Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection
This paper proposes a method for forecasting surface solar irradiance (SSI), the most critical factor in solar photovoltaic (PV) power generation. The proposed method uses 16-channel data obtained by the GEO-KOMPSAT-2A (GK2A) satellite of South Korea as the main data for SSI forecasting. To determin...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/5/888 |
| _version_ | 1827319398565675008 |
|---|---|
| author | Jinyong Kim Eunkyeong Kim Seunghwan Jung Minseok Kim Baekcheon Kim Sungshin Kim |
| author_facet | Jinyong Kim Eunkyeong Kim Seunghwan Jung Minseok Kim Baekcheon Kim Sungshin Kim |
| author_sort | Jinyong Kim |
| collection | DOAJ |
| description | This paper proposes a method for forecasting surface solar irradiance (SSI), the most critical factor in solar photovoltaic (PV) power generation. The proposed method uses 16-channel data obtained by the GEO-KOMPSAT-2A (GK2A) satellite of South Korea as the main data for SSI forecasting. To determine feature variables related to SSI from the 16-channel data, the differences and ratios between the channels were utilized. Additionally, to consider the fundamental characteristics of SSI originating from the sun, solar geometry parameters, such as solar declination (SD), solar elevation angle (SEA), and extraterrestrial solar radiation (ESR), were used. Deep learning-based feature selection (Deep-FS) was employed to select appropriate feature variables that affect SSI from various feature variables extracted from the 16-channel data. Lastly, spatio-temporal deep learning models, such as convolutional neural network–long short-term memory (CNN-LSTM) and CNN–gated recurrent unit (CNN-GRU), which can simultaneously reflect temporal and spatial characteristics, were used to forecast SSI. Experiments conducted to verify the proposed method against conventional methods confirmed that the proposed method delivers superior SSI forecasting performance. |
| first_indexed | 2024-04-25T00:20:06Z |
| format | Article |
| id | doaj.art-7239b0dea60e4be9b81259de917ea4b3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-25T00:20:06Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7239b0dea60e4be9b81259de917ea4b32024-03-12T16:54:21ZengMDPI AGRemote Sensing2072-42922024-03-0116588810.3390/rs16050888Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature SelectionJinyong Kim0Eunkyeong Kim1Seunghwan Jung2Minseok Kim3Baekcheon Kim4Sungshin Kim5Department of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaThis paper proposes a method for forecasting surface solar irradiance (SSI), the most critical factor in solar photovoltaic (PV) power generation. The proposed method uses 16-channel data obtained by the GEO-KOMPSAT-2A (GK2A) satellite of South Korea as the main data for SSI forecasting. To determine feature variables related to SSI from the 16-channel data, the differences and ratios between the channels were utilized. Additionally, to consider the fundamental characteristics of SSI originating from the sun, solar geometry parameters, such as solar declination (SD), solar elevation angle (SEA), and extraterrestrial solar radiation (ESR), were used. Deep learning-based feature selection (Deep-FS) was employed to select appropriate feature variables that affect SSI from various feature variables extracted from the 16-channel data. Lastly, spatio-temporal deep learning models, such as convolutional neural network–long short-term memory (CNN-LSTM) and CNN–gated recurrent unit (CNN-GRU), which can simultaneously reflect temporal and spatial characteristics, were used to forecast SSI. Experiments conducted to verify the proposed method against conventional methods confirmed that the proposed method delivers superior SSI forecasting performance.https://www.mdpi.com/2072-4292/16/5/888solar irradiance forecastingdeep learning-based feature selectionspatio-temporal deep learning modelsolar geometryGK2A satellite data |
| spellingShingle | Jinyong Kim Eunkyeong Kim Seunghwan Jung Minseok Kim Baekcheon Kim Sungshin Kim Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection Remote Sensing solar irradiance forecasting deep learning-based feature selection spatio-temporal deep learning model solar geometry GK2A satellite data |
| title | Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection |
| title_full | Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection |
| title_fullStr | Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection |
| title_full_unstemmed | Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection |
| title_short | Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection |
| title_sort | spatio temporal deep learning based forecasting of surface solar irradiance leveraging satellite data and feature selection |
| topic | solar irradiance forecasting deep learning-based feature selection spatio-temporal deep learning model solar geometry GK2A satellite data |
| url | https://www.mdpi.com/2072-4292/16/5/888 |
| work_keys_str_mv | AT jinyongkim spatiotemporaldeeplearningbasedforecastingofsurfacesolarirradianceleveragingsatellitedataandfeatureselection AT eunkyeongkim spatiotemporaldeeplearningbasedforecastingofsurfacesolarirradianceleveragingsatellitedataandfeatureselection AT seunghwanjung spatiotemporaldeeplearningbasedforecastingofsurfacesolarirradianceleveragingsatellitedataandfeatureselection AT minseokkim spatiotemporaldeeplearningbasedforecastingofsurfacesolarirradianceleveragingsatellitedataandfeatureselection AT baekcheonkim spatiotemporaldeeplearningbasedforecastingofsurfacesolarirradianceleveragingsatellitedataandfeatureselection AT sungshinkim spatiotemporaldeeplearningbasedforecastingofsurfacesolarirradianceleveragingsatellitedataandfeatureselection |