This work provides some criteria that allow network administrators to measure the impact of different network configurations have on voice, data, and video applications quality of service offered to the different user...
详细信息
ISBN:
(纸本)9781728173498
This work provides some criteria that allow network administrators to measure the impact of different network configurations have on voice, data, and video applications quality of service offered to the different users. For that, this project implemented tests to measure parameters such as packet loss, delay and jitter using static routing, different packet scheduling algorithms (Custom Queuing, Priority Queuing, and Weighted First Queuing), different services (voice, data, and video), and connection speeds using Cisco 2800 Routers and D-ITG traffic generator in conjunction with the Network Time Protocol synchronizer. A comparative analysis of sensitive parameters for Quality of Service was conducted to describe network behavior for each service. The implemented services presented performances according to quality requirements, reported in the literature. Specifically, the data service presented delay and jitter within the levels considered acceptable for this application and zero packet loss. For its part, the video service presented levels of delay and jitter according to the quality requirements for streaming. Finally, the voice service presented the best configuration performance with the Priority Queuing algorithm, for all measured service quality parameters.
In this paper we propose two modified proportional fair scheduling algorithms for multiuser multicarrier systems. Compared to the existing proportional fair scheduling algorithms, our proposed algorithms are devised t...
详细信息
ISBN:
(纸本)9781424452385
In this paper we propose two modified proportional fair scheduling algorithms for multiuser multicarrier systems. Compared to the existing proportional fair scheduling algorithms, our proposed algorithms are devised to support the delay constraint for the real-time applications as well as to guarantee a certain level of fairness. The simulation results show that the proposed scheduling algorithms not only almost achieve proportional fairness with low complexity but also support real-time service users.
We consider the problem of selfish misbehavior in scheduling algorithms of wireless networks. All wireless scheduling algorithms are designed under the assumption that network users will follow the algorithm specifica...
详细信息
ISBN:
(纸本)9781424493289
We consider the problem of selfish misbehavior in scheduling algorithms of wireless networks. All wireless scheduling algorithms are designed under the assumption that network users will follow the algorithm specifications. In this paper, we study two scheduling algorithms in which a selfish user might misbehave in order to achieve better performance. In the first case, we consider a network that implements cross-layered rate control mechanism to determine arrival rate of users as well as link schedules. We explain a scenario in which a selfish user obtains extra throughput by misleading the scheduling component of the network. We find an equivalent optimization framework that captures misbehavior pattern of the selfish user. We present a solution to prevent such a greedy behavior by imposing a cost term on the utility function of the users. In the second part of the work, we consider the family of random access scheduling algorithms in which users of the wireless network wait for randomly chosen back-off intervals before accessing the medium. A selfish user might wait for smaller back-off in order to obtain an unfair advantage. We present a comparison method to detect such a greedy misbehavior.
Resource scheduling is a fundamental issue in achieving high performance on computational grids. In this paper, we concentrate on parallel resource scheduling problems for hierarchical resource scheduling architecture...
详细信息
ISBN:
(纸本)9780769526942
Resource scheduling is a fundamental issue in achieving high performance on computational grids. In this paper, we concentrate on parallel resource scheduling problems for hierarchical resource scheduling architecture of computational Grids, and propose a Stochastic Reward Nets (SRN) based performability evaluation framework for evaluating the performability of resource scheduling algorithms for computational Grid with resource unavailability. Within the proposed framework, performability model of hierarchical resource scheduling is constructed, 36 combinations of 6 global job scheduling algorithms and 6 local processor allocation algorithms are specified in the uniform performability model, and performability metrics are derived.
Cache-partitioned architectures allow subsections of the shared last-level cache (LLC) to be exclusively reserved for some applications. This technique dramatically limits interactions between applications that are co...
详细信息
ISBN:
(纸本)9780769561493
Cache-partitioned architectures allow subsections of the shared last-level cache (LLC) to be exclusively reserved for some applications. This technique dramatically limits interactions between applications that are concurrently executing on a multi-core machine. Consider n applications that execute concurrently, with the objective to minimize the makespan, defined as the maximum completion time of the n applications. Key scheduling questions are: (i) which proportion of cache and (ii) how many processors should be given to each application? Here, we assign rational numbers of processors to each application, since they can be shared across applications through multi-threading. In this paper, we provide answers to (i) and (ii) for perfectly parallel applications. Even though the problem is shown to be NP-complete, we give key elements to determine the subset of applications that should share the LLC (while remaining ones only use their smaller private cache). Building upon these results, we design efficient heuristics for general applications. Extensive simulations demonstrate the usefulness of co-scheduling when our efficient cache partitioning strategies are deployed.
scheduling algorithms assign contention probability for each link in Wireless Ad Hoc Networks and plays a key role in deciding the system performance. Recently, many low cost distributed scheduling algorithms are prop...
详细信息
ISBN:
(纸本)9781424420742
scheduling algorithms assign contention probability for each link in Wireless Ad Hoc Networks and plays a key role in deciding the system performance. Recently, many low cost distributed scheduling algorithms are proposed. In this paper, we propose to improve the performance of a class of distributed collision-based scheduling algorithms, called constant time distributed scheduling algorithms, by exploring the advantage brought by the unevenness of links' contention probabilities. Specifically, we prove that there exists ordering relationship for the success probability of any neighborhood when the contention probability vectors are ordered in the sense of majorization. We show how to modify the existing algorithms so as to find a new contention probability vector that majorizes the original one in a distributed manner. Our simulation results indicate that by using our modified algorithms, the average queue lengths of a stable system can be reduced by 25% to 50%, while the capacity region remains the same. Our modification to the existing algorithms is extremely simple and entails essentially zero additional cost.
This paper considers semi-online scheduling problems on parallel identical machines with combined partial information. For the objective to minimize makespan, and both the largest processing time of all jobs and the t...
详细信息
ISBN:
(纸本)9783540744498
This paper considers semi-online scheduling problems on parallel identical machines with combined partial information. For the objective to minimize makespan, and both the largest processing time of all jobs and the total processing time of all jobs are known in advance, we present an optimal algorithm with competitive ratio 4/3 on three machines. For the objective to maximize the minimum machine load, and both the largest processing time of all jobs and the optimal value are known in advance, we present algorithms which are optimal when the machine number is less than 5.
This work introduces an application of simulation-optimization techniques to the emerging field of green internet computing. The paper discusses the relevance of considering environmental factors in modern computing a...
详细信息
ISBN:
(纸本)9781479939503;9781479920778
This work introduces an application of simulation-optimization techniques to the emerging field of green internet computing. The paper discusses the relevance of considering environmental factors in modern computing and then describes how simulation can be combined with scheduling metaheuristics in order to reduce the expected time needed to complete a set of tasks in a server under the realistic assumption of stochastic processing times. This, in turn, allows for a reduction in average energy consumption, which makes the computing facility more efficient from an environmental perspective. Some experiments have been carried out in order to illustrate these potential savings.
In previous work, the authors have already proposed an approach to approximate solving scheduling problems neural network based algorithms, applied to the preemptive and non-preemptive scheduling for a mono or multipr...
详细信息
ISBN:
(纸本)0818680342
In previous work, the authors have already proposed an approach to approximate solving scheduling problems neural network based algorithms, applied to the preemptive and non-preemptive scheduling for a mono or multiprocessor environment. Results were presented in a systematic approach for translating task constraints into neural network building rules that are independently added to the neural architecture. The main advantage of this methodology is that the neural network built according the rules converges to a solution of the scheduling problem in only a few propagation times of analogue amplifiers. In this paper, we present new rules that extend the methodology to handle precedence constraints. We present the formal energy function which minimum occurs when the precedence constraints are met and finally we present a performance analysis of the quality of the results obtained by this approach.
In this paper, we propose novel low-energy scheduling algorithms with low computational complexities for the heterogeneous Body A rea Network (BAN) systems, considering task graphs with deadlines (timing constraints) ...
详细信息
ISBN:
(纸本)9780769529752
In this paper, we propose novel low-energy scheduling algorithms with low computational complexities for the heterogeneous Body A rea Network (BAN) systems, considering task graphs with deadlines (timing constraints) and precedence relationships to satisfy. Our proposed novel scheme, referred to as "critical-path information track-and-up-date ", analyses the critical-paths, identifies the slack and distributes it over tasks such that the overall energy consumption is minimised. Our dynamic scheduling algorithm utilises the results from the static scheduling algorithm and attempts to aggressively reduce the energy consumption. Simulations for the task graph for a typical BAN application show that our static and dynamic scheduling algorithms deliver 25% and 15% more energy savings respectively Compared to typical slack reclamation based scheduling algorithms.
暂无评论