基于改进差分进化算法的万安水库防洪优化调度

Optimal Operation of Flood Control in Wan’an Reservoir Based on Improved Differential Evolution Algorithm

水库防洪调度问题具有多阶段、非线性和多重复杂约束特性,研究其高效稳定求解方法有助于提升其防洪优化调度效果。差分进化算法(DE)作为一种启发式智能优化方法在水库优化调度应用中效果较好,但受其随机搜索策略影响搜索易早熟收敛陷入局部最优。为平衡DE的全局和局部搜索能力,提出了一种改进差分进化算法(SDE),通过考虑适应度排序的差分变异策略用于提升搜索能力,并通过随机选择机制用于提升开发能力。相关数值试验验证了SDE收敛能力显著优于粒子群算法(PSO)、遗传算法(GA)、差分进化(DE)、连续域蚁群优化算法(ACOR)。实例分析结果表明,SDE在可行解、计算时间、精度、稳定性和速度指标上均优于逐步优化算法(POA)和DE,平均削峰率较POA提升0.17%-4.26%,较DE提升0.13%-1.26%。

The reservoir flood control operation problem has the characteristics of multi-stage,nonlinear and multiple complex constraints.The research of solution method will help to improve the effect of flood control optimal operation.Differential evolution algorithm(DE)has a good effect in the application of reservoir optimal operation,but it is prone to premature convergence and fall into local optimum due to the random search strategy.In order to balance the global and local search ability of DE,this paper proposed an improved differential evolution algorithm SDE,which is used to im-prove the search ability by considering the differential mutation strategy of fitness ranking and to improve the development ability by random selection mechanism.The related numerical experiments verified that the SDE convergence is signifi-cantly better than that of the DE,GA,PSO,and ACOR.The results of case study show that the SDE is better than POA and DE in terms of the feasible solution,calculation time,accuracy,convergence stability and speed.The average flood-peak rate of the SDE is 0.17%-4.26% higher than the POA,and is 0.13%-1.26% higher than the DE.