DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU
In an era of high penetration of renewable energy, accurate photovoltaic (PV) power forecasting is crucial for balancing and scheduling power systems. However, PV power output has uncertainty since it depends on stochastic weather conditions. In this paper, we propose a novel short-term PV forecasti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/1/144 |
| _version_ | 1827617217773043712 |
|---|---|
| author | Keunju Song Jaeik Jeong Jong-Hee Moon Seong-Chul Kwon Hongseok Kim |
| author_facet | Keunju Song Jaeik Jeong Jong-Hee Moon Seong-Chul Kwon Hongseok Kim |
| author_sort | Keunju Song |
| collection | DOAJ |
| description | In an era of high penetration of renewable energy, accurate photovoltaic (PV) power forecasting is crucial for balancing and scheduling power systems. However, PV power output has uncertainty since it depends on stochastic weather conditions. In this paper, we propose a novel short-term PV forecasting technique using Delaunay triangulation, of which the vertices are three weather stations that enclose a target PV site. By leveraging a Transformer encoder and gated recurrent unit (GRU), the proposed TransGRU model is robust against weather forecast error as it learns feature representation from weather data. We construct a framework based on Delaunay triangulation and TransGRU and verify that the proposed framework shows a 7–15% improvement compared to other state-of-the-art methods in terms of the normalized mean absolute error. Moreover, we investigate the effect of PV aggregation for virtual power plants where errors can be compensated across PV sites. Our framework demonstrates 41–60% improvement when PV sites are aggregated and achieves as low as 3–4% of forecasting error on average. |
| first_indexed | 2024-03-09T09:41:44Z |
| format | Article |
| id | doaj.art-766fd3e8be3c40709f537ea05bf729f9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T09:41:44Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-766fd3e8be3c40709f537ea05bf729f92023-12-02T00:53:37ZengMDPI AGSensors1424-82202022-12-0123114410.3390/s23010144DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRUKeunju Song0Jaeik Jeong1Jong-Hee Moon2Seong-Chul Kwon3Hongseok Kim4Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaDepartment of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaSmart Power Distribution Laboratory, KEPCO Research Institute, Daejeon 34056, Republic of KoreaSmart Power Distribution Laboratory, KEPCO Research Institute, Daejeon 34056, Republic of KoreaDepartment of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaIn an era of high penetration of renewable energy, accurate photovoltaic (PV) power forecasting is crucial for balancing and scheduling power systems. However, PV power output has uncertainty since it depends on stochastic weather conditions. In this paper, we propose a novel short-term PV forecasting technique using Delaunay triangulation, of which the vertices are three weather stations that enclose a target PV site. By leveraging a Transformer encoder and gated recurrent unit (GRU), the proposed TransGRU model is robust against weather forecast error as it learns feature representation from weather data. We construct a framework based on Delaunay triangulation and TransGRU and verify that the proposed framework shows a 7–15% improvement compared to other state-of-the-art methods in terms of the normalized mean absolute error. Moreover, we investigate the effect of PV aggregation for virtual power plants where errors can be compensated across PV sites. Our framework demonstrates 41–60% improvement when PV sites are aggregated and achieves as low as 3–4% of forecasting error on average.https://www.mdpi.com/1424-8220/23/1/144Delaunay triangulationinterpretable AITransGRU |
| spellingShingle | Keunju Song Jaeik Jeong Jong-Hee Moon Seong-Chul Kwon Hongseok Kim DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU Sensors Delaunay triangulation interpretable AI TransGRU |
| title | DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU |
| title_full | DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU |
| title_fullStr | DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU |
| title_full_unstemmed | DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU |
| title_short | DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU |
| title_sort | dttrans pv power forecasting using delaunay triangulation and transgru |
| topic | Delaunay triangulation interpretable AI TransGRU |
| url | https://www.mdpi.com/1424-8220/23/1/144 |
| work_keys_str_mv | AT keunjusong dttranspvpowerforecastingusingdelaunaytriangulationandtransgru AT jaeikjeong dttranspvpowerforecastingusingdelaunaytriangulationandtransgru AT jongheemoon dttranspvpowerforecastingusingdelaunaytriangulationandtransgru AT seongchulkwon dttranspvpowerforecastingusingdelaunaytriangulationandtransgru AT hongseokkim dttranspvpowerforecastingusingdelaunaytriangulationandtransgru |