JiSMART2021—034: A Deep Learning-Based Method for Residential Energy Demand Forecasting

Abstract

The application of smart technology for residential energy consumption management requires efficient and accurate hourly forecasting of energy demands. In recent years, the LSTM network had made remarkable achievements in the field of load forecasting. This paper proposed a deep learning method based on an attentionalbased LSTM network (A-LSTM). To evaluate the application potential of the A-LSTM model in real cases, the training set and test set used in experiments are the real energy consumption data collected by “Jono Zero Carbon Smart Community” in Kitakyushu, Japan. Pearce analysis was first carried out on the source data set and built the target database. Then three baseline models were built. Finally, the applications are performed on the target database, and the results are analyzed from multiple perspectives, including model comparisons on different sizes of the training set, model comparisons on different system operation modes, graphical examination, etc. The results showed that the performance of the A-LSTM model was better than other baseline models, it could provide accurate and reliable hourly forecasting for residential energy demand.