Neural Networks for Residential Load Forecasting and the Impact of Systematic Feature Identification

Authors Nicolai Bo Vanting1*, Zheng Ma1, Bo Nørregaard Jørgensen1 Affiliations 1 SDU Center for Energy Informatics, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark Abstract Due to political decisions and ambitions, the energy system faces challenges in the coming years. Especially distribution system operators are affected by the challenges because they maintain grid control. Accurate predictions of the electricity load can help DSOs better plan and maintain their grid. The study aims to test a systematic data identification and selection process to forecast the electricity load of Danish residential areas. The five-ecosystem CSTEP framework maps relevant independent variables on the cultural, societal, technological, economic, and political dimensions. Based on the literature, a recurrent neural network (RNN), long-short-term memory network (LSTM), gated recurrent unit (GRU), and feed-forward network (FFN) are evaluated and compared. The models are trained and tested using different data inputs and forecasting horizons to assess the impact of the systematic approach and the practical flexibility of the models. The findings show that the models achieve equal performances of around 0.96 adjusted R2 score and 4-5% absolute percentage error for the one-hour predictions. Forecasting 24 hours gave an adjusted R2 of around 0.91 and increased the error slightly to 6-7% absolute percentage error. The impact of the systematic identification approach depended on the type of neural network, with the FFN showing the highest increase in error when removing the supporting variables. The GRU and LSTM did not rely on the identified variables, showing minimal changes in performance with or without them. The systematic approach to data identification can help researchers better understand the data inputs and their impact on the target variable. The results indicate that a focus on curating data inputs affects the performance more than choosing a specific type of neural network architecture.