使用参数自由的声搜索方法进行水资源调配的设计优化
摘要:虽然仿生算法和元启发式算法应用于水资源调配优化设计时已经克服了基于梯度算法的不足,例如基因算法、模拟退火算法、紧急搜索算法,蛙跳算法、蚁群优化算法、声搜索算法、交叉墒算法、分散搜索算法、混合粒子群算法和蜂群优化算法,但是这些算法还要求完成算法参数设置的任务。本研究为两个主要的算法参数(HMCR和PAR)提供了参数自由设置的技术,并且把这项技术和声搜索算法联系起来。该模型在一个普遍基准问题的优化设计中的得到应用,其结果很好的实现了总体最优值。因此,该项技术有望在一个更加友好的环境设计实践中得到应用。
Abstract: Although phenomenon-mimicking or metaheuristic algorithms, such as genetic algorithm, simulated annealing, tabu search, shuffled frog-leaping algorithm, ant colony optimization algorithm, harmony search, cross entropy, scatter search, hybrid particle swarm optimization, and honeybee mating optimization, have overcome the disadvantages of gradient-based algorithms when optimally designing water distribution networks, those algorithms require the extra tedious task of algorithm parameter setting. This study proposes a novelparameter-setting-free technique for two major algorithm parameters (HMCR and PAR) and combines it with the harmony search algorithm. When the proposed model is applied to the optimal design of a popular benchmark problem, it reaches the global optimum with good results. Thus, the technique is expected to be used in the real-world design process under a more user-friendly environment.