作　　者： ; ;

机构地区： 广东工业大学

出　　处： 《水力发电》 2008年第5期46-49,共4页

摘　　要： 随着电力市场的改革,水电厂经济调度的地位将日益突出。在考虑振动、出力限制、开停机等多种约束条件的情况下,提出并设计了一种基于混合神经网络和遗传算法的水电厂经济调度系统。为反映机组复杂的非线性工作特性,建立了基于人工神经网络方法的耗水量模型,在此基础上采用改进的遗传算法对机组进行了优化组合。结果表明:数字仿真及其现场应用都取得了满意的结果。 The economic dispatch of hydropower plant play more and more important role with the reform of power market. Based on neural network and genetic algorithm, a system for economic dispatch of hydropower plant is proposed and designed, which takes into consideration the multiple constraints such as vibration, unit commitment, etc. To reflect the real non-linear characteristic of generating unit, the neural network is applied to building the unit discharge model. On this basis, the economic dispatch is performed by an improved genetic algorithm. The results show that both the digital simulation and field application obtain satisfactory results.

关 键 词： 水电厂 遗传算法 神经网络 经济调度 多约束条件

领　　域： [水利工程]