Particle swarm optimizers for Pareto optimization with enhanced archiving techniques

Abstract

During the last decades, numerous heuristic search methods for solving multi-objective optimization problems have been developed. Population oriented approaches such as evolutionary algorithms and particle swarm optimization can be distinguished into the class of archive-based algorithms and algorithms without archive. While the latter may lose the hest solutions found so far, archive based algorithms keep track of these solutions. In this article a new particle swarm nptimization technique, called DOPS, for multi-objective optimization problems is proposed. DOPS integrates well-known archiving techniques from evolutionary algorithms into particle swarm optimization. Modifications and extensions of the archiving techniques are empirically analyzed and several test functions are used to illustrate the usability of the proposed approach. A statistical analysis of the obtained results is presented. The article concludes with a discussion of the obtained results as well as ideas for further research.

Multi-Objective Particle Swarm Optimization (MOPSO) based on Pareto Dominance Approach

“…MOPSO was competitive against NSGA-II and PAES on typical benchmark problems, under common performance metrics, and it is currently considered one of the most typical multi-objective PSO approaches. A sensitivity analysis on the parameters of the algorithm, including the number of hypercubes used, can provide further useful information on this simple though efficient approach [10], [11].…”

A fuzzy particle swarm optimization algorithm for computer communication network topology design

“…In MOO PSO, the leaders are the personal best positions (local leaders) and neighborhood best positions (global leaders). The basic idea is to select leaders to the particles that are non-dominated with respect to the rest of the swarm [5,9,19,24,40,41,47,49]. and 'OR' operators appeared to be quite rigid [36].…”

RhoGTPase Involvement in Breast Cancer Migration and Invasion

“…The grid size is limited, so those particles located in less density cube have a higher priority for retention than those in the crowding area. In [56], similar to the adaptive grid procedure, an adaptive local archive, grouped by clustering algorithm, is applied to the multiple-swarm MOPSO to improve the well-distributed sections of Pareto front that associate with each subswarm.…”

“…Secondly, the particle within such hypercube is randomly selected as the nbest. The grid concept is also adopted in [56] as a external archive. In [55,62], gBest and pBest position are both selected from archive and in [41], both of them are selected from group leaders in the adaptive local archive through a roulette wheel selection,.…”

“…The selection probability is inversely proportional to the number of dominated solutions inside the cube (see Figure 3). In [56], an elitist policy is performed to store nondominated solutions in an external archive with grid structure and a uniform mutation is applied.…”