Forecasting day-ahead spot electricity prices using deep neural networks with attention mechanism
Authors:
- Adam Marszałek,
- Tadeusz Burczyński
Abstract
This paper presents a novel approach to forecast hourly day-ahead electricity prices. In recent years, many predictive models based on statistical methods and machine learning (deep learning) techniques have been proposed. However, the approach presented in this paper focuses on the problem of constructing a fair and unbiased model. In this considered case, unbiased means that the model can increase prediction accuracy and decrease categorical bias across different data clusters. For this purpose, a model combining techniques such as long short-term memory (LSTM) recurrent neural network, attention mechanism, and clustering is created. The proposed model’s main feature is that the attention weights for LSTM hidden states are calculated considering a context vector given for each sample individually as the cluster center to which the sample belongs. In training mode, the samples are iteratively (one time per epoch) clustered based on representation vectors given by the attention mechanism. In the empirical study, the proposed model was applied and evaluated on the Nord Pool market data. To confirm that the model decreases categorical bias, the obtained results were compared with results of similar LSTM models but without the proposed attention mechanism.
- Record ID
- CUT40d17022a14942b29f1552cd6d0c5214
- Publication categories
- ;
- Author
- Journal series
- Journal of Smart Environments and Green Computing, ISSN 2767-6595
- Issue year
- 2021
- Vol
- 1
- No
- 1
- Pages
- 21-31
- Other elements of collation
- schem.; wykr.; Bibliografia (na s.) - 29-31; Bibliografia (liczba pozycji) - 42; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 1, Iss. 1
- Keywords in English
- deep learning, electricity prices forecasting, time series forecasting, attention mechanism, debiasing, Nord Pool data
- DOI
- DOI:10.20517/jsegc.2021.02 Opening in a new tab
- URL
- https://segcjournal.com/journal/volume_issues_archive/2021/1/72 Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 5
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT40d17022a14942b29f1552cd6d0c5214/
- URN
urn:pkr-prod:CUT40d17022a14942b29f1552cd6d0c5214
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.