LS-LSTM-AE: Power load forecasting via Long-Short series features and LSTM-Autoencoder

Abstract

Aiming at weak representation ability and severe loss of time series features in the traditional methods when facing large-scale and complex power load forecasting tasks, an LSTM-Autoencoder model that integrates long-term and short-term features of the samples is proposed for load forecasting. The encoder part simultaneously receives long time series and short time series as input to extract time series features of different levels and generate related latent vectors. The decoder tries to reconstruct the input sequence while outputting the prediction results to ensure that the latent vectors are meaningful. In addition, the model also uses a mixture of supervised and unsupervised training methods. Experiments based on a publicly available dataset from Alberta Electric System Operator showed that the method presented in this research is superior to many existing mainstream methods, with a mean absolute error of less than 52MW between the prediction results and the actual load values.

Keywords

• Load forecasting
• Deep learning
• LSTM
• Autoencoder
• Unsupervised learning
• Supervised learning