Meta-heuristic and Evolutionary Algorithms for Engineering Optimization

8 Particle Swarm Optimization

Summary

This chapter describes the particle swarm optimization (PSO) technique, which is inspired by the swarming strategies of various organisms in nature. The next section reviews a few implementations of the PSO. The remainder of this chapter describes the PSO algorithm and presents a pseudocode for its implementation.

8.1 Introduction

Kennedy and Eberhart (1995) developed the particle swarm optimization (PSO) algorithm as a meta‐heuristic algorithm based on the social behavior exhibited by birds or fishes when striving to reach a destination. Balci and Valenzuela (2004) presented a technique that uses the PSO combined with the Lagrangian relaxation (LR) framework to solve a power generator scheduling problem known as the unit commitment problem. Chuanwen and Bompard (2005) applied a self‐adaptive chaotic PSO algorithm for optimal hydroelectric plant dispatch model based on the rule of maximizing the benefit in a deregulated environment. The proposed approach introduced chaos mapping, and the self‐adaptive chaotic PSO algorithm increased the mapping convergence rate and associated precision. Suribabu and Neelakantan (2006) used the Environmental Protection Agency’s hydraulic network simulator (EPANET) and the PSO algorithm in a combined simulation and optimization model to design a water distribution pipeline network. Matott et al. (2006) identified the PSO algorithm as an effective technique for solving pump‐and‐treat optimization problems ...