Fig 2 - uploaded by Gianfranco Nencioni
Content may be subject to copyright.
Source publication
Software-defined networking (SDN) promises to improve the programmability and flexibility of networks, but it may bring also new challenges that need to be explored. The purpose of this technical report is to assess how the deployment of the SDN controllers affects the overall availability of SDN. For this, we have varied the number, homing and loc...
Contexts in source publication
Context 1
... this evaluation we consider the national backbone net- work depicted in Figure 2 and consists of 10 nodes across 4 cities, and two dual-homed SDN controllers. The nodes are located in the four major cities in Norway, Bergen (BRG), Trondheim (TRD), Stavanger (STV), and Oslo (OSL). ...
Context 2
... evaluate the impact of the connectivity and the redun- dancy of the SDN controllers in the national backbone network we consider the following case studies: 1) There is only one controller and it is connected to OSL1 2 ; 2) There are two single-homed controllers (SC1 connected to T RD 2 and SC2 connected to OSL1 2 ); 3) Reference scenario depicted in Figure 2; 4) The controllers are triple-homed (added connections from SC1 to BRG 1 and from SC2 to BRG 2 to the reference scenario); 5) The controllers are quadruple-homed (added connections from SC1 to ST V 1 and from SC2 to ST V 2 to the previous scenario); 6) There are three controllers (added controller connected to BRG 1 and to BRG 2 to the reference scenario); 7) There are four controllers (added controller connected to ST V 1 and to ST V 2 to the previous scenario); 8) There is one dual-homed controller (deleted SC2 from the reference scenario). Figure 3 shows the unavailability of SDN in the case studies. ...
Similar publications
Sistem informasi kepegawaian merupakan sebuah sistem yang bertujuan untuk mengelola data kepegawaian sebuah, kebutuhan akan informasi pada saat ini semakin meningkat hal ini memnuntut kinerja sebuah informasi untuk cepat dan dapat di dapat di percaya dalam mengelola informasi. Namun dalam hal ini pelaksanaan Sistem informasi kepegawaian di SDN BINA...
Software-defined networking (SDN) is a great innovation, which makes the network programmable so that it is easier to achieve failures recovery. Through pre-programmed recovery strategies and pre-deployed backup resource, flows can be redirected to destination quickly upon failures. However, it consumes a large amount of backup resources for fast f...
The emerging software defined vehicular networking
(SDVN) paradigm promises to dramatically
simplify network management and enable
innovation through network programmability.
Despite noticeable advances of SDNs in wired
networks, it is also becoming an indispensable
component that potentially provides flexible and
well managed next-generation wirel...
Citations
... Work by other authors that used Bayesian Network is presented by (Beuzen et al., 2018;Franke et al., 2012;Usman et al., 2017). Nencioni et al. (2017) investigated the Availability of Software Defined Networking, SDN. ...
... Dynamic policies have been applied to the network devices using numerous network optimization and improvement tasks such as network availability [10], MPLS optimization [11], load balancing in data centers [12], and resilience for smart grid communications [13]. To date, there has not been any significant development that uses ML in developing the dynamic policies. ...
... Controller redundancy and its effects on availability and performance was the subject of a number of research papers. The Nencioni et al. [35] present a study on the effect of the number of controllers, their connectivity and their locations within the network on availability. This study establishes the decisive effect of redundancy while demonstrating that too many backup controllers (from three controllers in the mentioned scenario) increase the operating cost without necessarily improving the availability. ...
... However, controller redundancy is not the optimal solution for dealing with malicious attacks since the backup controller may also be targeted by the same threat (mechanisms for intrinsic resiliency are more appropriate in this case). We have referred to some of the most relevant studies and researches on this topic and discussing their differences and complementarity [35,36,38,39]. The proposed solutions depend on the architecture as well as the size of the network and vary from a centralized and full redundant system to a decentralized system with strategies for load balancing and fault tolerance. ...
The SDN paradigm profoundly affects the architecture of networks in favor of more adaptability to the needs for new value-added services. This article examines the positive and negative impacts of such a change on network security. While few in-depth studies have attempted to cover this issue in a comprehensive way, we first tried to define the most relevant axes of analyses with regard to this concept, namely availability, access control and application services oriented security. In relation to these axes as well as to the state of the art of security, a number of researches and studies that have addressed this issue by proposing solutions through the OpenFlow specification are analyzed with the aim to highlight the real opportunities and the real challenges brought by this new concept for the network security.
... Many works address the controller placement problem in SDN, but with slightly different objectives. The works [14,15,16,17,18,19,20,21,22] target fault tolerance, whereas [23,24,25] aim at balancing the loads on the controllers. [26] strives for network resource minimization in mobile cellular networks. ...
We consider a distributed Software Defined Networking (SDN) architecture adopting a cluster of multiple controllers to improve network performance and reliability. Differently from previous work, we focus on the control traffic exchanged among the controllers, in addition to the Openflow control traffic exchanged between controllers and switches. We develop an analytical model to estimate the reaction time perceived at the switches due to the inter-controller communications, based on the data-ownership model adopted in the cluster. The model is then accurately validated in an operational Software Defined WAN (SDWAN). We advocate a careful placement of the controllers, taking into account the two above kinds of control traffic. We evaluate, for some real ISP network topologies, the possible delay tradeoffs for the controllers placement problem and we propose a novel evolutionary algorithm to find the corresponding Pareto frontier. Our work provides novel quantitative tools to optimize the plan and the design of the network supporting the control plane of SDN networks, especially when the network is very large and in-band control plane is adopted. We also show that for operational distributed controllers (e.g. OpenDaylight and ONOS), the location of the leader controller adopted in the background consensus algorithm has a strong impact on the reactivity perceived by switches.
... In addition to the forwarding nodes, there are two dual-homed SDN controllers (SC 1 and SC 2 ), which are connected to TRD and OSL1. We have considered two dual-homed SDN controllers based on the deployment consideration in [23], where the impact of the SDN controller deployment (number, connectivity to the transport network, and location) on the network availability is evaluated by using the two-level model proposed in [9]. In [23], the results highlight that from a network operator prospective the best solution for providing an availability similar to the one provided by a traditional IP network is by deploying two dual-homed SDN controllers and that the location of the SDN controllers has a marginal impact. ...
... We have considered two dual-homed SDN controllers based on the deployment consideration in [23], where the impact of the SDN controller deployment (number, connectivity to the transport network, and location) on the network availability is evaluated by using the two-level model proposed in [9]. In [23], the results highlight that from a network operator prospective the best solution for providing an availability similar to the one provided by a traditional IP network is by deploying two dual-homed SDN controllers and that the location of the SDN controllers has a marginal impact. ...
Software-Defined Networking (SDN) promises to improve the programmability and flexibility of networks, but also brings new challenges that need to be explored. The main objective of this paper is to include failure correlation in a quantitative assessment of the properties of SDN backbone networks to determine whether they can provide similar availability as the traditional IP backbone networks. To achieve this goal, this paper has formalised a two-level availability model that captures the global network connectivity without neglecting the essential details and which includes a failure correlation assessment. The paper proposes a modular and systematic approach for characterising the principal minimal-cut sets in both SDN and traditional networks, and Stochastic Activity Network (SAN) models for characterising the single network elements. To demonstrate the feasibility of the model, an extensive sensitivity analysis has been carried out on a national backbone network.
... The In both networks there are two dual-homed SDN controllers (SC1 and SC2). This choice has been taken accordingly a study on SDN controller configuration [19], where impact of the location, number, and homing of SDN controllers on the national backbone network is investigated. ...
Software-Defined Networking (SDN) promises to improve the programmability and flexibility of networks, but it may also bring new challenges that need to be explored. The main objective of this paper is to present a quantitative assessment of the properties of SDN backbone networks to determine whether they can provide similar availability to the traditional IP backbone networks. To achieve this goal, we have completed the following steps:
i) we formalized a two-level availability model that is able to capture the global network connectivity without neglecting the essential details;
ii) we proposed Markov models for characterizing the single network elements in both SDN and traditional networks;
iii) we carried out an extensive sensitivity analysis of a~national and a~world-wide backbone networks.
The results have highlighted the considerable impact of operational and management (O&M) failures on the overall availability of SDN. High O&M failure intensity may reduce the availability of SDN as much as one order of magnitude compared to traditional networks.
Moreover, the results show that the impact of software and hardware failures on the overall availability of SDN can be significantly reduced through proper overprovisioning of the SDN controller(s).
Every day challenges are increasingly progressing
in the modern world of today. Finding the identity of an
individual becomes compulsory in our societies. Therefore a
means for identifying and detecting one face becomes
necessary and even compulsory. Facial recognition problem is
among the top vital issues that today’s attention has been
focused, the need to identify faces in almost every sectors like
in military, education, commence and etc. become the work of
engineers or scientist to see all effort are put together in order
to obtained better accuracy of theses facial recognition models .
Algorithms deployed in the field of facial recognition research
area, do not give better or optimal performances. Then the use
of means like optimization becomes necessary even within the
selected or desired classification method. In this research,
Local Binary Pattern (LBP) was used for feature extraction
while Support Vector Machines (SVM) was used as a classifier.
However, it is important to find good values of the SVM hyper
parameters C and γ in order to obtain good results. Particle
Swarm Optimization (PSO) is proposed to optimize and choose
the best SVM hyper parameters. Results obtained using the
LBP-PSO-SVM pipeline gave a [C, γ], a mean-squared-error
of 0.028571 and an overall best accuracy of 98.33%.
Framework carried out in this research worked better than the
use of SVM alone, having less complexity with less time of
implementation.
Fifth-generation (5G) wireless networks are characterized by applying the software-defined-networking (SDN) and network-function-virtualization (NFV) concepts to provide higher reliability and scalability, and lower latency for advent data-hungry services. Since the originally proposed centralized architecture of SDN controller cannot fulfill those requirements, distributed architectures are presented where multiple SDN controllers across the network constitute the control layers. Furthermore, to fully achieve the network flexibility offered by SDN, we incorporate virtualized SDN (vSDN) controllers, enabled through the NFV technology. In vSDN with distributed architecture, controller placement is one of the main challenges, which is an NP-hard optimization problem with conflicting objectives: 1) maximizing the reliability of network with low latency; 2) minimizing the cost of implementation. In order to achieve such a compromise, in this work, we formulate the problem of vSDN controller placement and introduce some performance metrics to model the latency of communication between controller-switch pairs and also robustness against vSDN controller failures in a network. The introduced formulation is some sorts of submodular optimization, which is exploited to develop several algorithms. Simulations results demonstrate that, with a negligible performance loss, a significant reduction in the number of vSDN controllers is achievable. Finally, latency, cost, and robustness trade-offs are investigated.
In order to realize the fairness between multi-priority data streams and ensure the quality of service of multi-priority data streams under this new network architecture of SDN, it is necessary to study the scheduling strategy of multi-priority data streams and analyze the performance of network models under different scheduling strategies. In this paper, the network load balancing model of multi-priority data stream is established, and then the performance of data flow scheduling under this model is analyzed by using stochastic network calculus theory. The arrival curve and service curve of the data stream under the model are derived, and then the end-to-end delay and the end-to-end delay probability boundary of the data stream are obtained. finally, the correctness of the theoretical derivation is verified by numerical experiments.
