Task Scheduling Optimization in Heterogeneous Distributed Systems

Abstract

Efficient task scheduling is essential for obtaining high performance in heterogeneous distributed computing systems. Several algorithms are proposed for heterogeneous distributed computing systems. In this paper, a new static scheduling algorithm is proposed called Highest Communicated Path of Task (HCPT) algorithm to efficiently schedule tasks on the heterogeneous distributed computing systems. Our algorithm is based on the list-scheduling technique. The algorithm not only is focused on reducing the makespan, but also provides better performance than the other algorithms in terms of speedup and efficiency. It consists of three phases, level sorting phase, task-prioritizing phase and processor selection phase. From the theoretical analysis of the HCPT algorithm with other algorithms for a Directed A-cyclic Graph (DAG), the better performance is observed.