A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature Selection
High precision short-term photovoltaic (PV) power prediction can reduce the damage associated with large-scale photovoltaic grid-connection to the power system. In this paper, a combination deep learning forecasting method based on variational mode decomposition (VMD), a fast correlation-based filte...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/15/5410 |
| _version_ | 1827602929320722432 |
|---|---|
| author | Kaitong Wu Xiangang Peng Zilu Li Wenbo Cui Haoliang Yuan Chun Sing Lai Loi Lei Lai |
| author_facet | Kaitong Wu Xiangang Peng Zilu Li Wenbo Cui Haoliang Yuan Chun Sing Lai Loi Lei Lai |
| author_sort | Kaitong Wu |
| collection | DOAJ |
| description | High precision short-term photovoltaic (PV) power prediction can reduce the damage associated with large-scale photovoltaic grid-connection to the power system. In this paper, a combination deep learning forecasting method based on variational mode decomposition (VMD), a fast correlation-based filter (FCBF) and bidirectional long short-term memory (BiLSTM) network is developed to minimize PV power forecasting error. In this model, VMD is used to extract the trend feature of PV power, then FCBF is adopted to select the optimal input-set to reduce the forecasting error caused by the redundant feature. Finally, the input-set is put into the BiLSTM network for training and testing. The performance of this model is tested by a case study using the public data-set provided by a PV station in Australia. Comparisons with common short-term PV power forecasting models are also presented. The results show that under the processing of trend feature extraction and feature selection, the proposed methodology provides a more stable and accurate forecasting effect than other forecasting models. |
| first_indexed | 2024-03-09T05:28:31Z |
| format | Article |
| id | doaj.art-9c7b447c82444136ba115e9a9d9560b6 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T05:28:31Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-9c7b447c82444136ba115e9a9d9560b62023-12-03T12:34:54ZengMDPI AGEnergies1996-10732022-07-011515541010.3390/en15155410A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature SelectionKaitong Wu0Xiangang Peng1Zilu Li2Wenbo Cui3Haoliang Yuan4Chun Sing Lai5Loi Lei Lai6Department of Electrical Engineering, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaHigh precision short-term photovoltaic (PV) power prediction can reduce the damage associated with large-scale photovoltaic grid-connection to the power system. In this paper, a combination deep learning forecasting method based on variational mode decomposition (VMD), a fast correlation-based filter (FCBF) and bidirectional long short-term memory (BiLSTM) network is developed to minimize PV power forecasting error. In this model, VMD is used to extract the trend feature of PV power, then FCBF is adopted to select the optimal input-set to reduce the forecasting error caused by the redundant feature. Finally, the input-set is put into the BiLSTM network for training and testing. The performance of this model is tested by a case study using the public data-set provided by a PV station in Australia. Comparisons with common short-term PV power forecasting models are also presented. The results show that under the processing of trend feature extraction and feature selection, the proposed methodology provides a more stable and accurate forecasting effect than other forecasting models.https://www.mdpi.com/1996-1073/15/15/5410short-term PV power forecastingtrend feature extractionfast correlation-based filterbidirectional long short-term memory network |
| spellingShingle | Kaitong Wu Xiangang Peng Zilu Li Wenbo Cui Haoliang Yuan Chun Sing Lai Loi Lei Lai A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature Selection Energies short-term PV power forecasting trend feature extraction fast correlation-based filter bidirectional long short-term memory network |
| title | A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature Selection |
| title_full | A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature Selection |
| title_fullStr | A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature Selection |
| title_full_unstemmed | A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature Selection |
| title_short | A Short-Term Photovoltaic Power Forecasting Method Combining a Deep Learning Model with Trend Feature Extraction and Feature Selection |
| title_sort | short term photovoltaic power forecasting method combining a deep learning model with trend feature extraction and feature selection |
| topic | short-term PV power forecasting trend feature extraction fast correlation-based filter bidirectional long short-term memory network |
| url | https://www.mdpi.com/1996-1073/15/15/5410 |
| work_keys_str_mv | AT kaitongwu ashorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT xiangangpeng ashorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT ziluli ashorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT wenbocui ashorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT haoliangyuan ashorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT chunsinglai ashorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT loileilai ashorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT kaitongwu shorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT xiangangpeng shorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT ziluli shorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT wenbocui shorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT haoliangyuan shorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT chunsinglai shorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection AT loileilai shorttermphotovoltaicpowerforecastingmethodcombiningadeeplearningmodelwithtrendfeatureextractionandfeatureselection |