Evaluation of neural networks for residential load forecasting and the impact of systematic feature identification

被引：1
作者：
Vanting N.B. [1 ]
Ma Z. [1 ]
Jørgensen B.N. [1 ]
机构：
[1] SDU Center for Energy Informatics, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense
来源：
Energy Informatics | 2022年 / 5卷 / Suppl 4期
关键词：
Artificial neural network; Ecosystem; Feature identification; Feature selection; Recurrent neural network; Residential electricity consumption; Short-term load forecasting;
D O I：
10.1186/s42162-022-00224-5
中图分类号：
学科分类号：
摘要：
Energy systems face challenges due to climate change, distributed energy resources, and political agenda, especially distribution system operators (DSOs) responsible for ensuring grid stability. Accurate predictions of the electricity load can help DSOs better plan and maintain their grids. 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 1-h predictions. Forecasting 24 h 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. © 2022, The Author(s).
引用
收藏
相关论文
共 59 条
  • [1] Ahmad T., Chen H., Utility companies strategy for short-term energy demand forecasting using machine learning based models, Sustain Cities Soc, 39, pp. 401-417, (2018)
  • [2] Al-Rashid Y., Paarmann L.D., Short-term electric load forecasting using neural network models, Proceedings of the 1996 IEEE 39Th Midwest Symposium on Circuits & Systems Part 3 (Of 3), pp. 1436-1439, (1996)
  • [3] Andersen F.M., Baldini M., Hansen L.G., Jensen C.L., Households’ hourly electricity consumption and peak demand in Denmark, Appl Energy, 208, pp. 607-619, (2017)
  • [4] Biewald L., Experiment Tracking with Weights and Biases, (2020)
  • [5] Billanes J.D., Ma Z., Jorgensen B.N., Consumer central energy flexibility in office buildings, J Energy Power Eng, 11, 10, pp. 621-630, (2017)
  • [6] Billanes J.D., Ma Z., Jorgensen B.N., The bright green hospitals case studies of hospitals’ energy efficiency and flexibility in Philippines, 2018 8th international conference on power and energy systems (ICPES), pp. 190-195, (2018)
  • [7] BBR Information, (2022)
  • [8] Cho K., van Merrienboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., Et al., Learning phrase representations using RNN encoder–decoder for statistical machine translation, (2014)
  • [9] Christensen K., Ma Z., Vaerbak M., Demazeau Y., Jorgensen B.N., Agent-based decision making for adoption of smart energy solutions, IV International Congress of Research in Sciences and Humanities Science and Humanities International Research Conference (SHIRCON 2019), (2019)
  • [10] Christensen K., Ma Z., Jorgensen B.N., Technical, economic, social and regulatory feasibility evaluation of dynamic distribution tariff designs, Energies, 14, 10, (2021)
123456