基于级联网络的电力系统短期负荷预测

电力系统短期负荷预测对电力系统运行设计具有十分重要的意义。因此，在分析了电力负荷运行曲线的基础上，提出了一种基于级联模糊神经网络的预测模型。该模型采用基于神经网路理论的模糊模型参数辨识方法，很适合于复杂系统的模糊预测和控制。详细地对输入量的选择和学习算法进行了分析。实例表明，此方法具有町靠、鲁棒性好和快速等特点，优于神经网络电力负荷预报方法。

Cascaded Network Based Short-term Load Forecasting of Electric Power System

Short-term load prediction of electric power system is important to operation and design of power system. Except the operation curves of electric power system toad are analyzed, the predictive model based on a cascaded fuzzy neural network is proposed. The model is suitable for fuzzy prediction and control of complex system because the recognition method of fuzzy module parameters baaed on the theory of neural network is adopted. The selection for input variables and the learning algorithm are analyzed in detail. The test results reveal that the method possesses more advantages than neural network load forecasting method in electric power with reliability, robustness and fast speed.