Table 2 - uploaded by Xiao Qin
Content may be subject to copyright.
Source publication
Security requirements of security-critical real-time applications must be met in addition to satisfying timing constraints. However, conventional real-time scheduling algorithms ignore the applications' security requirements. In recognition that an increasing number of applications running on clusters demand both real-time performance and security,...
Contexts in source publication
Context 1
... must be submitted from authenticated users and, thus, authentication services are deployed to authenticate users who wish to access clusters [9][11] [14]. Table 2 lists three authentication techniques: weak authentication using HMAC-MD5; acceptable authentication using HMAC- SHA-1, fair authentication using CBC-MAC-AES. Each authentication technique is assigned a security level based on the performance. ...
Context 2
... task T i requires q security services, which are provided in sequential order. It is to be noted that , , and in Equation (9) are derived from Equations (6)- (7) and Table 2. In section 5, Equation (9) will be used to calculated the earliest start times and minimal security overhead. ...
Citations
... Scheduling algorithms are divided into two categories, namely, dynamic scheduling [4] and static scheduling [5]. To satisfy a given SLA of real-time applications in distributed systems, scheduling mechanisms are responsible for ensuring that all tasks complete before their deadline [15]. Existing real-time scheduling algorithms found in the literature include both preemptive [2] and nonpreemptive [13]. ...
In this work we propose a two-phase scheduling technique (TOPS) for distributed real-time systems. The first phase of TOPS is in charge of producing a scheduling sequence, whereas the second phase aims to dispatch tasks to computing nodes of a distributed system. The two phases are independent of one another and; therefore, one can change a policy in one phase without configuring another phase. TOPS makes it possible to observe the impacts of sorting policies on the performance of scheduling policies. We implement a TOPS prototype, in which the first phase is comprised of three sorting policies and the second phase consists of two scheduling policies in the second phase. TOPS enables us to discover that combining the EDF (Earliest-Deadline-First) and AEAP (As-Early-As-Possible) policies leads to an optimized performance among all the six candidate algorithms.
... Scheduling algorithms are divided into two categories, namely, dynamic scheduling [26] [7] and static scheduling [8] [9]. To satisfy a given SLA of real-time applications in distributed systems, scheduling mechanisms are responsible for ensuring that all tasks are complete before their deadline [34]. Existing real-time scheduling algorithms found in the literature include both preemptive [4] and non-preemptive [31]. ...
In this work we propose a two-phase scheduling technique (TOPS) for distributed real-time systems. Our TOPS scheduling approach has two distinct phases. The first phase is in charge of producing a scheduling sequence, whereas the second phase aims to dispatch tasks to computing nodes of a distributed system. The second phase also judiciously determines the starting time of each task. One salient feature of our approach lies in high flexibility, which allows system developers to apply multiple policies in each phase. The two phases are independent of one another; therefore, one can change a policy in one phase without configuring another phase. With TOPS in place, we are able to observe the impacts of sorting policies on the performance of scheduling policies. We implement a prototype of TOPS, where the first phase is comprised of three sorting policies, and the second phase consists of two scheduling policies. TOPS enables us to discover that combining the EDF (earliest deadline first) and AEAP (as early as possible) policies leads to an optimized performance among all six candidate algorithms.
... Scheduling algorithms are divided into two categories, namely, dynamic scheduling [13][4] and static scheduling [5] [6]. To satisfy a given SLA of real-time applications in distributed systems, scheduling mechanisms are responsible for ensuring that all tasks are complete before their deadline [17]. Existing real-time scheduling algorithms found in the literature include both preemptive [2] and non-preemptive [15]. ...
In this work we propose a two-phase scheduling technique (TOPS) for distributed real-time systems. Our TOPS scheduling approach has two distinct phases. The first phase is in charge of producing a scheduling sequence, whereas the second phase aims to dispatch tasks to computing nodes of a distributed system. The second phase also judiciously determines the starting time of each task. One salient feature of our approach lies in high flexibility, which allows system developers to apply multiple policies in each phase. The two phases are independent of one another; therefore, one can change a policy in one phase without configuring another phase. Given a distributed system where there are K policies in phase one and L policies in phase two, the total number of scheduling algorithms offered by the two-phase mechanism is KL. An immediate benefit of this approach is that it makes it possible to independently and concurrently investigate sorting policies in phase one and scheduling policies in phase two. With TOPS in place, we are able to observe the impacts of sorting policies on the performance of scheduling policies. We implement a prototype of TOPS, where the first phase is comprised of three sorting policies, and the second phase consists of two scheduling policies. TOPS enables us to discover that combining the EDF and AEAP policies leads to an optimized performance among all six candidate algorithms.
... This may compromise the security of packets, especially for high-risk/critical applications. Consider a military use such as an aircraft control system [1] running on a parallel and distributed system [2,3]. Such applications need realtime information even over high latency links such as satellite communication, along with security requirement [4]. ...
... If a packet P satisfies property-1 on a node N j , then it is transferred to Q a . The arriving packets P has a tuple ha i ; Pt i ; D i ; Sl i i. 3 Therefore, the total processing time (T i j ) for the packet P i j can be calculated using Eq. 3 [8,16,20]: ...
Security is a major concern of modern real-time applications, besides requiring stringent latency bound. However, encryption algorithms are computation intensive task which impacts the timeliness of the real-time applications. Therefore, there exists a trade-off between the desired level of security and the service guarantee. In this paper, we propose a security-aware dynamic scheduling algorithm (SADSA) using a grid of computational elements (CEs) which performs this trade-off and tries to maximize the instantaneous average security level of the packets besides providing a guaranteed service. As packets arrive, we first assign them to the CEs based on the utilization value of a CE, which is the ratio of completion time and a deadline of the last packet in a CE. The security level of all the packets is then dynamically adjusted to meet the minimum required security level while maximizing the average security level of all the packets in that CE. We first show that the proposed assignment algorithm is NP-hard, is 2-competitive to the optimal solution, and that the proposed algorithm provides a sub-optimal solution. Further, using extensive simulation, we show that the proposed SADSA algorithm performs better in terms of guarantee ratio, average security level and overall performance compared to the existing algorithms.
... Security-aware scheduling strategy for real-time applications on clusters (SAREC) [30], proposes a security-aware scheduling strategy, or which integrates security requirements into scheduling for real-time applications by employing our security overhead model. Scheduling real-time data-intensive applications (SARDIG) is a security-attentive dynamic realtime scheduling algorithm architecture and a dynamic grid scheduling algorithm for providing security for real-time data-intensive applications [31]. ...
... The performance of the proposed method is compared with three well-known scheduling methods of the grid environment, namely Earlier Deadline First (EDF) [29] algorithms, Security-Aware scheduling strategy for Real-time applications on Clusters (SAREC) [30] and the Security of Real-Time Data-Intensive Applications on Grids (SARDIG) [31]. Table 2 shows the simulation results of the completeness ratio for the four algorithms. ...
: To maximize the utilization, reliability and availability of power resources, some distribution strategy has to be implemented, which is possible nowadays with the support of modern information technologies (IT). To further develop power utilization, the customer should be aware of efficient power utilization, and the problem of customer management has to be resolved, where payment of electric bills could be through online solutions. A customer-aware power regulatory model is proposed that provides awareness to the consumer regarding the usage of electrical energy, in a secure and reliable solution that combines the features of electrical engineering with cloud computing to ensure better performance in notifying issues, which is done based on location and enhances the operation of smart grids. Instant electric meters are equipped with remote gadgets which communicate with a central cloud administration to produce electric bills for the client. The model provides mindfulness by showing history/notifications and suggestions for energy utilization through the smart meters. The user is provided with security keys to view the reading values and pay bills. To make the solution more accessible, the electronic data will be maintained on various servers at different locations of the cloud. Subsequently, there will be a service provider who manages service requests. A hardwired electric meter transmits the electric readings, which in turn access the particular service to make an entry for the particular connection on the cloud. The usage data will also be maintained at different locations in the cloud, which are accessible to different levels of users with appropriate security measures. The user accessibility is controlled by a Third Party Auditor (TPA) that computes the trustworthiness of users using a trust management scheme. This article also proposes a hash function, which computes and verifies the signature of the keys submitted by the users and also has a higher completeness ratio, which reaches 0.93, than typical methods. This is noteworthy, and the investigation results prove the system’s proficiency in providing assured service.
... Security-aware scheduling strategy for real-time applications on clusters (SAREC) [30], proposes a security-aware scheduling strategy, or which integrates security requirements into scheduling for real-time applications by employing our security overhead model. Scheduling real-time data-intensive applications (SARDIG) is a security-attentive dynamic real-time scheduling algorithm architecture and a dynamic grid scheduling algorithm for providing security for real-time data-intensive applications [31]. ...
... The performance of the proposed method is compared with three well-known scheduling methods of the grid environment, namely Earlier Deadline First (EDF) [29] algorithms, Security-Aware scheduling strategy for Real-time applications on Clusters (SAREC) [30] and the Security of Real-Time Data-Intensive Applications on Grids (SARDIG) [31]. Table 2 shows the simulation results of the completeness ratio for the four algorithms. ...
To maximize the utilization, reliability and availability of power resources, some kind of distribution strategy has to be implemented, which is possible nowadays with the support of modern information technologies (IT). To further develop power utilization, the customer should aware about efficient power utilization and the problem of customer management has to be resolved, where payment of electric bills could be through online solutions. A customer-aware power regulatory model is proposed that provides awareness to the consumer regarding the usage of electrical energy, in a secure and reliable solution that combines the features of electrical engineering with cloud computing to ensure better performance in notifying issues, which is done based on location, and enhances the execution of smart grids. Instant electric meters are equipped with remote gadgets which communicate with the central cloud administration to produce electric bills for the client. The model provides mindfulness by showing history/notification and suggestions for energy utilization through the smart meters. The user is provided with security keys to view the reading values and pay bills. To make the solution more accessible, the electric data will be maintained on various servers at different locations of the cloud and subsequently there will be service provider who manages the service requests. A hardwired electric meter transmits the electric readings, which in turn access the particular service to make an entry for the particular connection at the cloud. The usage data will also be maintained at different locations in the cloud, which are accessible with appropriate security measures for different levels of users. The user accessibility is controlled by a Third Party Auditor (TPA) that computes the trustworthiness of users using a trust management scheme. This article also proposes a hash function, which computes and verifies the signature of the keys submitted by the users as well as it has a higher completeness ratio, which reaches 0.93, than typical methods. This is noteworthy and investigation results prove the proficiency in providing assured service.
... All these mechanisms cannot be applied in the hierarchical data collection model because the PO and the MDs cannot establish a direct connection. Xie et al. [19] depicted how a gadget builds up Joint keys with various controllers at different progressive levels. ...
... Security level is measured by total solicitations produced and finished. The execution of the proposed technique is contrasted and five well-known scheduling strategies for the grid environment, to be specific: security of real time data intensive applications on grids (SARDIG) [23], SAREC: a security-aware scheduling strategy for real-time applications on clusters [20], and earlier deadline first (EDF) [19] algorithms. Table 1 demonstrates the simulation parameters used to assess the proposed technique. ...
To expand the usage, reliability, availability of power resources and some distribution system must be met which is conceivable by the support of present day information technologies. This paper concentrates on client support and electricity distribution, where payment of electric bills (counting energy utilization every month or year and association points of interest) should be possible with online arrangements. It is proposed a protected and reliable solution which joins the elements of the electrical system with the network systems to give better execution on informing issues, which is done given demand location. The electric readings of the client will be upgraded each month in the database which is kept up in the distributed storage. The client will be furnished with security keys to see the perusing values and perform payment of bills. To make the solution more available, the dynamic information will be kept up on different servers in various areas of the cloud, and there will be a service supplier who deals with the service request. The hardwired electric meter transmits the electrical reading, which turn accesses the particular service to make an entry for the specific association at the cloud. The usage data will be kept up at various area of the cloud, which is accessible with security, measures various clients. The customer availability is controlled with SCADA. © 2018 Springer Science+Business Media, LLC, part of Springer Nature
... The absolute requirement of a security system is the guarantee of high data security; however, in cases in which WSNs are used, high data security affects the performance and lifetime of the system because a higher data-security level means greater energy consumption for cryptographic data functions [20], [21], [22]. The solution is to balance the use of resources through the security level of data [14], [23], which is basically used to offset the use of resources when their availability has entered a critical phase. The policy of applying a high level of security to each output affects the lifetime of a WSN because higher security levels of data put greater demands on the CPU and increase battery consumption [21]. ...
WSNs have five main components namely, sensing device, processor, memory, power supply, and transceiver. The power supply, processor, and memory are the main resources and have limited resources; therefore, resource availability in WSNs must be maintain. With limited resources available, the WSNs is required to be able to work as efficiently as possible, operated long time and secure due to its placement in extreme areas. Another challenge is choice, short time operation with strong security or long time operation with adaptable security. This article provides limited resource solutions to WSNs whose placement is in extreme areas that are impossible to do maintenances. As a solution, an adaptation approach to resource availability and security is use, as offered by the ARSy Framework. For testing using the component Raspberry pi 3 Model B and DS18B20 temperature sensor. The advantage the raspberry pi, because the CPU and Memory resources are large capacity. With these advantages are highly manageable and allow to integrate several types of sensors in one raspberry pi unit, and the battery resource becomes optional that will be used based on the design requirements, because the battery consumption is wasteful. The result of the research shows performance ARSy framework when compared to the system that works without ARSy framework mechanism.
Keywords: Extreme Area, WSN, ARSy Framework, Limited Resources, Resource Adaptation, Security Adaptation
... These advantages make WSNs very powerful; however, they also have many limitations, such as dependence on batteries as energy sources, smaller central processing unit (CPU) and memory capacity [5], security vulnerabilities [6,7], and radio inference [8,9]. Because of these limitations, a resource-aware policy [10][11][12][13] for adaptation mechanisms and security-aware policy [14][15][16][17] for data security based on the available resources of sensor nodes are required. ...
... The absolute requirement of a security system is the guarantee of high data security; however, in cases in which WSNs are used, high data security affects the performance and lifetime of the system because a higher data-security level means greater energy consumption for cryptographic data functions [3,33,34]. The solution is to balance the use of resources through the security level of data [14,15], which is basically used to offset the use of resources when their availability has entered Sensors 2018, 18, 1594 3 of 15 a critical phase. The policy of applying a high level of security to each output affects the lifetime of a WSN because higher security levels of data put greater demands on the CPU and increase battery consumption [33]. ...
... Determining the security level [15] is the last stage before data are sent to the data server. There are four security levels based on the availability of resources (see Table 3): level 3 is high security level, which is the most ideal because the output data sent to the data server have the maximum level of security, with the average resource availability of the network being 75-100%; level 2 is medium security level with the average resource availability being 50-75%; level 1 is low security level with average resource availability being 20-50%; and level 0 is very-low security level with ...
Wireless Sensor Networks (WSNs) with limited battery, central processing units (CPUs), and memory resources are a widely implemented technology for early warning detection systems. The main advantage of WSNs is their ability to be deployed in areas that are difficult to access by humans. In such areas, regular maintenance may be impossible; therefore, WSN devices must utilize their limited resources to operate for as long as possible, but longer operations require maintenance. One method of maintenance is to apply a resource adaptation policy when a system reaches a critical threshold. This study discusses the application of a security level adaptation model, such as an ARSy Framework, for using resources more efficiently. A single node comprising a Raspberry Pi 3 Model B and a DS18B20 temperature sensor were tested in a laboratory under normal and stressful conditions. The result shows that under normal conditions, the system operates approximately three times longer than under stressful conditions. Maintaining the stability of the resources also enables the security level of a network’s data output to stay at a high or medium level.
... Recently, the researchers concentrate on developing security-aware energy-e±cient task scheduling mechanisms [20][21][22][23][24][25][26][27][28][29][30] that cannot only promote the system safety performance but also improve the system energy e±ciency. The third category to realize a secure system is investigating the safety issues in speci¯c applications such as cyber-physical systems (CPSs), [31][32][33] automotive systems, [34][35][36][37] clusters, [38][39][40] grids, 41-43 etc. Contribution and organization: A large amount of state-of-art approaches designed for security-aware RTES are summarized in this paper. The rest of the paper is organized in Fig. 1. ...
... Xie et al. 38 presented a security overhead model after investigating the scheduling problem of many real-time tasks with di®erent security requirements to measure the security overheads caused by security critical tasks. To integrate security requirements into scheduling of the real-time applications on clusters by using the proposed model, they proposed a security-aware scheduling strategy named SAREC, which realizes high security quality for real-time applications on clusters and meets its timing constraints. ...
With the rapid development of embedded systems, users and services have been greatly facilitated while also experiencing security threats as a result of cyber-attacks and system vulnerabilities. Currently, the real-time embedded system (RTES) focus is to deal with these security issues. In this paper, we introduce a short review of security-aware techniques for RTES. We mainly discuss two common approaches to improve the security of RTESs. The first approach is achieved by exploring specific attacks. The second approach is realized by deploying security-guaranteed services. However, improving the security of embedded systems may cause excessive energy consumption at the same time. Therefore, we investigate the secure and energy-aware RTESs on a wide range of research. In addition, we study a number of common applications used in secure RETSs. This paper stands for providing awareness and better understanding of the current RTES research status as well as technical theory behind it. Hence, the RTES security issues are resolved.
