基于动态规划和遗传算法的混合算法研究

A Hybrid Algorithm Based on Dynamic Programming Method and Genetic Algorithm

动态规划法和遗传算法是目前在水电站厂内经济运行中广泛应用的两种优化算法,文章提出了一种基于动态规划法和遗传算法的混合优化算法来分别解决大规模机组组合问题中空间最优化和时间最优化的计算机求解问题。避免了遗传算法计算速度缓慢的问题,又避免了动态规划法的"维数灾"问题。最后使用清江隔河岩水电站的4台机组的运行数据进行了仿真研究,并和完全使用动态规划法的结果进行了比较,获得了良好的效果,说明该混合优化算法对于厂内经济运行是一种可行的算法。

The dynamic programming method and genetic algorithm are two algorithms widely applied to the hydropower station's in-house economical operation. This paper presents a hybrid algorithm that applies the dynamic programming method and genetic algorithm to the space optimization and time optimization respectively. The hybrid algorithm avoids both the slow problem of genetic algorithm and the high multidimensional problem of dynamic programming method. Applying the method to the Geheyan hydropower station, the results show that the method is efficient for economical operation of hydropower station.