飞蛾火焰优化算法及其在梯级水库优化调度中的应用

Moth-Flame Optimization Algorithm and Its Application in Reservoir Optimal Operation

利用一种新型群智能仿生算法——飞蛾火焰优化(MFO)算法求解某梯级水库群丰、平、枯优化调度问题,求解结果与混合蛙跳算法(SFLA)、粒子群优化算法(PSO)、布谷鸟搜索算法(CS)和入侵杂草优化算法(IWO)的求解结果进行比较。结果表明,MFO算法丰、平、枯优化调度发电量分别比其他4种算法增加了0. 179 2～0. 960 2、0. 097 2～0. 564 1、0. 082 4～0. 322 0亿kW·h,具有较好的优化调度效果。将MFO算法应用于实际工程,验证了该算法具有较好的收敛精度和全局极值寻优能力,是一种有效可行的水库群优化调度模型求解方法,可为求解水库优化调度问题提供新的途径和方法。

Using a new type of swarm intelligence mimic algorithm-moths to a flame optimization(MFO)algorithm to solve a cascade reservoir,flat,dry optimization scheduling problem.And the results are compared with results of SFLA(SFLA),particle swarm optimization(PSO),the cuckoo search algorithm(CS)and the intrusion weed optimization algorithm(IWO).The results show that the optimal scheduling power generation of the MFO algorithm is 0.1792~0.9602,0.0972~0.5641,and 0.0824~0.3220 million kW/h higher than the other four algorithms,respectively,and has a better optimal scheduling effect.This paper applies the MFO algorithm to practical engineering and verifies that the algorithm has good convergence accuracy and global extremum optimization ability.It is an effective and feasible solution method to the reservoir group optimization scheduling model,and it can provide a new solution to reservoir optimal scheduling problems.