摘要
本文针对综合利用水库的特点,建立了水库优化调度的马尔可夫决策规划模型。文中论述了策略迭代的原理和方法,探讨了策略迭代法的应用。
A mathematical model of Markovian decision programming is proposed in this paper, it is in accordance with the special characterteristic of the multipuropose reservoirs. The principle and method of policy iteration is discussed. At the same time, the application of policy iterative method is discussed.
关键词
策略迭代法
水库
优化调度
Policy iterative method
markovian decision programming
optimal dispatching
