基于BP神经网络的短期负荷预测建模仿真

通过BP神经网络与Matlab相结合，建立起三层四功能单元的BP神经网络短期负荷预测模型，并采用某条线路1年的历史负荷波动数据对模型进行“学习”训练。预测一日24小时负荷数据的Matlab仿真及误差分析结果表明，所构筑的BP神经网络模型具有较高的可靠性和准确性，误差率可以有效地控制在2％以内。BP神经网络模型大大提高了短期负荷预测数据的处理效率与可信性，是研究电力系统经济调度的一种新的非线性建模仿真模型。

Modeling and simulation of electricity short-term load forecast based on BP neural network

Combining BP neural network and Matlab, the three layer and four-function BP neural network shortterm load forecasting model is built. One year load fluctuations history data is used to training the model. The daily load predicting data by Matlab simulation and error analysis result show that the error rate can be effectively controlled in less than 2% which verified the reliability and accuracy of the constructed BP neural network model. The BP neural network model greatly improves the efficiency and accuracy of short-term load forecasting data processing, it is a new model of nonlinear modeling and simulation model tbr doing research on the power economic dispatch system.