Integrating preference based weighted sum into evolutionary multi-objective optimization
Guang-Hong Liu, Gang Wu, Tao Zheng, Qing Hua Ling · 2011
Most of the recent studies on evolutionary multi-objective optimization (EMO) focus on finding the whole set of Pareto optimal solutions. In practice, the users are normally interested in some regions of Pareto front which satisfy their preferences and an ultimate decision making process may be dominated by several decision makers. In this paper, we integrate the weighted sum model of preferences into EMO algorithms to guide the search towards the pertinent regions of interest to decision makers. The proposed method can obtain multiple sub-regions corresponding to each decision maker in a single run. On a number of test problems we show that the proposed algorithm efficiently guides the population towards the interesting regions, with which a better and a more reliable decision can be made.