Multi objective particle swarm optimization: algorithms and applications

Abstract

The primary motivation of this work is to explore and improve particle swarm optimization (PSO) techniques for multi-objective (MO) function optimization as well as to expand its applications in real world bin packing problems. Information from this study would help people better understand PSO concept, and its advantages and disadvantages in application to MO problems. The proposed fuzzy update strategy helps PSO overcome difficulties in solving MO problems with lots of local minimum. The coevolutionary design and the distributed PSO algorithm can help reduce processing time in solving complex MO problems. And the successful application of PSO to bin packing problem may also be able to help PSO find other applications in solving real world combinatorial problems. We primarily use an experimental methodology backed up with statistical analysis to achieve the objectives of this dissertation. The effectiveness and efficiency of the proposed algorithms are compared against other multi-objective evolutionary algorithms using test cases.