An efficient load balancing algorithm for heterogeneous grid systems considering desirability of grid sites

Many scheduling and load balancing solutions have been proposed for traditional distributed computing systems. However, they all suffer from significant deficiencies when extended to a Grid environment: some use a centralized approach that makes the algorithms not scalable, while others either ignore the difference in processing power among grid sites, or assign loads among grid sites without considering communication overhead in collecting load information. In this paper, we present an efficient desirability-aware load balancing algorithm to tackle the above new challenges in heterogeneous grid systems. The simulation results show that our proposed algorithm yields better performance when compared with the so-called "Nearest Neighbor" load balancing (LB) algorithm. Our algorithm is dynamic, sender-initiated and decentralized