Abstract
The COVID-19 pandemic has caused fluctuations in electricity demand, altering people's lifestyles and electricity usage patterns, thereby affecting the accuracy of demand predictions. However, existing studies on electricity forecasting have not adequately considered the incorporation of COVID-19-related features and the analysis of electricity usage characteristics across different regions of the UK. Therefore, this paper, based on data of the UK's national electricity demand, conducts an analysis around the scenario of a large-scale health emergency in society. We explore the changing patterns and regional characteristics of electricity consumption during the COVID-19 pandemic, comparing the forecast results before and during the pandemic to illustrate its impact on the UK's electricity demand. By introducing COVID-19-related features into the models, we compare the forecast results before and after their inclusion. The results indicate that the COVID-19 pandemic has had a certain impact on the electricity prediction in the UK, leading to a 22.8% decrease in prediction accuracy. However, the models' correlation improved with the inclusion of COVID-19-related features, resulting in a 13.2% enhancement in prediction accuracy compared to the previous models. Additionally, the study summarizes other factors influencing electricity demand, such as power imports/exports and clean energy usage, as considerations for electricity distribution planning. This contributes to improving the accuracy of predicting the UK's electricity demand during COVID-19 pandemic, enabling the government to adjust power dispatching plans reasonably based on relevant factors, achieving rational distribution and efficient scheduling of power resources.
Similar content being viewed by others
Data availability
The electricity demand dataset for the United Kingdom is sourced from the National Grid Electricity System Operator (ESO), which is updated every two hours and can be used for time series forecasting. The website for accessing this dataset is the ESO Data Portal: Home | National Grid Electricity System Operator (nationalgrideso.com). The pandemic-related data is obtained from the UK government website, specifically from the England Summary | Coronavirus (COVID-19) in the UK (data.gov.uk). The data related to electricity production quantity and production types in the UK is acquired from Kaggle. The website for accessing this dataset is Hourly Electricity Consumption and Production | Kaggle.
References
Fumo N, Biswas RM (2015) Regression analysis for prediction of residential energy consumption. Renew Sustain Energy Rev. https://doi.org/10.1016/j.rser.2015.03.035
Zhang Y, Kong W, Dong ZY et al (2019) Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Trans Smart Grid. https://doi.org/10.1109/TSG.2017.2753802
Li C, Chen Z, Liu J et al (2019) Power Load Forecasting Based on the Combined Model of LSTM and XGBoost. In: The 2019 the International Conference. https://doi.org/10.1145/3357777.3357792.
Fan M, Hu Y, Zhang X et al (2019) Short-term Load Forecasting for Distribution Network Using Decomposition with Ensemble prediction. In: 2019 Chinese Automation Congress (CAC).IEEE. https://doi.org/10.1109/CAC48633.2019.8997169
Alhussein M, Aurangzeb K, Haider SI (2020) Hybrid CNN-LSTM model for short-term individual household load forecasting. IEEE Access 8:180544–180557. https://doi.org/10.1109/ACCESS.2020.3028281
Hadri S, Najib M, Bakhouya M, Fakhri Y, Arroussi ME (2021) Performance evaluation of forecasting strategies for electricity consumption in buildings. Energies. https://doi.org/10.3390/en14185831
Ribeiro AMNC, do Carmo PRX, Endo PT, Rosati P, Lynn T (2022) Short- and Very Short-Term Firm-Level Load Forecasting for Warehouses: A Comparison of Machine Learning and Deep Learning Models. Energies 15:750. https://doi.org/10.3390/en15030750
Huang J, Algahtani M, Kaewunruen S (2022) Energy forecasting in a public building: a benchmarking analysis on long short-term memory (LSTM), support vector regression (SVR), and extreme gradient boosting (XGBoost) networks. Appl Sci. https://doi.org/10.3390/app12199788
Jiang P, Fan YV, Kleme JJ (2021) Impacts of COVID-19 on energy demand and consumption: challenges, lessons and emerging opportunities. Appl Energy. https://doi.org/10.1016/j.apenergy.2021.116441
Chen Y, Yang W, Zhang B (2020) Using mobility for electrical load forecasting during the COVID-19 pandemic, arxiv-eess.sp (IF: 3)
Abdulrahman MHA, Abdulrahman A et al (2020) Energy demand in the state of Kuwait during the covid-19 pandemic: technical, economic, and environmental perspectives. Energies. https://doi.org/10.3390/en13174370
Tudose AM, Picioroaga II, Sidea DO, Bulac C, Boicea VA (2021) Short-term load forecasting using convolutional neural networks in COVID-19 context: the romanian case study. Energies. https://doi.org/10.3390/en14134046
Saha B, Ahmed KF, Saha S, Islam MT (2021) Short-term electrical load forecasting via deep learning algorithms to mitigate the impact of covid-19 pandemic on power demand. In: 2021 international conference on automation, control and
Wang Z, Wang H (2021) Improving load forecast in energy markets during COVID-19. arxiv-eess.sp
Payal G, Anil K, Raghav B (2020) Impact of Covid19 on electricity load in Haryana (India). Int J Energy Res. https://doi.org/10.1002/ER.6008
Wang Q, Li S, Jiang F (2021) Uncovering the impact of the COVID-19 pandemic on energy consumption: new insight from difference between pandemic-free scenario and actual electricity consumption in China. J Clean Prod 6:127897
Zarbakhsh N, Misaghian MS, Mcardle G (2022) Human mobility-based features to analyse the impact of COVID-19 on power system operation of Ireland. IEEE Open Access J Power Energy. https://doi.org/10.1109/OAJPE.2022.3155960
Hora C, Dan F, Bendea G, Secui C (2022) Residential short-term load forecasting during atypical consumption behavior. Energies. https://doi.org/10.3390/en15010291
Liu J, Zhang Z, Fan X, Zhang Y, Wang J, Zhou K, Liang S, Yu X, Zhang W (2022) Power system load forecasting using mobility optimization and multi-task learning in COVID-19. Appl Energy. https://doi.org/10.1016/j.apenergy.2021.118303
Ammar A, Esmat Z, Rateb J (2022) The impact of COVID-19 pandemic on electricity consumption and electricity demand forecasting accuracy: empirical evidence from the state of Qatar. Energy Strat Rev. https://doi.org/10.1016/J.ESR.2022.100980
Ku AL et al (2022) Changes in hourly electricity consumption under COVID mandates: a glance to future hourly residential power consumption pattern with remote work in Arizona. Appl Energy 310:118539
Srivastava KR, Greff K,Schmidhuber J (2015) Training very deep networks. CoRR, abs/1507.06228
Muhammad M (2022) LSTM input timestep optimization using simulated annealing for wind power predictions. PLoS ONE 17(10):e0275649–e0275649
Xiuyan P, Biao Z and Yanqing C (2015) The short-term load forecasting of electric power system based on combination forecast model. In: The 27th Chinese Control and Decision Conference (2015 CCDC), Qingdao, China, pp 6509-6512. https://doi.org/10.1109/CCDC.2015.7161993
Acknowledgements
The authors wish to express their sincere thanks to the Beijing University of Technology for its valuable support and assistance to the current work.
Author information
Authors and Affiliations
Contributions
Conceptualization, Y.D.; methodology, Y.D.; validation, Y.D; formal analysis, Y.D.; investigation, Y.D.; resources, Y.D.; data curation, Y.D.; writing—original draft preparation, Y.D.; writing—review and editing, C.Y.; visualization, Y.D.; supervision, C.Y.; project administration, Y.S.; All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dong, Y., Yan, C. & Shao, Y. The electricity demand forecasting in the UK under the impact of the COVID-19 pandemic. Electr Eng (2024). https://doi.org/10.1007/s00202-023-02233-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00202-023-02233-3