基于食物链机制的动态多物种粒子群算法

针对粒子群优化(PSO)算法在解决多峰函数时容易陷入局部最优的问题,提出了一种基于食物链机制的动态多物种粒子群(DSPSO)算法。受生物界的启发,引入食物链机制来保证种群的多样性,并结合繁殖机制使得算法具有良好的优化性能。食物链机制中,整个标榜群被分为几个子种群,每个子种群都能够捕食另外一个子种群。通过一定概率发生的捕食现象使得标榜群得以进化,剔除对种群贡献小的粒子,并通过繁殖策略生成新的粒子。种群通过不断地进化保证了种群的多样性,同时通过剔除较差粒子的误导作用使算法的进化更有效率。为了验证算法的有效性,选择了包括偏移函数、旋转函数在内的10个测试函数来测试DSPSO算法的性能。实验结果表明DSPSO算法有着良好的寻优性能。与PSO、局部版本的粒子群(LPSO)算法、动态多群粒子群(DMS-PSO)算法和全面学习粒子群(CLPSO)算法相比,DSPSO算法不仅能够得到较高精度的解,而且还具有较高的可信度。

Dynamic multi-species particle swarm optimization based on food chain mechanism

a novel Dynamic multi-Species Particle Swarm Optimization (DSPSO) algorithm based on food chain mechanism was proposed aiming at the problem that the basic Particle Swarm Optimization (PSO) algorithm is easy fall into local optimal solution when solving multimodal problems. Inspired by the natural ecosystem, a food chain mechanism and a reproduction mechanism were employed to keep the swarm diversity and good performance. In food chain mechanism, the swarm was divided into several sub-swarms, and each sub-swarm could prey on the others. The memory leader swarm was evolved and the less contributed particle was eliminated through predation, and then the new particle was generated through reproduction mechanism. The diversity was kept through the evaluation of the swarm, and the efficiency of the algorithm was enhanced through eliminating the misleading effect of the less contributed particles. In order to verify the effectiveness of the algorithm, ten benchmark problems including shifted problems and rotated problems were chose to test the performance of DSPSO. The experimental results show that DSPSO has a well optimizing performance. Compared with PSO algorithm, Local version Particle Swarm Optimization (LPSO) algorithm, Dynamic Multi-Swarm Particle Swarm Optimization (DMS-PSO) algorithm and Comprehensive Learning Particle Swarm Optimization (CLPSO) algorithm, DSPSO algorithm not only obtains more accurate solutions, but also has higher reliability.