供水系统直接优化调度遗传算法求解模型研究

针对目前我国完全采用微观模型的方法难以满足供水系统优化调度的要求的现实，以测压点压力
宏观模型、水源供水量和水源供水水头之间的关系模型替代复杂的管网水力平衡方程，并以每一泵站每
时段应有水泵运行求得的出水量和管网求得的需水量相等的条件,建立了大型供水系统的多目标混合离散
变量的直接优化调度模型.利用遗传算法对直接优化调度模型进行求解，提出了对各种约束条件处理的方
法;针对遗传算法容易早熟等的不足，提出将遗传算法和模拟退火技术相结合，并采用自适应交叉和变异
率的解决方法.算例计算表明，该算法具有较强的适用性.

Research on genetic algorithm model of direct optimal operation of water supply system

In view of the actual situation that the method of adopting microcosmic model can hardly satisfy the demands of optimal scheduling of water supply system in China now, the complicated network hydraulic equations were replaced by macroscopic nodal pressure model and the model of relationship between supply flow and water source head. The direct optimal operation model with multi-objective mixed discrete variables of large-scale water supply system was established, based on the condition that the outlet flow obtained by the Q-H pump curve of pump station at each time period was equal to the needed water flow obtained by water distribution network. Genetic algorithm was introduced to deal with the direct optimal operation model of water supply. Methods for handling each constraint condition were put forward, and overcome the shortcoming such as premature convergence of genetic algorithm, a solving method was brought forward in which genetic algorithm was combined with simulated annealing technology and selfadaptive crossover and mutation probabilities were adopted. An application example shows the feasibility of this algorithm.