Adaptive Multi-crossover Evolutionary Algorithm for Real-world Optimization Problems

Abstract

Evolutionary algorithms (EAs) have been extensively used since their invention. EAs are considered as a powerful tool to solve numerous optimisation problems in various fields. Their search mechanisms have been actively developed to improve their search efficiency toward global optima solutions. This study aims to investigate the effects of using different types of recombination (crossover) schemes. It introduces an adaptive version of EA called adaptive multi-crossover evolutionary algorithm (AMCEA). The proposed AMCEA offers multiple forms of heuristic crossover operators based on genetic algorithm (GA) and harmony search algorithm (HSA). The proposed technique improves the search attitude by allowing the effective utilisation of exploration and exploitation strategies during the evolution process. The quality of the proposed AMCEA is evaluated on six real-world numerical optimisation problems (IEEE-CEC2011), and results are compared with those obtained with five variants of GA and HSA. Results demonstrate the superiority of the AMCEA over previously improved algorithms in terms of solution quality; it achieves the lowest mean results and lowest best results in 75% and 66% of the total experiment cases, respectively.