Comparison of Load Balancing Algorithms in a Grid

Abstract

The ever changing demands on the computational resources have generated the need for solutions that are more flexible. Using a ¿bigger box¿ that has more and faster processors and permanent storage or more random access memory (RAM) is not a viable solution as the system usage patterns vary. A grid based distributed system can solve this problem by allowing multiple independent jobs to run over a network of heterogeneous computing nodes. Keeping the workload represented by these jobs balanced over the network of computers requires network-aware load balancing algorithms that are dynamic and quick. The objective of this paper work is to review the different load balancing algorithms for the grid, identify the comparison metrics for the load balancing algorithms and to carry out comparison between these algorithms based on these identified metrics.