A heuristic scheduling strategy for independent tasks on grid

Abstract

Task scheduling is an NP-complete problem and is an integral part of parallel and distributed computing. It is more complicated under the grid computing environment. In this paper, we consider the problem of allocating independent, heterogeneous tasks on grid environment. A heuristic task scheduling strategy which is composed of two algorithms satisfied with resource load balance is presented. The WMTG-min heuristic algorithm schedules tasks by employing the weighted mean execution time, which reflects the performance of overall machines, and it is a high efficient algorithm. The further optimal scheduling result of the above algorithm is gained by the WMTSG-min algorithm which employs the weighted mean execution time and sufferage value as heuristic information. The performance of the proposed algorithms is evaluated via extensive simulation experiments. Experiment results show that the heuristic strategy performs significantly to ensure high throughput. Furthermore, results show that although it may not be polynomial, the WMTSG-min algorithm is efficient