Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN)
The future power grid will have more distributed energy sources, and the widespread access of distributed energy sources has the potential to improve the energy efficiency, resilience, and sustainability of the system. However, distributed energy, mainly wind power generation and photovoltaic power...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/11/4436 |
| _version_ | 1797597525081849856 |
|---|---|
| author | Jizhong Xue Zaohui Kang Chun Sing Lai Yu Wang Fangyuan Xu Haoliang Yuan |
| author_facet | Jizhong Xue Zaohui Kang Chun Sing Lai Yu Wang Fangyuan Xu Haoliang Yuan |
| author_sort | Jizhong Xue |
| collection | DOAJ |
| description | The future power grid will have more distributed energy sources, and the widespread access of distributed energy sources has the potential to improve the energy efficiency, resilience, and sustainability of the system. However, distributed energy, mainly wind power generation and photovoltaic power generation, has the characteristics of intermittency and strong randomness, which will bring challenges to the safe operation of the power grid. Accurate prediction of solar power generation with high spatial and temporal resolution is very important for the normal operation of the power grid. In order to improve the accuracy of distributed photovoltaic power generation prediction, this paper proposes a new distributed photovoltaic power generation prediction model: ROLL-GNN, which is defined as a prediction model based on rolling prediction of the graph neural network. The ROLL-GNN uses the perspective of graph signal processing to model distributed generation production timeseries data as signals on graphs. In the model, the similarity of data is used to capture their spatio-temporal dependencies to achieve improved prediction accuracy. |
| first_indexed | 2024-03-11T03:07:17Z |
| format | Article |
| id | doaj.art-1381141b478e46ebbf3325b2b6e5face |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T03:07:17Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-1381141b478e46ebbf3325b2b6e5face2023-11-18T07:48:50ZengMDPI AGEnergies1996-10732023-05-011611443610.3390/en16114436Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN)Jizhong Xue0Zaohui Kang1Chun Sing Lai2Yu Wang3Fangyuan Xu4Haoliang Yuan5Department of Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaDepartment of Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaThe future power grid will have more distributed energy sources, and the widespread access of distributed energy sources has the potential to improve the energy efficiency, resilience, and sustainability of the system. However, distributed energy, mainly wind power generation and photovoltaic power generation, has the characteristics of intermittency and strong randomness, which will bring challenges to the safe operation of the power grid. Accurate prediction of solar power generation with high spatial and temporal resolution is very important for the normal operation of the power grid. In order to improve the accuracy of distributed photovoltaic power generation prediction, this paper proposes a new distributed photovoltaic power generation prediction model: ROLL-GNN, which is defined as a prediction model based on rolling prediction of the graph neural network. The ROLL-GNN uses the perspective of graph signal processing to model distributed generation production timeseries data as signals on graphs. In the model, the similarity of data is used to capture their spatio-temporal dependencies to achieve improved prediction accuracy.https://www.mdpi.com/1996-1073/16/11/4436distributed generationPV forecastinggraph neural networks |
| spellingShingle | Jizhong Xue Zaohui Kang Chun Sing Lai Yu Wang Fangyuan Xu Haoliang Yuan Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN) Energies distributed generation PV forecasting graph neural networks |
| title | Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN) |
| title_full | Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN) |
| title_fullStr | Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN) |
| title_full_unstemmed | Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN) |
| title_short | Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN) |
| title_sort | distributed generation forecasting based on rolling graph neural network roll gnn |
| topic | distributed generation PV forecasting graph neural networks |
| url | https://www.mdpi.com/1996-1073/16/11/4436 |
| work_keys_str_mv | AT jizhongxue distributedgenerationforecastingbasedonrollinggraphneuralnetworkrollgnn AT zaohuikang distributedgenerationforecastingbasedonrollinggraphneuralnetworkrollgnn AT chunsinglai distributedgenerationforecastingbasedonrollinggraphneuralnetworkrollgnn AT yuwang distributedgenerationforecastingbasedonrollinggraphneuralnetworkrollgnn AT fangyuanxu distributedgenerationforecastingbasedonrollinggraphneuralnetworkrollgnn AT haoliangyuan distributedgenerationforecastingbasedonrollinggraphneuralnetworkrollgnn |