改进的灰狼算法在电动汽车充电调度中的应用

针对灰狼优化算法（grey wolf opotimizer, GWO）易早熟收敛和陷入局部最优的缺点，提出一种基于精英反向学习的混合灰狼算法（grey wolf optimizer based on particle swarm optimizer,PSO-GWO）。首先，利用精英反向学习机制初始化种群，使种群保持多样性；然后提出一种非线性控制因子策略，增加算法的搜索能力，提高算法的收敛速度；最后基于差分进化和粒子群思想更新了位置方程，从而提升算法的收敛性能。采取10个基准测试函数将本文提出的改进的算法与差分进化算法、粒子群算法、传统灰狼算法、其他学者提出的改进灰狼优化算法进行对比。实验结果表明，本文提出的算法与其他算法相比，在求解多峰函数问题上效果显著，可以搜索到最优解0，同时求解最优非0解函数的效果也体现地较优越；同时运用改进的算法在实际电动汽车充电调度上进行了对比分析，发现也取得了不错的效果。

Application of Improved Grey Wolf algorithm based on elite reverse learning strategy in electric vehicle charging scheduling

Aiming at the shortcomings of grey wolf optimizer (GWO) which is easy to converge prematurely and fall into local optimization, a hybrid grey wolf optimizer based on elite reverse learning (pso-gwo) is proposed. Firstly, the elite reverse learning mechanism is used to initialize the population to maintain the diversity of the population; Then a nonlinear control factor strategy is proposed to increase the search ability of the algorithm and improve the convergence speed of the algorithm; Finally, the position equation is updated based on differential evolution and particle swarm optimization, so as to improve the convergence performance of the algorithm. Ten benchmark functions are used to compare the improved algorithm proposed in this paper with differential evolution algorithm, particle swarm optimization algorithm, traditional gray wolf algorithm and improved gray wolf optimization algorithm proposed by other scholars. The experimental results show that compared with other algorithms, the algorithm proposed in this paper has remarkable effect in solving the multi-modal function problem, can search the optimal solution 0, and has better effect in solving the optimal non-0 solution function at the same time; At the same time, the improved algorithm is used to compare and analyze the actual electric vehicle charging scheduling, and it is found that it has also achieved good results.