提出求解水电站优化调度问题的新方法——遗传算法，它不同于经典优化算法的特点是，从多个初值点开始寻优，沿多路径搜索实现全局或准全局最优，计算过程中不需要存储状态或决策变量离散点，大大减少计算机内存，不必求导运算，编程简单，是一种有效的自适应随机搜索算法.

This paper presents a genetic algorithm for hydro-power station scheduling.It has over existing mathematical programming methods.The GA uses a population of points at a time in contrast to the single point approach by the traditional ones.The GA will guarantee to find the global optimum. The GA has the benefit of greatly reduced memory requirement. It does not demand problem derivative.It is a good adaptive stochastic search method.A case study is given.