic congestion control mechanism, but it is not capable of adapting to network conditions. However, IoT scenarios exhibit significant resource constraints, which pose new challenges on the design of congestion control mechanisms. In this article we present CoCoA, an advanced congestion control mechanism for CoAP being standardized by the Internet Engineering Task Force CoRE working group. CoCoA introduces a novel round-trip time estimation technique, together with a variable backoff factor and aging mechanisms in order to provide dynamic and controlled retransmission timeout adaptation suitable for the peculiarities of IoT communications. We conduct a comparative performance analysis of CoCoA and a variety of alternative algorithms including state-of-the-art mechanisms developed for TCP. The study is based on experiments carried out in real testbeds. Results show that, in contrast to the alternative methods considered, CoCoA consistently outperforms the default CoAP congestion control mechanism in all evaluated scenarios.
The traditional approach to build a secure connection is to run a key exchange protocol and, once the key has been established, to use this key afterwards in a secure channel protocol. The security of key exchange and channel protocols, and to some extent also of the composition of both, has been scrutinized extensively in the literature. However, this approach usually falls short of capturing some key exchange protocols in which, due to practical motivation, the originally separated phases become intertwined and keys are established continuously. Two prominent examples of such protocols are TLS (with resumption), and Google's recently proposed low-latency protocol QUIC. In this work we revisit the previous security of model of Brzuska et al. (CCS'11) and expand it into a multi-stage key exchange model in the style of Bellare and Rogaway. In our model, parties can establish multiple keys in different stages and use these keys between stages, even to establish the next key. The advantage of using the formalization of Brzuska et al. is that it has been designed with the aim to provide compositional guarantees. Hence, we can, too, give sufficient conditions under which multi-stage key exchange protocols compose securely with any symmetric-key application protocol, like a secure channel protocol. We then exercise our model for the case of the QUIC protocol. Basically, we show that QUIC is an adequately secure multi-stage key exchange protocol and meets the suggested security properties of the designers. We continue by proposing some slight changes to QUIC to make it more amenable to our composition result and to allow reasoning about its security as a combined connection establishment protocol when composed with a secure channel protocol.
As the Internet of Things (IoT) evolves to encompass ever increasing quantities of smart devices, sensors and other smart objects, attention must be paid to considering what kinds of wireless networks should be employed, and the data transfer protocols to be used to allow communication among these entities. It is highly important that energy consumption for communication remains as minimal as possible. In this paper we present power consumption measurements in end devices, when REST-based resource retrieval is performed with HTTP and CoAP over 3GPP EDGE, HSPA and LTE networks. Our findings are based on actual measurements taken over the radio interface of a mobile handset in live cellular networks, and show that for a few transactions of small packet sizes, HTTP performs comparatively well in terms of power consumption. Also, power consumption is lowest in the handset when EDGE is used, but an LTE network with operator assisted power savings approaches power consumption levels seen with EDGE. Finally, for sessions consisting of large number of transactions, we show that using CoAP over the WebSocket protocol results in significantly less power consumption compared to HTTP.
The Computer Laboratory, University of Cambridge hosted a workshop on "Internet on the Move" on September 22, 2012. The objective of the workshop was to bring academia, industry and regulators to discuss the challenges in realizing the notion of ubiquitous mobile Internet. The editorial summarises a general overview of the issues discussed on enabling universal mobile coverage and some of the solutions that have been proposed to alleviate the problem of having ubiquitous mobile connectivity.
This document describes HMAC, a mechanism for message authentication using cryptographic hash functions. HMAC can be used with any iterative cryptographic hash function, e.g., MD5, SHA-1, in combination with a secret shared key. The cryptographic strength of HMAC depends on the properties of the underlying hash function.
Abstract lwIP is an implementation of the TCP/IP protocol stack. The focus of the lwIP stack is to reduce memory usage and code size, making lwIP suitable for use in small clients with very limited resources such as embedded systems. In order to reduce processing and memory demands, lwIP uses a tailor made API that does not require any data copying. This report describes the design and implementation of lwIP. The algorithms and data structures used both in the protocol implementations and in the sub systems such as the memory,and bufier management,systems are described. Also included in this report is a reference manual for the lwIP API and some code examples of using lwIP. Contents
Many signaling protocols in IP networks need a protection against message loss, but they do not require a strict in-sequence data delivery. Since TCP provides reliable in-order transport, end-to-end delays may be unnecessarily increased due to head-of-line blocking. An alternative transport protocol is SCTP, which is optimized for signaling applications and provides mechanisms for reliable, partial-ordered or unordered message delivery. In this paper, we quantify the impact of head-of-line blocking on the response time of transaction-based signaling applications. In order to mitigate this problem, we compare different solutions based on TCP and SCTP. Both a new analytical model and measurements on state-of-the-art operating systems show to which extend SCTP can improve transport delays by leveraging transmission over multiple parallel streams or using unordered data delivery. Our analysis reveals that using one or multiple parallel TCP connections can result in much higher end-to-end delays, even for moderate packet loss probabilities. We also observe significant differences in the TCP performance of different operating systems.
When a message is transformed into a ciphertext in a way designed to protect both its privacy and authenticity, there may be additional information, such as a packet header, that travels alongside the ciphertext (at least conceptually) and must get authenticated with it. We formalize and investigate this authenticated-encryption with associated-data (AEAD) problem. Though the problem has long been addressed in cryptographic practice, it was never provided a definition or even a name. We do this, and go on to look at efficient solutions for AEAD, both in general and for the authenticated-encryption scheme OCB. For the general setting we study two simple ways to turn an authenticated-encryption scheme that does not support associated-data into one that does: nonce stealing and ciphertext translation. For the case of OCB we construct an AEAD-scheme by combining OCB and the pseudorandom function PMAC, using the same key for both algorithms. We prove that, despite "interaction" between the two schemes when using a common key, the combination is sound. We also consider achieving AEAD by the generic composition of a nonce-based, privacy-only encryption scheme and a pseudorandom function.
An Adaptation Model for Mobile IPv6 Support in lowPANs
- R Silva
- J M Silva
R. Silva, J. M. Silva, An Adaptation Model for Mobile IPv6 Support in lowPANs,
2009. https://tools.ietf.org/id/draft-silva-6lowpan-mipv6-00.html
- A Dunkels
A. Dunkels, Full TCP/IP for 8-bit Architectures, in: Proceedings of the 1st International Conference on Mobile Systems, Applications and Services, ACM, 2003,
pp. 85-98.
The Secure Sockets Layer (SSL) Protocol Version 3.0
- A Freier
- P Karlton
- P Kocher
A. Freier, P. Karlton, P. Kocher, RFC 6101: The Secure Sockets Layer (SSL) Protocol Version 3.0, [Online]. Available: http://tools.ietf.org/html/rfc6101 2011.
- S Radhakrishnan
- Y Cheng
- J Chu
- A Jain
- B Raghavan
S. Radhakrishnan, Y. Cheng, J. Chu, A. Jain, B. Raghavan, TCP Fast Open, in:
Proceedings of the Seventh Conference on Emerging Networking Experiments
and Technologies, 2011, p. 21.
Seamblue: Seamless Bluetooth Low Energy Connection Migration for Unmodified IoT Devices
- S R Hussain
- S Mehnaz
- S Nirjon
- E Bertino
S.R. Hussain, S. Mehnaz, S. Nirjon, E. Bertino, Seamblue: Seamless Bluetooth
Low Energy Connection Migration for Unmodified IoT Devices, in: Proceedings
of the International Conference on Embedded Wireless Systems and Networks
(EWSN), 2017, pp. 927-944.
Design of an FPGA based Embedded System for protecting the server from SYN flood attack
- S V Chimkode
S.V. Chimkode, Design of an FPGA based Embedded System for protecting the
server from SYN flood attack, Goa University, 2017 Ph.D. thesis.
Analysis of TCP issues in internet of things
- D S S R A R Nageswara
- Lakshminadh
D.S.S.R.A.R. Nageswara K LakshmiNadh, Analysis of TCP issues in internet of
things, Int. J. Pure Appl. Math. 118 (14) (2018).
- Z Shelby
- K Hartke
- C Bormann
Z. Shelby, K. Hartke, C. Bormann, RFC 7252: The Constrained Application Protocol (CoAP), [Online]. Available: http://www.rfc-editor.org/info/rfc7252 2014.
- T Dierks
- E Rescorla
T. Dierks, E. Rescorla, RFC 5246: The Transport Layer Security (TLS) Protocol,
[Online]. Available: https://tools.ietf.org/html/rfc5246 2008.
Datagram Transport Layer Security Version 1.2
- E Rescorla
- N Modadugu
E. Rescorla, N. Modadugu, RFC 6347: Datagram Transport Layer Security Version 1.2, [Online]. Available: https://tools.ietf.org/html/rfc6347 2012.
RFC: 6347 The Datagram Transport Layer Security (DTLS) Connection Identifier
- H T Eric Rescorla
H.T. Eric Rescorla, RFC: 6347 The Datagram Transport Layer Security
(DTLS) Connection Identifier, [Online]. Available: https://tools.ietf.org/html/
draft-ietf-tls-dtls-connection-id-00#page-3 2017a.
Datagram Transport Layer Security Version 1.2
- H T Eric Rescorla
H.T. Eric Rescorla, RFC 6347: Datagram Transport Layer Security Version 1.2,
[Online]. Available: https://tools.ietf.org/html/rfc6347 2017b.
The Chromium Project
Google, The Chromium Project, [Online]. Available: http://www.chromium.org/
developers/design-documents/dns-prefetching 2018.
QUIC: A UDP-based Multiplexed and Secure Transport
Google, QUIC: A UDP-based Multiplexed and Secure Transport, [Online]. Available: https://datatracker.ietf.org/doc/draft-ietf-quic-transport/ 2018.