Single Objective Guided Multiobjective Optimization Algorithm

Most of multiobjective optimization algorithms consider multiple objectives as a whole when solving multiobjective optimization problems (MOPs). However, in MOPs, different objective functions may possess different properties. Hence, it can be beneficial to build objective-wise optimization strategy for each objective separately. This paper presents a single objective guided multiobjective optimization (SOGMO) framework to solve continuous MOPs. In SOGMO framework, a solution is first selected from archive, and then objective-wise learning strategy is developed for each objective separately. Finally, all the objectives of the considered solution can be simultaneously optimized in parallel by the cooperation of objective-wise learning process. An instantiation of SOGMO, called SOGMO-NFO, is designed by introducing a neighborhood field optimization (NFO), as objective-wise learning strategy. Simulation results show that SOGMO-NFO outperforms current state-of-the-art multiobjective evolutionary algorithms.