Title: Hybrid strategy of multi-objective differential evolution (H-MODE) for multi-objective optimisation
Authors: Ashish M. Gujarathi; B.V. Babu
Addresses: Department of Petroleum and Chemical Engineering, College of Engineering, Sultan Qaboos University, P.O. Box 33, Al-Khod, P.C. 123, Muscat, Sultanate of Oman ' Institute of Engineering and Technology, JK Laxmipat University, Jaipur – 302 026 (Rajasthan), India
Abstract: Evolutionary multi-objective optimisation (EMO) algorithms are preferred for solving the multi-objective optimisation (MOO) problems due to their ability of producing multiple solutions in a single run. In this study, hybridisation of the traditional sequential simplex method is considered with the evolutionary multi-objective differential evolution (MODE) algorithm for solving MOO problems. The hybrid strategy of MODE ensured that both the speed and accuracy are attained in a single algorithm. Various strategies of MODE algorithm are tested on several benchmark MOO test problems [both constrained (namely, SCH, FON, KUR, ZDT1, ZDT2, ZDT4, and ZDT3 and ZDT4) and unconstrained (namely, CONSTR and TNK)]. Two widely accepted performance metrics (convergence and diversity) from the point of view of MOO study are considered for evaluating the performance of strategies of MODE algorithm. Pareto fronts are obtained using newly developed strategies of MODE and are compared with the Pareto front obtained using other EMO strategy (NSGA-II). It is found that all the developed strategies of MODE algorithm converge to the true Pareto front for most of the test problems. However, the strategies of MODE result in slightly lower value of diversity metric as compared to NSGA-II for most of the test problems considered in this study.
Keywords: differential evolution; multi-objective optimisation; MOO; evolutionary algorithms; Pareto optimal front; hybrid algorithms; memetic algorithms; test problems.
International Journal of Computational Intelligence Studies, 2013 Vol.2 No.2, pp.157 - 186
Available online: 23 Jul 2013 *Full-text access for editors Access for subscribers Purchase this article Comment on this article