基于Sin混沌反向学习与柯西变异灰狼优化算法研究

Research on Grey Wolf Optimization Algorithm Based on Sin Chaos Backward Learning and Cauchy Mutation

摘要: 灰狼优化算法在收敛精度和局部寻优方面存在一定的缺点，本文提出了一种改进的灰狼优化算法。为了保证灰狼种群同时具有遍历性和随机性，该算法将Sin混沌与反向学习策略相结合对灰狼种群进行了初始化。为了提高全局最优搜索能力，将柯西变异用于更新灰狼种群，从而跳出局部最优的问题。同时，为了提高局部搜索能力和提高收敛精度，引入权值因子的方法进行改进。通过选取7个标准测试函数，验证改进灰狼优化算法的有效性。实验表明，与灰狼优化算法、鲸鱼优化算法和蜻蜓优化算法相比较，本文提出的改进的灰狼优化法性能具有一定的优势。

Abstract: The grey wolf optimization algorithm has certain shortcomings in terms of convergence accuracy and local optimization. This paper proposes an improved grey wolf optimization algorithm. In order to ensure that the grey wolf population has both ergodicity and randomness, this algorithm combines Sin chaos with a reverse learning strategy to initialize the grey wolf population. In order to improve the global optimal retrieval ability, Cauchy mutation is used to update the grey wolf population, thus avoiding the problem of local optima. At the same time, in order to improve local search ability and convergence accuracy, a weight factor method is introduced for improvement. 7 standard test functions are selected to verify the effectiveness of the improved Grey Wolf optimization algorithm. The experiment shows that compared with the Grey Wolf optimization algorithm, Whale optimization algorithm, and Dragonfly optimization algorithm, the improved Grey Wolf optimization method proposed in this paper has certain advantages in performance.