A Dynamic Sliding Load Balancing Strategy in Distributed Systems
Computer Science Department, Jordan University of Science and Technology, Jordan
Abstract: A sliding strategy for load balancing is introduced. The strategy groups a certain number of adjacent nodes to perform a load balancing process. Upon the completion of a given period, the groups are to be rotated by shifting each group one position to the right, thus produces different groups. This strategy (sort of clustering) not only reduces the load balancing overheads, but also it could be utilized as a backbone by any load balancing strategy. The proposed load balancing strategy always converges, and tends to be in a steady state in a negligible processing time. In this paper, the load status and the locations of the nodes regarding the system’s topology are irrelevant to load balancing process. The new algorithm can be always applied to any distributed system, even if it is heavily loaded, since the cost of scheduling is very low due to the highly reduced number of messages. This is achieved by reducing dramatically the overheads incurred from attached information tables, message passing, job thrashing, and response time.
Keywords: Load balancing, distributed systems, scalability, message passing.
Received January 10, 2005; accepted March 20, 2005