基于Epsilon-MOEA的给水系统多目标优化与决策

给水系统优化运行是多目标优化问题,决策者需要从众多的候选方案中筛选出一个综合性能最好的方案.将多目标进化算法与多属性决策相接合,采用两阶段方法来求解供水系统的多目标优化与决策问题.首先构建供水系统的多目标优化模型,包括供水系统的运行费用与维护费用最小化,以及水压服务水平的最大化,运用多目标进化算法Epsilon-MOEA求解,生成Pareto解集.然后,基于信息熵方法得到属性权重,用逼近理想的排序方法(TOPSIS)进行多属性决策(MADM)研究,对Pareto最优解进行排序.算例应用表明,该方法能够对供水系统运行的多个目标进行优化,并使决策者能够从众多的候选方案中选出综合性能较好的方案.

Multiple objective optimization and decision making in water distribution system using Epsilon-MOEA

In this paper,the combination of multi-objective evolutionary algorithm(MOEA) and multi-attribute decision making(MADM) is proposed to solve the optimal operation problem in water distribution system.This approach is composed of two steps.In the first step,a multi-objective optimizing model is built,which includes the operation cost,the minimum of maintenance cost and the maximum of hydraulic service level.Multi-objective evolutionary algorithm(Epsilon-MOEA) is employed to achieve the set of Pareto solution.In the second step,based on information entropy weight,and the technique for order preference by similarity to ideal solution(TOPSIS),a multi-attribute decision making approach is adopted to rank solutions to determine the best solution.Practical application of this method shows that Epsilon-MOEA is a promising multiple objective evolutionary algorithm to solve the optimal operation problem in water distribution system,and can help decision makers to choose the best solution from Pareto sets.