Evolutionary Multiobjective Optimization with a Segment-Based External Memory Support for the Multiobjective Quadratic Assignment Problem

• DOI: 10.1109/cec.2005.1555036
• Publication Date: 2005-12-13T15:55:52Z
• Authors: A. Acan; A. Unveren
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Multiobjective evolutionary optimization has been demonstrated to be an efficient method for some difficult multiobjective problems; particularly the quadratic assignment problem which is a provably NP-complete with multitude of real-world applications. This paper introduces use segment-based external memory in optimization. In principle, variable-size solution segments taken from number previously promising solutions are stored whose elements used construction new solutions. solution, segment retrieved and complete through recombination operators. The aim provide further intensification around without weakening exploration capabilities. Different instances performance evaluations and, almost all trials, proposed strategy provided significantly better results than genetic algorithm (MOGA).