Decomposition-Residuals Neural Networks: Hybrid System Identification Applied to Electricity Demand Forecasting

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Day-ahead energy forecasting systems struggle to provide accurate demand predictions due to pandemic mitigation measures. Decomposition-Residuals Deep Neural Networks (DR-DNN) are hybrid point-forecasting models that can provide more accurate electricity demand predictions than single models within the COVID-19 era. DR-DNN is a novel two-layer hybrid architecture with: a decomposition and a nonlinear layer. Based on statistical tests, decomposition applies robust signal extraction and filtering of input data into: trend, seasonal and residuals signals. Utilizing calendar information, temporal signals are added: sinusoidal day/night cycles, weekend/weekday, etc. The nonlinear layer learns unknown complex patterns from all those signals, with the usage of well-established deep neural networks. DR-DNN outperformed baselines and state-of-the-art deep neural networks on next-day electricity forecasts within the COVID-19 era (from September 2020 to February 2021), both with fixed and Bayesian optimized hyperparameters. Additionally, model interpretability is improved, by indicating which endogenous or exogenous inputs contribute the most to specific hour-ahead forecasts. Residual signals are very important on the first hour ahead, whereas seasonal patterns on the 24th. Some calendar features also ranked high: whether it is day or night, weekend or weekday and the hour of the day. Temperature was the most important exogenous factor.
Funding Information
  • Other funding ('Kom op tegen Kanker', CM (Christelijke Mutualiteit))
  • Flemish Government Agencies (Baekeland PhD (HBC.20192204), EWI: the Flanders AI Research Program, Innovation mandate (HBC.2019.2209), VLAIO: CSBO (HBC.2021.0076))
  • KU Leuven Research Fund (Project C16/15/059, Project C24/18/022, Project C3/19/053, Project C3/20/117, Project C3I-21-00316)
  • KU Leuven Industrial Research Fund (Fellowship 13-0260, Fellowship IOFm/16/004, Fellowship IOFm/20/002, Several Leuven Research and Development bilateral)
  • European Commission European Research Council under the European Union (European Union?s Horizon 2020 research, ERC Adv. Grant grant agreement No 885682)
  • Flemish Government Agencies FWO (EOS Project no G0F6718N (SeLMA), Infrastructure project I013218N, PhD Grants (SB/1SA1319N, SB/1S93918, SB/1S1319N), SBO project S005319N, TBM Project T001919N)

This publication has 26 references indexed in Scilit: