Abstract:

Aiming at the shortcomings of Equilibrium Optimizer （EO） such as low optimization accuracy， slow convergence and being easy to fall into local optimum， a new EO in consideration with distance factor and Elite Evolutionary Strategy （EES） named E-SFDBEO was proposed. Firstly， the distance factor was introduced to select the candidate solutions of the equilibrium pool， and the adaptive weight was used to balance the fitness value and distance， thereby adjusting the exploration and development capabilities of the algorithm in different iterations. Secondly， the EES was introduced to improve the convergence speed and accuracy of the algorithm by both elite natural evolution and elite random mutation. Finally， the adaptive t-distribution mutation strategy was used to perturb some individuals， and the individuals were retained with greedy strategy， so that the algorithm was able to jump out of the local optimum effectively. In the simulation experiment， the proposed algorithm was compared with 4 basic algorithms and 2 improved algorithms based on 10 benchmark test functions and Wilcoxon rank sum test was performed to the algorithms. The results show that the proposed algorithm has better convergence and higher solution accuracy.

Key words: Equilibrium Optimizer (EO), distance factor, Elite Evolutionary Strategy (EES), adaptive weight, global optimization

摘要：

针对平衡优化器（EO）存在寻优精度低、收敛速度慢、容易陷入局部最优的不足，提出一种考虑距离因素与精英进化策略的平衡优化器（E-SFDBEO）。该算法首先在平衡池候选解的选择中引入距离因素，通过自适应权重平衡适应度值和距离，调节算法在不同迭代时期的探索和开发能力；其次引入精英进化策略（EES），以精英自然进化和精英随机变异两种方式提升算法的收敛速度和精度；最后使用自适应t分布变异策略对部分个体施加扰动，并以贪心策略对个体进行保留，使算法能够有效跳出局部最优。在仿真实验中对所提算法与4种基本算法和2种改进算法在10个基准测试函数进行比较，并对算法进行Wilcoxon秩和检验，结果表明所提算法具有更好的收敛性和更高的求解精度。

关键词: 平衡优化器, 距离因素, 精英进化策略, 自适应权重, 全局优化