水电站机组负荷分配中动态规划与遗传算法性能比较

Comparison of Dynamic Programming and Genetic Algorithm in Unit Economic Load Dispatching of Hydropower Station

以三峡水库26台机组为研究背景,以计算精度、计算时间和算法稳定性为评价指标,采用数值试验方法,开展了动态规划和遗传算法在机组负荷分配中的性能比较研究。设计了计算精度相同比较计算时间和计算时间相同比较计算精度的具有可比性的数值实验方案,得到了动态规划和遗传算法的性能随机组数变化的关系。结果表明,在机组数小于10台时,遗传算法的性能优于动态规划;当机组数大于10台时,遗传算法性能低于动态规划法。

Taking the 26 units in Three Gorges Hydropower Station as the research background,the performance of Dynamic Programming(DP) and Genetic Algorithm(GA) in economic load dispatching of units is compared by numerical simulation method with the calculation accuracy,calculation time and algorithm stability as the evaluation indexes.Two comparable numerical experiment schemes are designed,one is to compare the time-cost under the assumption of setting same calculation precision,other is to compare the calculation precision under the assumption of setting same calculation time-cost.The relationship between the performance of DP and GA with the number of units are obtained.The results show that the performance of GA is better than that of DP when the number of units is less than 10,and is lower than that of DP when the number of units is more than 10.