A Multiobjective Evolutionary Algorithm Based on Objective-Space Localization Selection

External archive guided radial-grid multi objective differential evolution

Differential evolution (DE) is a robust evolutionary algorithm for solving single-objective and multi-objective optimization problems (MOPs). While numerous multi-objective DE (MODE) variants exist, prior research has primarily focused on parameter control and mutation operators, often neglecting the issue of inadequate population distribution across the objective space. This paper proposes an external archive-guided radial-grid-driven differential evolution for multi-objective optimization (Ar-RGDEMO) to address these challenges. The proposed Ar-RGDEMO incorporates three key components: a novel mutation operator that integrates a radial-grid-driven strategy with a performance metric derived from Pareto front estimation, a truncation procedure that employs Pareto dominance in conjunction with a ranking strategy based on shifted similarity distances between candidate solutions, and an external archive that preserves elite individuals using a clustering approach. Experimental results on four sets of benchmark problems demonstrate that the proposed Ar-RGDEMO exhibits competitive or superior performance compared to seven state-of-the-art algorithms in the literature.

Multi-objective particle swarm optimization with reverse multi-leaders

Despite being easy to implement and having fast convergence speed, balancing the convergence and diversity of multi-objective particle swarm optimization (MOPSO) needs to be further improved. A multi-objective particle swarm optimization with reverse multi-leaders (RMMOPSO) is proposed as a solution to the aforementioned issue. First, the convergence strategy of global ranking and the diversity strategy of mean angular distance are proposed, which are used to update the convergence archive and the diversity archive, respectively, to improve the convergence and diversity of solutions in the archives. Second, a reverse selection method is proposed to select two global leaders for the particles in the population. This is conducive to selecting appropriate learning samples for each particle and leading the particles to quickly fly to the true Pareto front. Third, an information fusion strategy is proposed to update the personal best, to improve convergence of the algorithm. At the same time, in order to achieve a better balance between convergence and diversity, a new particle velocity updating method is proposed. With this, two global leaders cooperate to guide the flight of particles in the population, which is conducive to promoting the exchange of social information. Finally, RMMOPSO is simulated with several state-of-the-art MOPSOs and multi-objective evolutionary algorithms (MOEAs) on 22 benchmark problems. The experimental results show that RMMOPSO has better comprehensive performance.

A robust performance evaluation approach for solution preservation in multiobjective optimization

Many real-world optimization problems have complex features, such as bias, multimodel, etc. Existing evolutionary algorithms mainly utilize solutions’ current performance to decide their survivals, which are not comprehensive enough to describe the evolving trend, and may misguide the evolve decision. In this paper, a novel robust performance evaluation approach for evolutionary multiobjective optimization algorithm is proposed. Here, the robustness refers to the performance fluctuation degree among several generations, which can be expressed by interval values in respect to the decision and objective spaces. Based on the robust performance evaluation, solutions can be selected and preserved considering their historical performance, and thus, the exploration strength in convergence potential areas can be maintained. Meanwhile, to construct an evolutionary algorithm that embeds robustness evaluation, a robust elite managerial method and a learning-based updating strategy are also designed. Experiments on multiobjective benchmark problems and a real-world optimization in a robotic manipulation system have proved the superiority of the proposed approach.