Locating and tracking multiple dynamic optima by a particle swarm model using speciation

• Published in: IEEE transactions on evolutionary computation Vol. 10; no. 4; pp. 440 - 458
• Main Authors: Parrott, D., Xiaodong Li
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2006; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Australia; Computer science; Dynamics; Feedback; Information technology; Iterative methods; Mathematical analysis; Multimodal optimization; Optimization; optimization in dynamic environments; particle swam optimization (PSO); Particle swarm optimization; Particle tracking; Seeds; Shape; Similarity; Speciation; Studies; Tracking; tracking optima in dynamic environments
• DOI: 10.1109/TEVC.2005.859468
• ISSN: 1089-778X

This paper proposes an improved particle swarm optimizer using the notion of species to determine its neighborhood best values for solving multimodal optimization problems and for tracking multiple optima in a dynamic environment. In the proposed species-based particle swam optimization (SPSO), the swarm population is divided into species subpopulations based on their similarity. Each species is grouped around a dominating particle called the species seed. At each iteration step, species seeds are identified from the entire population, and then adopted as neighborhood bests for these individual species groups separately. Species are formed adaptively at each step based on the feedback obtained from the multimodal fitness landscape. Over successive iterations, species are able to simultaneously optimize toward multiple optima, regardless of whether they are global or local optima. Our experiments on using the SPSO to locate multiple optima in a static environment and a dynamic SPSO (DSPSO) to track multiple changing optima in a dynamic environment have demonstrated that SPSO is very effective in dealing with multimodal optimization functions in both environments