基于经验模式分解与LSTM神经网络的短期电价预测模型

Short-term electricity price forecasting model based on empirical mode decomposition and LSTM neural network

在开放的电力市场中,日前电价预测是个重要的研究方向。本文提出了一种基于经验模式分解(EMD)与长短期记忆神经网络(LSTM)的序列电价预测模型,使用EMD提取电价序列中的周期分量与趋势分量,利用LSTM分别对周期分量与趋势分量进行序列预测,输出各分量的预测结果,通过支持向量机回归(SVR)叠加各分量的预测序列生成预测价格序列。最后,以美国PJM电力市场的电价数据为算例,与ARIMA模型、单一LSTM神经网络模型的预测结果进行比较,验证了EMD-LSTM-SVR模型能够提高短期电价预测精度。

Short-term electricity price forecasting is an important research domain in electricity market.In this paper,a hybrid model for short-term electricity price forecasting based on empirical mode decomposition(EMD)and long short-term memory neural network(LSTM)is proposed.First,EMD is used to extract the periodic component and trend component in the series,and then LSTM is used to predict the periodic component and trend component respectively;finally,the forecast price sequence is generated by the support vector machine regression(SVR)superposing forecast series of each component.Taking the data of US PJM power market as a case study,the EMD-LSTM-SVR model is confirmed to improve the prediction accuracy of short-term electricity price comparing with the results of ARIMA model and single LSTM model.