Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer Model
Deep learning techniques excel at capturing and understanding the symmetry inherent in data patterns and non-linear properties of photovoltaic (PV) power, therefore they achieve excellent performance on short-term PV power forecasting. In order to produce more precise and detailed forecasting result...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/15/1/238 |
| _version_ | 1797436782225129472 |
|---|---|
| author | Yuanshao Huang Yonghong Wu |
| author_facet | Yuanshao Huang Yonghong Wu |
| author_sort | Yuanshao Huang |
| collection | DOAJ |
| description | Deep learning techniques excel at capturing and understanding the symmetry inherent in data patterns and non-linear properties of photovoltaic (PV) power, therefore they achieve excellent performance on short-term PV power forecasting. In order to produce more precise and detailed forecasting results, this research suggests a novel Autoformer model with De-Stationary Attention and Multi-Scale framework (ADAMS) for short-term PV power forecasting. In this approach, the multi-scale framework is applied to the Autoformer model to capture the inter-dependencies and specificities of each scale. Furthermore, the de-stationary attention is incorporated into an auto-correlation mechanism for more efficient non-stationary information extraction. Based on the operational data from a 1058.4 kW PV facility in Central Australia, the ADAMS model and the other six baseline models are compared with 5 min and 1 h temporal resolution PV power data predictions. The results show in terms of four performance measurements, the proposed method can handle the task of projecting short-term PV output more effectively than other methods. Taking the result of predicting the PV energy in the next 24 h based on the 1 h resolution data as an example, MSE is 0.280, MAE is 0.302, RMSE is 0.529, and adjusted R-squared is 0.824. |
| first_indexed | 2024-03-09T11:07:34Z |
| format | Article |
| id | doaj.art-d97e836ae5ba4edf9cebb8fbcc68f05a |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T11:07:34Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-d97e836ae5ba4edf9cebb8fbcc68f05a2023-12-01T00:53:56ZengMDPI AGSymmetry2073-89942023-01-0115123810.3390/sym15010238Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer ModelYuanshao Huang0Yonghong Wu1Department of Statistics, College of Science, Wuhan University of Technology, Wuhan 430070, ChinaDepartment of Statistics, College of Science, Wuhan University of Technology, Wuhan 430070, ChinaDeep learning techniques excel at capturing and understanding the symmetry inherent in data patterns and non-linear properties of photovoltaic (PV) power, therefore they achieve excellent performance on short-term PV power forecasting. In order to produce more precise and detailed forecasting results, this research suggests a novel Autoformer model with De-Stationary Attention and Multi-Scale framework (ADAMS) for short-term PV power forecasting. In this approach, the multi-scale framework is applied to the Autoformer model to capture the inter-dependencies and specificities of each scale. Furthermore, the de-stationary attention is incorporated into an auto-correlation mechanism for more efficient non-stationary information extraction. Based on the operational data from a 1058.4 kW PV facility in Central Australia, the ADAMS model and the other six baseline models are compared with 5 min and 1 h temporal resolution PV power data predictions. The results show in terms of four performance measurements, the proposed method can handle the task of projecting short-term PV output more effectively than other methods. Taking the result of predicting the PV energy in the next 24 h based on the 1 h resolution data as an example, MSE is 0.280, MAE is 0.302, RMSE is 0.529, and adjusted R-squared is 0.824.https://www.mdpi.com/2073-8994/15/1/238photovoltaic powerdeep learningshort-term forecastingtransformer modelnonstationaritymulti-scale analysis |
| spellingShingle | Yuanshao Huang Yonghong Wu Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer Model Symmetry photovoltaic power deep learning short-term forecasting transformer model nonstationarity multi-scale analysis |
| title | Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer Model |
| title_full | Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer Model |
| title_fullStr | Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer Model |
| title_full_unstemmed | Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer Model |
| title_short | Short-Term Photovoltaic Power Forecasting Based on a Novel Autoformer Model |
| title_sort | short term photovoltaic power forecasting based on a novel autoformer model |
| topic | photovoltaic power deep learning short-term forecasting transformer model nonstationarity multi-scale analysis |
| url | https://www.mdpi.com/2073-8994/15/1/238 |
| work_keys_str_mv | AT yuanshaohuang shorttermphotovoltaicpowerforecastingbasedonanovelautoformermodel AT yonghongwu shorttermphotovoltaicpowerforecastingbasedonanovelautoformermodel |