Prediction-based Independent Task Scheduling for Heterogeneous Distributed Computing Systems

Independent task scheduling algorithms in distributed computing systems deal with three main conflicting factors including load balance, task execution time and scheduling cost. In this paper, the problem of scheduling tasks arriving at a low rate and with long execution time in heterogeneous computing systems is studied, and a new scheduling algorithm based on prediction is proposed. This algorithm evaluates the utility of task scheduling based on statistics and prediction to solve the influence of heterogeneous computing systems. The experimental results reveal that the proposed algorithm adequately balances the conflicting factors, and thus performs better than some classical algorithms such as MCT and MET when the parameters are well selected.
distributed computing system task scheduling independent task heterogeneous system prediction
Youwei Lu Zhenzhen Xu Feng Xia
School of software, Dalian University of Technology, Dalian 116620, China State Key laboratory of Ro School of software, Dalian University of Technology, Dalian 116620, China
国际会议
沈阳
英文
1039-1046
2011-11-22(万方平台首次上网日期,不代表论文的发表时间)