Dealing with Boundary Constraint Violations in Particle Swarm Optimization with Aging Leader and Challengers (ALC-PSO)

Abstract

Boundary violation is a common process in optimization problems. This problem can be seen in Particle Swarm Optimization(PSO) and its variants too. An aging based variant of PSO called, PSO with Aging Leader and Challengers(ALC-PSO) overcomes the stagnation problem that existed in PSO. To avoid the problem of random particles, some bound handling mechanisms need to be applied to Particle Swarm Optimization with Aging Leader and Challengers (ALC-PSO) to improve its performance. During the search process, some particles may leave the search boundaries within which the optimal solution is to be found. It becomes essential to handle such boundary constraint violations and some boundary handling strategies are required to be implemented. This paper presents some of these bound handling methods applied to ALC-PSO algorithm and comparisons are made with PSO. These methods include velocity initialization, velocity clamping and bound handling methods. The results are simulated on MATLAB R2011b for Ackley benchmark problem.