Application of Fuzzy Logic in Load Balancing of Homogenous Distributed Systems

[摘要] Various studies have shown that distributing the work load evenly among processors of a distributed system highly improves system performance and increases resource utilization. This process is known as load balancing. Fuzzy logic has been applied in many fields of science and industry to deal with uncertainties. Existing research in using fuzzy logic for the purpose of load balancing has only concentrated in utilizing fuzzy logic concepts in describing processors load and tasks execution length. The responsibility of the fuzzy-based load balancing process itself, however, has not been discussed and in most reported work is assumed to be performed in a distributed fashion by all nodes in the network. This paper proposes a new fuzzy dynamic load balancing algorithm for homogenous distributed systems.The proposed algorithm utilizes fuzzy logic in dealing with inaccurate load information, making load distribution decisions, and maintaining overall system stability. In terms of control, we propose a new approach that specifies how, when, and by which node the load balancing is implemented. Our approach is called Centralized-But-Distributed (CBD). An evaluation study of the proposed algorithm shows that our algorithm is able to reduce the average response time and average queue length as compared to known load balancing algorithms reported in the literature.

[学科分类] 物理（综合）

[关键词] Dynamic Load Balancing;Fuzzy Logic;Distributed System;Algorithms.