Several decentralized load balancing policies have been proposed to address the issue of scalability in grids.However, the communication overhead incurred in exchanging state information remains a burden. In this paper, we propose a dynamic, decentralized load balancing policy which performs very competitively in heterogeneous grids. The policy uses an effective mechanism for state information exchange, which significantly reduces the communication overhead, while quickly updating the state information in a decentralized fashion.
Published in:
Future Computing, Service Computation, Cognitive, Adaptive, Content, Patterns, 2009. COMPUTATIONWORLD '09. Computation World:
Date of Conference: 15-20 Nov. 2009