Strategies based on polar coordinates to keep diversity in multi-objective genetic algorithm

Most of the multi-objective genetic algorithms (MOGAs) can be divided into two steps, namely constructing the nondominated set and truncation procedure. The quality of the latter directly affects the efficiency and the distribution of MOGA. In this paper, a new MOGA named PCGA (polar coordinates genetic algorithm) is proposed. The technique, which uses grids to keep diversity of solutions with polar coordinates, is introduced into PCGA. The time complexity of its truncation approach is higher than that of NSGA2, but is greatly lower than that of SPEA2. Meanwhile, though PCGA´s distribution is not as good as that of SPEA2, it makes a large improvement with respect to that of NSGA2.