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

Nicolai Bo Vanting*, Zheng Grace Ma, Bo Nørregaard Jørgensen

*Kontaktforfatter

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

76 Downloads (Pure)

Abstract

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 R 2 score and 4–5% absolute percentage error for the 1-h predictions. Forecasting 24 h gave an adjusted R 2 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.

OriginalsprogEngelsk
Artikelnummer63
TidsskriftEnergy Informatics
Vol/bind5
Udgave nummerSuppl. 4
Antal sider23
ISSN2520-8942
DOI
StatusUdgivet - 21. dec. 2022
BegivenhedEnergy Informatics.Academy Conference 2022 - Dandy Business Park, Vejle, Danmark
Varighed: 24. aug. 202225. aug. 2022
https://www.energyinformatics.academy/eia-2022-conference

Konference

KonferenceEnergy Informatics.Academy Conference 2022
LokationDandy Business Park
Land/OmrådeDanmark
ByVejle
Periode24/08/202225/08/2022
Internetadresse

Emneord

  • Short-Term Load Forecasting
  • Residential Electricity Consumption
  • Artificial Neural Network
  • Recurrent Neural Network
  • Feature Identification
  • Feature Selection
  • Ecosystem

Fingeraftryk

Dyk ned i forskningsemnerne om 'Evaluation of Neural Networks for Residential Load Forecasting and the Impact of Systematic Feature Identification'. Sammen danner de et unikt fingeraftryk.

Citationsformater