A novel particle swarm optimization for constrained optimization problems

作者：Li, Xiangyong^*; Tian, Peng; Kong, Min

来源：18th Australian Joint Conference on Artificial Intelligence, AI 2005: Advances in Artificial Intelligence , China,Tibet Autonomous Region,Ali, 2005-12-05 to 2005-12-09.

• Constrained optimization problems
• Mutation strategy
• Particle swarm optimization
• Population diversity

This paper proposes a novel particle swarm optimization (PSO) for solving constrained optimization problems. Based upon the acceptable assumption that any feasible solution is better than any infeasible solution, a new mechanism for constraints handling is incorporated in the standard particle swarm optimization. In addition to the mechanism of constraints handling, a mutation strategy to increase population diversity is added to the proposed algorithm to improve convergence. Experimental results compared with genetic algorithm and a standard PSO show that the proposed algorithm is a desirable and competitive algorithm for solving constrained optimization problems.

• 出版日期2005
• 单位上海交通大学