电力系统短期负荷预测的模糊神经网络方法

针对电力系统短期负荷预测问题 ,考虑到气象因素对负荷的影响 ,提出了一种模糊神经网络的短期负荷预测方法 ,首先根据评价函数选取相似日学习样本 ,然后利用隶属函数对影响负荷的特征因素向量的分量进行模糊处理 ,采用反向传播算法 ,对 2 4点每点建立一个预测模型 ,提高了学习效能。适合在短期负荷预测中使用 ,具有较好的预测精度

Fuzzy Neural Network for Short-Term Load Forecasting

Aiming at short term load forecasting, this paper provides a fuzzy ANN method based on similar historical day data. BP arithmetic is adopted. Weather factors are considered. Similar historical days based on the evaluation function are selected. All factors influencing load are dealt with using membership function. Forecasting models are established for each point of 24 point, which can improve the learning performance with better forecasting accuracy. The method is generally suitable for short term load forecasting.