دانلود رایگان مقاله گونه بر اساس ازدحام ذرات بهینه ساز توسط حافظه

ABSTRACT

Both the species strategy and the memory scheme are efficient methods for addressing dynamic optimization problems. However, the combination of these two efficient techniques has scarcely been studied. Thus, this paper focuses on how to hybridize these two methods. In this paper, a new swarm updating method is proposed to enhance a representative species-based algorithm, i.e., SPSO (Species-based Particle Swarm Optimization), and the new algorithm is named MSPSO. MSPSO has two characteristics. First, the number of replaced particles in the current swarm is set adaptively according to the number of species. To not substantially destroy the exploitation capability of each species, no more than one particle in each species is replaced by the memory. Second, the retrieved memory particles are categorized according to their fitness values and their distances to the seed of the closest species. Aimed at enhancing the search in both promising areas and existing species, each category is processed by different operations. The MPB, Cyclic MPB and DRPBG are used to test the performance of MSPSO. Experimental results demonstrate that MSPSO is competitive for dynamic optimization problems.

6. Conclusion and future work

Both the memory scheme and the multi-swarm strategy are effective techniques for dynamic optimization problems. However, their hybrids have scarcely been studied. In most cases, employing the traditional population updating methods to enhance the performance of the multi-swarm algorithms by the memory may not yield ideal results. Aimed at the two aforementioned problems, a new swarm updating method is proposed in this paper and embedded into the typical species-based algorithm SPSO. The number of replaced particles, instead of being predefined, is set adaptively according to the number of species. This may alleviate the impact generated by the unsuitable assignment. To not substantially destroy the exploitation capability of each species, no more than one particle is replaced by the memory in each species. The retrieved memory particles are grouped into four categories and processed by different strategies. To demonstrate the validity and feasibility of the new method, the proposed algorithm MSPSO is compared with SPSO and its variants on both the MPB and CMPB. Moreover, MSPSO is tested on the DRPBG and compared with other algorithms. The experimental results show that MSPSO is competitive. The effect of the memory size on the performance of the algorithm is tested in different dynamic scenarios. The experimental results indicate that the optimal setting of the memory size is largely influenced by the number of peaks in the search space. If there are few peaks, a small memory size would be favorable.When the number of peaks becomes larger, a large memory size would be better. How to set the memory size adaptively is a topic of our future work.