改进鲸鱼算法在多目标水资源优化配置中的应用

为了使鲸鱼优化算法(WOA)能更好地解决复杂多目标水资源优化配置问题,首先采用Logistic映射进行种群位置初始化,提高初始化种群位置的质量,并加入惯性权重增强局部搜索能力,从而实现对WOA的改进;其次,将改进后的鲸鱼算法(AWOA)应用于以经济效益和社会效益最大(缺水量最小)为目标的邯郸市水资源优化配置模型;最后,以求解所得Pareto前沿中缺水量最小为特殊偏好,将AWOA与WOA和粒子群算法(PSO)从迭代过程和求解结果上进行了对比分析。从迭代过程来看,AWOA比PSO和WOA能够以较快的速度收敛,WOA收敛速度最慢;从求解结果分析,由AWOA所得经济效益和社会效益均优于由WOA和PSO所得结果。因此,AWOA在收敛速度和收敛精度上均得到了较大幅度的提升,其应用于多目标水资源优化配置求解是可行和有效的。

Application of ameliorative whale optimization algorithm to optimal allocation of multi-objective water resources

In order to make whale optimization algorithm ( WOA) better to solve the complicated problem from the optimal allocation of multi-objective water resources，the location of the population is initialized with Logistic mapping for enhancing the quality of the initialized location of population at first，and then inertia weight is added to enhance the local search ability，so as to realize the amelioration of WOA. Secondly，the ameliorative whale optimization algorithm ( AWOA) is applied to the Handan water resources optimal allocation model which takes the maximizations of both the economic benefit and social benefit ( the minimization of water shortage) therein as its target. At last，by taking solving the obtained minimization of water shortage in the Pareto front as the special preference，the iterative processes and the solving results of AWOA，WOA and particle swarm optimization ( PSO) are compared and analyzed. In the aspect of the iterative process，AWOA has a faster converging speed than that of PSO and WOA，in which the converging speed of WOA is the slowest. The analysis on the iterative results shows that both the economic benefit and social benefit obtained from AWOA are better than those got from WOA and PSO. Therefore，both the converging speed and converging accuracy of AWOA are largely enhanced，thus it is feasible and effective to be applied to solve the optimal allocation of multi-objective water resources.