Solar Irradiance Forecasting with Transformer Model
Solar energy is one of the most popular sources of renewable energy today. It is therefore essential to be able to predict solar power generation and adapt energy needs to these predictions. This paper uses the Transformer deep neural network model, in which the attention mechanism is typically appl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/17/8852 |
| _version_ | 1827666982238945280 |
|---|---|
| author | Jiří Pospíchal Martin Kubovčík Iveta Dirgová Luptáková |
| author_facet | Jiří Pospíchal Martin Kubovčík Iveta Dirgová Luptáková |
| author_sort | Jiří Pospíchal |
| collection | DOAJ |
| description | Solar energy is one of the most popular sources of renewable energy today. It is therefore essential to be able to predict solar power generation and adapt energy needs to these predictions. This paper uses the Transformer deep neural network model, in which the attention mechanism is typically applied in NLP or vision problems. Here, it is extended by combining features based on their spatiotemporal properties in solar irradiance prediction. The results were predicted for arbitrary long-time horizons since the prediction is always 1 day ahead, which can be included at the end along the timestep axis of the input data and the first timestep representing the oldest timestep removed. A maximum worst-case mean absolute percentage error of 3.45% for the one-day-ahead prediction was obtained, which gave better results than the directly competing methods. |
| first_indexed | 2024-03-10T03:00:16Z |
| format | Article |
| id | doaj.art-e300e82a548647fd8f66bd28f7b6b0de |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:00:16Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e300e82a548647fd8f66bd28f7b6b0de2023-11-23T12:48:00ZengMDPI AGApplied Sciences2076-34172022-09-011217885210.3390/app12178852Solar Irradiance Forecasting with Transformer ModelJiří Pospíchal0Martin Kubovčík1Iveta Dirgová Luptáková2Department of Applied Informatics, Faculty of Natural Sciences, University of Ss. Cyril and Methodius, J. Herdu 2, 917 01 Trnava, SlovakiaDepartment of Applied Informatics, Faculty of Natural Sciences, University of Ss. Cyril and Methodius, J. Herdu 2, 917 01 Trnava, SlovakiaDepartment of Applied Informatics, Faculty of Natural Sciences, University of Ss. Cyril and Methodius, J. Herdu 2, 917 01 Trnava, SlovakiaSolar energy is one of the most popular sources of renewable energy today. It is therefore essential to be able to predict solar power generation and adapt energy needs to these predictions. This paper uses the Transformer deep neural network model, in which the attention mechanism is typically applied in NLP or vision problems. Here, it is extended by combining features based on their spatiotemporal properties in solar irradiance prediction. The results were predicted for arbitrary long-time horizons since the prediction is always 1 day ahead, which can be included at the end along the timestep axis of the input data and the first timestep representing the oldest timestep removed. A maximum worst-case mean absolute percentage error of 3.45% for the one-day-ahead prediction was obtained, which gave better results than the directly competing methods.https://www.mdpi.com/2076-3417/12/17/8852transformersolar irradianceweatherrenewable energysequence-to-sequence predictioncorrelations |
| spellingShingle | Jiří Pospíchal Martin Kubovčík Iveta Dirgová Luptáková Solar Irradiance Forecasting with Transformer Model Applied Sciences transformer solar irradiance weather renewable energy sequence-to-sequence prediction correlations |
| title | Solar Irradiance Forecasting with Transformer Model |
| title_full | Solar Irradiance Forecasting with Transformer Model |
| title_fullStr | Solar Irradiance Forecasting with Transformer Model |
| title_full_unstemmed | Solar Irradiance Forecasting with Transformer Model |
| title_short | Solar Irradiance Forecasting with Transformer Model |
| title_sort | solar irradiance forecasting with transformer model |
| topic | transformer solar irradiance weather renewable energy sequence-to-sequence prediction correlations |
| url | https://www.mdpi.com/2076-3417/12/17/8852 |
| work_keys_str_mv | AT jiripospichal solarirradianceforecastingwithtransformermodel AT martinkubovcik solarirradianceforecastingwithtransformermodel AT ivetadirgovaluptakova solarirradianceforecastingwithtransformermodel |