Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical Context
Abstract In this paper, we perform a short-run Electricity Price Forecast (EPF) with a Recurrent Neural Network (RNN), namely Long Short-Term Memory (LSTM), using an algorithm that selects the variables and optimizes the hyperparameters. The results are compared with one of the standout machine lear...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-08-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-023-00309-3 |
| _version_ | 1797556520419852288 |
|---|---|
| author | Adela Bâra Simona-Vasilica Oprea Alexandru-Costin Băroiu |
| author_facet | Adela Bâra Simona-Vasilica Oprea Alexandru-Costin Băroiu |
| author_sort | Adela Bâra |
| collection | DOAJ |
| description | Abstract In this paper, we perform a short-run Electricity Price Forecast (EPF) with a Recurrent Neural Network (RNN), namely Long Short-Term Memory (LSTM), using an algorithm that selects the variables and optimizes the hyperparameters. The results are compared with one of the standout machine learning algorithms, namely eXtreme Gradient Boosting (XGB). Apart from other EPF solutions, in this paper, we focus on the interval before and after the pandemic and the conflict in Ukraine. Furthermore, compared to the previous papers that mainly approached German, Austrian, Australian, Spanish, Nordic electricity Day Ahead Markets (DAM), we emphasize on the EPF for one of the East-European countries—Romania whose market rules closely align with the rules of the European Union electricity DAM. The contribution of this study consists in creating a data set that spans from January 2019 to August 2022 and providing an algorithm to identify the best stacked LSTM architecture to cope with a challenging short-term EPF. The proposed algorithm identifies the most relevant variables using a correlation threshold and performs a combination of three parameters—hidden layer size, dropout and learning rate generating the best EPF results. |
| first_indexed | 2024-03-10T17:04:02Z |
| format | Article |
| id | doaj.art-8c11c79e506f43f88e530153f5619ce9 |
| institution | Directory Open Access Journal |
| issn | 1875-6883 |
| language | English |
| last_indexed | 2024-03-10T17:04:02Z |
| publishDate | 2023-08-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj.art-8c11c79e506f43f88e530153f5619ce92023-11-20T10:52:20ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832023-08-0116112210.1007/s44196-023-00309-3Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical ContextAdela Bâra0Simona-Vasilica Oprea1Alexandru-Costin Băroiu2Academy of Romanian ScientistsDepartment of Economic Informatics and Cybernetics, Bucharest University of Economic StudiesAcademy of Romanian ScientistsAbstract In this paper, we perform a short-run Electricity Price Forecast (EPF) with a Recurrent Neural Network (RNN), namely Long Short-Term Memory (LSTM), using an algorithm that selects the variables and optimizes the hyperparameters. The results are compared with one of the standout machine learning algorithms, namely eXtreme Gradient Boosting (XGB). Apart from other EPF solutions, in this paper, we focus on the interval before and after the pandemic and the conflict in Ukraine. Furthermore, compared to the previous papers that mainly approached German, Austrian, Australian, Spanish, Nordic electricity Day Ahead Markets (DAM), we emphasize on the EPF for one of the East-European countries—Romania whose market rules closely align with the rules of the European Union electricity DAM. The contribution of this study consists in creating a data set that spans from January 2019 to August 2022 and providing an algorithm to identify the best stacked LSTM architecture to cope with a challenging short-term EPF. The proposed algorithm identifies the most relevant variables using a correlation threshold and performs a combination of three parameters—hidden layer size, dropout and learning rate generating the best EPF results.https://doi.org/10.1007/s44196-023-00309-3Electricity price forecastDay-ahead marketLong short-term memoryExtreme gradient boosting, hyperparameters, tunning |
| spellingShingle | Adela Bâra Simona-Vasilica Oprea Alexandru-Costin Băroiu Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical Context International Journal of Computational Intelligence Systems Electricity price forecast Day-ahead market Long short-term memory Extreme gradient boosting, hyperparameters, tunning |
| title | Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical Context |
| title_full | Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical Context |
| title_fullStr | Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical Context |
| title_full_unstemmed | Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical Context |
| title_short | Forecasting the Spot Market Electricity Price with a Long Short-Term Memory Model Architecture in a Disruptive Economic and Geopolitical Context |
| title_sort | forecasting the spot market electricity price with a long short term memory model architecture in a disruptive economic and geopolitical context |
| topic | Electricity price forecast Day-ahead market Long short-term memory Extreme gradient boosting, hyperparameters, tunning |
| url | https://doi.org/10.1007/s44196-023-00309-3 |
| work_keys_str_mv | AT adelabara forecastingthespotmarketelectricitypricewithalongshorttermmemorymodelarchitectureinadisruptiveeconomicandgeopoliticalcontext AT simonavasilicaoprea forecastingthespotmarketelectricitypricewithalongshorttermmemorymodelarchitectureinadisruptiveeconomicandgeopoliticalcontext AT alexandrucostinbaroiu forecastingthespotmarketelectricitypricewithalongshorttermmemorymodelarchitectureinadisruptiveeconomicandgeopoliticalcontext |