Hybridizing Harmony Search Algorithm with Multi-Parent Crossover to Solve Real World Optimization Problems

摘要

Harmony search algorithm (HSA) is a recent evolutionary algorithm used to solve several optimization problems. The algorithm mimics the improvisation behaviour of a group of musicians to find a good harmony. Several variations of HSA have been proposed to enhance its performance. In this paper, a new variation of HSA that uses multi-parent crossover is proposed (HSA-MPC). In this technique three harmonies are used to generate three new harmonies that will replace the worst three solution vectors in the harmony memory (HM). The algorithm has been applied to solve a set of eight real world numerical optimization problems (1-8) introduced for IEEE-CEC2011 evolutionary algorithm competition. The experimental results of the proposed algorithm are comparedwith the original HAS, and two variations of HAS: global best HAS and tournament HAS. The HAS-MPC almost always shows superiority on all test problems.