A Performance Study of Task Scheduling Heuristics in HC Environment

Heterogeneous computing (HC) environment consists of different resources connected with high-speed links to provide a variety of computational capabilities for computing-intensive applications having multifarious computational requirements. The problem of optimal assignment of tasks to machines in HC environment is proven to be NP-complete requiring use of heuristics to find the near optimal solution. In this work we conduct a performance study of task scheduling heuristics in HC environment. Overall we have implemented 16 heuristics, among them 7 are proposed in this paper. Based on experimental results we specify the circumstances under which one heuristic will outperform the others.