Resource Management in Sustainable Cyber-Physical Systems Using Heterogeneous Cloud Computing
Resource Management in Sustainable Cyber-Physical Systems Using Heterogeneous Cloud Computing
复制标题
DOI：
10.1109/tsusc.2017.2723954
复制
发表时间：
2018-04
影响因子：
3.9
通讯作者：
Keke Gai;Meikang Qiu;Hui Zhao;Xiaotong Sun
中科院分区：
文献类型：
--
作者：
Keke Gai;Meikang Qiu;Hui Zhao;Xiaotong Sun
使用异构计算的分布式计算的大量增长使网络物理系统（CPS）得到了极大的扩展。将CPS与异构云计算相结合是提高系统可持续性的另一种方法。然而，在云系统中执行资源管理仍然遇到一些挑战，包括异构云中Web服务器容量和任务分配的瓶颈。服务需求的不稳定往往会导致服务延迟，从而影响企业的竞争力。本文研究了异构云中的任务分配问题，该问题被证明是一个np困难问题。提出的方法称为基于云的智能优化工作负载模型（SCOW），该模型使用预测云容量并考虑可持续因素将任务分配给异构云。为了达到优化目标，我们提出了几种算法，包括工作负载资源最小化算法（WRM）、智能任务分配算法（STA）和任务映射算法（TMA）。我们的实验评估检验了所提出方案的性能。
The substantial growth of the distributed computing using heterogeneous computing has enabled great expansions in Cyber Physical Systems (CPS). Combining CPS with heterogeneous cloud computing is an alternative approach for increasing sustainability of the system. However, execution of resource management in cloud systems is still encountering a few challenges, including the bottlenecks of the Web server capacities and task assignments in the heterogeneous cloud. The unstable service demands often result in service delays, which embarrasses the competitiveness of the enterprises. This paper addresses the problem of the task assignment in heterogeneous clouds, which is proved as a NP-hard problem. The proposed approach is called Smart Cloud-based Optimizing Workload (SCOW) Model that uses predictive cloud capacities and considers sustainable factors to assign tasks to heterogeneous clouds. To reach the optimization objective, we propose a few algorithms, which include Workload Resource Minimization Algorithm (WRM), Smart Task Assignment (STA) Algorithm, and Task Mapping Algorithm (TMA). Our experimental evaluations have examined the performance of the proposed scheme.