SPEA2+: Improving the Performance of the Strength Pareto Evolutionary Algorithm 2

Multi-objective optimization methods are essential to resolve real-world problems as most involve several types of objects. Several multi-objective genetic algorithms have been proposed. Among them, SPEA2 and NSGA-II are the most successful. In the present study, two new mechanisms were added to SPEA2 to improve its searching ability a more effective crossover mechanism and an archive mechanism to maintain diversity of the solutions in the objective and variable spaces. The new SPEA2 with these two mechanisms was named SPEA2+. To clarify the characteristics and effectiveness of the proposed method, SPEA2+ was applied to several test functions. In the comparison of SPEA2+ with SPEA2 and NSGA-II, SPEA2+ showed good results and the effects of the new mechanism were clarified. From these results, it was concluded that SPEA2+ is a good algorithm for multi-objective optimization problems.

• Type: Conference
• Year: 2004
• Where: PPSN
• Authors: Mifa Kim, Tomoyuki Hiroyasu, Mitsunori Miki, Shinya Watanabe
• Keywords: Distributed And Parallel Computing, Multi-objective Genetic Algorithms, Multi-objective Optimization, Multi-objective Optimization Methods, PPSN 2004