How to model European electricity load profiles using artificial neural networks. (1st November 2020)

• Record Type: Journal Article
• Authors: Behm, Christian; Nolting, Lars; Praktiknjo, Aaron
• Is Part Of: Applied energy. Volume 277(2020)
• Publication Date: 2020-11-01
• Subjects: Artificial Intelligence -- Artificial neural networks -- Energy system modeling -- Electricity load -- Security of electricity supply -- Machine learning; ANN Artificial neural network -- AR Autoregressive -- ARIMA Autoregressive integrated moving average -- ARMA Autoregressive moving average -- entso-e European Network of Transmission System Operators for Electricity -- EV Electric vehicle -- LR Learning rate -- LTLF Long-term load forecast -- MA Moving average -- MAF Mid-term Adequacy Forecast (as published by entso-e) -- MAPE Mean absolute percentage error -- MSE Mean square error -- MTLF Medium-term load forecast -- max Maximum -- min Minimum -- nom Nominal -- R2 Coefficient of determination -- RMSE Root-mean-square error -- SMAPE Symmetric mean absolute percentage error -- STLF Short-term load forecast -- VSTLF Very short-term load forecast; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2020.115564
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: Calculating synthetic weather-dependent electricity load profiles in hourly resolution. Introduction of novel approach using artificial neural networks. Application to Germany, France, Spain and Sweden (ex-post analysis) Substantial accuracy gains compared to entso-e approach based on linear regression. Potential to increase accuracy of future load forecasts. Abstract: We present a method to create synthetic, weather-dependent, annual electricity load profiles for European countries in hourly resolution using artificial neural networks as a necessary basis for long-term forecasts. To this end, we train fully connected dense artificial neural networks with 5 hidden layers and 1, 024 hidden nodes per layer using historic data for Germany from 2006 to 2015. Input parameters used in the model comprise calendrical information, annual peak loads and weather data. We benchmark our results against the current state-of-the-art method to generate synthetic load profiles used in mid-term adequacy forecasts published by the European Network of Transmission System Operators (entso-e). For validation year 2016, our approach shows a mean absolute percentage error of 2.8%, whereas the method as used by entso-e shows an average error of 4.8%. We then conduct forecasts for Germany, Sweden, Spain, and France using our synthetic load profiles for scenario year 2025 to demonstrate their pan-European applicability. Finally, we assess parameter variations that demonstrate high influences of outdoor temperatures and wind speed on the electricity load. Our approach can help to increase prediction accuracy of future electricity loads as electricity load profiles are a necessary input for these forecasts.