Chip multiprocessors(CMPs) allow thread level parallelism,thus increasing ***,this comes with the cost of temperature *** require more power,creating non uniform power map and *** at this problem,a thread scheduling a...
详细信息
Chip multiprocessors(CMPs) allow thread level parallelism,thus increasing ***,this comes with the cost of temperature *** require more power,creating non uniform power map and *** at this problem,a thread schedulingalgorithm,the greedy scheduling algorithm,was proposed to reduce the thermal emergencies and to improve the *** greedy scheduling algorithm was implemented in the Linux kernel on Intel's Quad-Core *** experimental results show that the greedy scheduling algorithm can reduce 9.6%-78.5% of the hardware dynamic thermal management(DTM) in various combinations of workloads,and has an average of 5.2% and up to 9.7% throughput higher than the Linux standard scheduler.
Nearly all bitrate adaptive video content delivered today is streamed using protocols that run a purely client based adaptation logic. The resulting lack of coordination may lead to suboptimal user experience and reso...
详细信息
Nearly all bitrate adaptive video content delivered today is streamed using protocols that run a purely client based adaptation logic. The resulting lack of coordination may lead to suboptimal user experience and resource utilization. As a response, approaches that include the network and servers in the adaptation process are emerging. In this article, we present an optimized solution for network assisted adaptation specifically targeted to mobile streaming in multi-access edge computing (MEC) environments. Due to NP-Hardness of the problem, we have designed a heuristic-based algorithm with minimum need for parameter tuning and having relatively low complexity. We then study the performance of this solution against two popular client-based solutions, namely Buffer-Based Adaptation (BBA) and Rate-Based Adaptation (RBA), as well as to another network assisted solution. Our objective is two fold: First, we want to demonstrate the efficiency of our solution and second to quantify the benefits of network-assisted adaptation over the client-based approaches in mobile edge computing scenarios. The results from our simulations reveal that the network assisted adaptation clearly outperforms the purely client-based DASH heuristics in some of the metrics, not all of them, particularly, in situations when the achievable throughput is moderately high or the link quality of the mobile clients does not differ from each other substantially.
We consider multiple base station (BS) cooperative transmission in downlink cellular networks to improve the spectral efficiency and the system capacity. Grouping BSs into clusters is a practical solution to realize B...
详细信息
ISBN:
(纸本)9781424492688
We consider multiple base station (BS) cooperative transmission in downlink cellular networks to improve the spectral efficiency and the system capacity. Grouping BSs into clusters is a practical solution to realize BSs cooperation and reduce system complexity. However, it still suffers from inter-cluster interference, especially for the cluster-edge users. In this paper, clustering and scheduling are jointly considered to deal with the problem. The clusters are formed dynamically from users' point of view to minimize the inter-cluster interference, and are allowed to be overlapped. Accordingly, coordinated precoding scheme is designed to manage the intra-cluster interference. A greedy scheduling algorithm is proposed jointly with dynamic clustering. Simulations show that the proposed joint algorithm provides impressive average throughput gain over the non-joint ones, and the user fairness is improved significantly.
Selecting appropriate resources for running a job efficiently is one of the common objectives in a computational grid. Resource scheduling should consider the specific characteristics of the application, and decide th...
详细信息
Selecting appropriate resources for running a job efficiently is one of the common objectives in a computational grid. Resource scheduling should consider the specific characteristics of the application, and decide the metrics to be used accordingly. This paper presents a distributed resource scheduling framework mainly consisting of a job scheduler and a local scheduler. In order to meet the requirements of different applications, we adopt HGSA, a Heuristic-based greedy scheduling algorithm, to schedule jobs in the grid, where the heuristic knowledge is the metric weights of the computing resources and the metric workload impact factors. The metric weight is used to control the effect of the metric on the application. For different applications, only metric weights and the metric workload impact factors need to be changed, while the schedulingalgorithm remains the same. Experimental results are presented to demonstrate the adaptability of the HGSA.
The task duplication based scheduling is a new approach to the scheduling problems. Although the task duplication based scheduling (TDS) algorithm proposed by Darbha and Agrawal generates an optimal schedule, the opti...
详细信息
ISBN:
(纸本)0780378652
The task duplication based scheduling is a new approach to the scheduling problems. Although the task duplication based scheduling (TDS) algorithm proposed by Darbha and Agrawal generates an optimal schedule, the optimality condition is very restricted. Thus, Park and Choe proposed an extended TDS algorithm whose optimality condition is less restricted than that of TDS algorithm, but the condition is very complex. In this paper, we provide a greedyalgorithm whose schedule length is shorter than both of the algorithms. The time complexity of our algorithm is in O(\V\(2)), where \V\ represents the number of tasks.
In data-intensive applications, such as high-energy physics, bio-informatics, we encounter applications involving numerous jobs that access and generate large datasets. Effective scheduling of such applications is a c...
详细信息
In data-intensive applications, such as high-energy physics, bio-informatics, we encounter applications involving numerous jobs that access and generate large datasets. Effective scheduling of such applications is a challenge, due to the need to consider for both computational resources and data storage resources. In this paper, we describe an adaptive scheduling model that considers availability of computational, storage and network resources. Based on this model we implement a scheduler used in our campus grid. The results achieved by our scheduler have been analysed by comparing with greedyalgorithm that is widely used in computational grids and some data grids.
暂无评论