基于累积式自回归动平均法和反向传播神经网络的短期负荷预测模型

针对电力系统短期负荷的特点建立了将累积式自回归动平均法(autoregressive integrated moving average，ARIMA)和采用反向传播算法(back propagation，BP)的神经网络法相结合的短期负荷预测模型。该模型利用ARIMA方法对线性时间序列逼近能力强的特点首先对预测日负荷进行预测，然后应用BP神经网络方法对预测结果进行修正，因此克服了单一算法存在的不足。应用该模型对某地区电网进行负荷预测，结果表明该方法的预测效果较好

A Short-Term Load Forecasting Model Based on ARIMA and BPNN

According to its features a short-term load forecasting model is built in which the autoregressive integrated moving average (ARIMA) is integrated with back propagation neural network (BPNN). By use of the strong approaching capacity to linear time series of ARIMA, the proposed model forecasts the load of the predicted day at first, then the load forecasted by ARIMA is modified by BPNN, thus the insufficiency of single algorithm is overcome. The forecasted results of an actual regional power system by the proposed model show that this method can offer better load forecasting results.