Improved genetic algorithms and list scheduling techniques for independent task scheduling in distributed systems

Abstract

Given a set of tasks with certain characteristics, e.g., data size, estimated execution time and a set of processing nodes with their own parameters, the goal of task scheduling is to allocate tasks at nodes so that the total makespan is minimized. The problem has been studied under various assumptions concerning task and node parameters with the resulting problem statements usually being NP-complete. List scheduling (LS) heuristics such as MaxMin and MinMin together with genetic algorithms (GAs) were applied in the past to find solutions. In this paper we investigate new heuristics for both the LS and the GA paradigm with the specific aim of improving the performance of the standard algorithms when task computations involve large data transfers. Experimental results under various environment assumptions illustrate the merits of the new algorithms. © 2007 IEEE.