Many-objective optimization based on information separation and neighbor punishment selection

Abstract

Many-objective optimization refers to optimizing a multi-objective optimization problem (MOP) where the number of objectives is more than 3. Most classical evolutionary multi-objective optimization (EMO) algorithms use the Pareto dominance relation to guide the search, which usually perform poorly in the many-objective optimization scenario. This paper proposes an EMO algorithm based on information separation and neighbor punishment selection (ISNPS) to deal with many-objective optimization problems. ISNPS separates individual's behavior in the population into convergence information and distribution information by rotating the original coordinates in the objective space. Specifically, the proposed algorithm employs one coordinate to reflect individual's convergence and the remaining $$m-1$$m-1 coordinates to reflect individual's distribution, where m is the number of objectives in a given MOP. In addition, a neighborhood punishment strategy is developed to prevent individuals from being crowded. From a series of experiments on 42 test instances with 3---10 objectives, ISNPS has been found to be very competitive against six representative algorithms in the EMO area.