基于自适应遗传算法的渠系优化配水模型研究

针对现有的建立在假定下级渠道配水流量相等基础上的渠道优化配水模型与绝大多数渠系实际配水要求不相符合等问题,研究了下级渠道流量不等时的渠系优化配水模型及其求解方法,并通过实例对基于自适应遗传算法和基本遗传算法的模型求解方法进行了比较。结果表明,与传统方法编制的配水方案相比,提出的模型和算法确定的渠系优化配水方案斗渠配水时间搭配合理、支渠配水流量均匀,符合优化配水原则;利用自适应遗传算法求解模型,能在进化过程中按个体优劣和群体分散程度自动调整遗传控制参数,可显著加快收敛速度和提高计算稳定性,具有较高的工程应用价值。

Study of Optimal Water Delivery Scheduling Models Based on Adaptive Genetic Algorithm

The present optimal water delivery scheduling models are based on the assumed equal design discharges of lateral canals, which are not in accordance with practical water delivery scheduling demand in most irrigation systems. In order to solve this problem, a model of lateral canals with unequal discharges and a solution method were proposed; the model solution methods based on AGA (Adaptive Genetic Algorithm) and SGA (Simple Genetic Algorithm) were compared with traditional method by using a practical irrigation system example. The results show that the lateral channels water delivery time is more uniform, and the branch water distribution is more homogeneous of the water delivery plan determined by the new model than the traditional method. The model solution method based on AGA can automatically adjust to the genetic controlling parameters on the basis of values of individual fitness and degree of population dispersion, which is more rapid and stable than the GA method, so it has a higher practical value in irrigation system management.