Fuzzy load balancing in an industrial distributed system for job scheduling

Article type: Research Article

Authors: Shaout, Adnan | McAuliffe, Patrick

Affiliations: Department of Electrical and Computer Engineering, The University of Michigan‐Dearborn, Dearborn, MI 48128, USA

Abstract: The paper presents a batch job scheduler for a distributed system which utilizes a fuzzy logic algorithm to balance the load on individual processors maximizing throughput of the overall system. The fuzzy load balancing algorithm has been implemented in a production processing environment rather than in simulation only. This paper demonstrates the power and simplicity of incorporating a fuzzy load balancing algorithm into a batch job scheduler which has produced excellent performance and reliability characteristics.

Journal: Journal of Intelligent and Fuzzy Systems, vol. 8, no. 3, pp. 191-199, 2000