基于补偿模糊神经网络和线性模型的短期电力负荷预测sfsfsf

在考虑了气象因素对负荷的影响的基础上，提出了一种补偿模糊神经网络和线性模型相结合的短期电力负荷预测新方法。首先采用补偿模糊神经网络求出峰、谷负荷，然后利用线性外推法求出未来1日中24个时刻的负荷值。该方法具有神经网络和线性模型的优点，实例仿真结果表明其具有较快的收敛速度、较高的预测精度和较强的鲁棒性。

Short-Term Load Forecasting Based on Compensated FuzzyNeural Networks and Linear Modelssfsfsf

Taking the influence of meteorological factors on electrical load into account, a novel short-term load forecasting method is proposed, in which the compensated fuzzy neural network is integrated with linear model and the loads in working days and rest days are forecasted respectively. At first the peak load and valley load are obtained by compensated fuzzy neural network, then 24 hourly load values of the next day are solved by linear extrapolated method. The proposed method simultaneously possesses the advantages of both neural network and linear model. Simulation results show that the proposed method has good performances in convergence speed, forecasting accuracy and robustness.