Aggregated Load Prediction Based on Convolutional Long and Short-Term Memory Network

Abstract

With the rapid development of economy, the proportion of air-conditioning is increasing. Due to modeling difficulties and the different user habits, the current prediction error of air-conditioning load is large. Thus, this paper uses the idea of data-driving modeling and proposes a kind of convutational long short term neural networks (ConvLSTM) based on deep learning to build air-conditioning aggregation model. Experiments show the effectiveness of the method.