A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network
Abstract Recent years, the tremendous number of distributed photovoltaic are integrated into low‐voltage distribution network, generating a significant amount of operational data. The centralized cloud data centre is unable to process the massive data precisely and promptly. Therefore, the operation...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | IET Renewable Power Generation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rpg2.13093 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832579813262491648 |
|---|---|
| author | Yuanliang Fan Han Wu Jianli Lin Zewen Li Lingfei Li Xinghua Huang Weiming Chen Jian Zhao |
| author_facet | Yuanliang Fan Han Wu Jianli Lin Zewen Li Lingfei Li Xinghua Huang Weiming Chen Jian Zhao |
| author_sort | Yuanliang Fan |
| collection | DOAJ |
| description | Abstract Recent years, the tremendous number of distributed photovoltaic are integrated into low‐voltage distribution network, generating a significant amount of operational data. The centralized cloud data centre is unable to process the massive data precisely and promptly. Therefore, the operational status of distributed photovoltaic systems in low‐voltage distribution network becomes difficult to predict. However, edge computing in the distribution network enable local processing of data to improve the real‐time and reliability of the forecasting service. In this regard, this paper proposes a distributed photovoltaic short‐term power forecasting model based on lightweight AI algorithms. Firstly, based on the Pearson correlation coefficient method, an analysis is conducted on the historical operational data in the network to extract important meteorological features that are correlated with the photovoltaic power output. Secondly, a distributed photovoltaic power forecasting model for the distribution network is constructed based on the Xception and attention mechanism. Finally, the model is trained using pruning, which involves removing redundant parts of the model, resulting in a compact and efficient forecasting model. By conducting validation on real‐world datasets, the results demonstrate that the model presented in this article possesses a smaller size and higher forecasting accuracy compared to other state‐of‐the‐art forecasting models. |
| format | Article |
| id | doaj-art-69a0e77150a84455877bc1b3433a377e |
| institution | Kabale University |
| issn | 1752-1416 1752-1424 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Renewable Power Generation |
| spelling | doaj-art-69a0e77150a84455877bc1b3433a377e2025-01-30T12:15:54ZengWileyIET Renewable Power Generation1752-14161752-14242024-12-0118163955396610.1049/rpg2.13093A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution networkYuanliang Fan0Han Wu1Jianli Lin2Zewen Li3Lingfei Li4Xinghua Huang5Weiming Chen6Jian Zhao7Distribution Technology Research Center Electric Power Research Institute of Fujian Electric Power Co., Ltd Fuzhou ChinaDistribution Technology Research Center Electric Power Research Institute of Fujian Electric Power Co., Ltd Fuzhou ChinaDistribution Technology Research Center Electric Power Research Institute of Fujian Electric Power Co., Ltd Fuzhou ChinaDistribution Technology Research Center Electric Power Research Institute of Fujian Electric Power Co., Ltd Fuzhou ChinaDistribution Technology Research Center Electric Power Research Institute of Fujian Electric Power Co., Ltd Fuzhou ChinaDistribution Technology Research Center Electric Power Research Institute of Fujian Electric Power Co., Ltd Fuzhou ChinaDistribution Technology Research Center Electric Power Research Institute of Fujian Electric Power Co., Ltd Fuzhou ChinaThe College of Electrical Engineering Shanghai University of Electric Power Shanghai ChinaAbstract Recent years, the tremendous number of distributed photovoltaic are integrated into low‐voltage distribution network, generating a significant amount of operational data. The centralized cloud data centre is unable to process the massive data precisely and promptly. Therefore, the operational status of distributed photovoltaic systems in low‐voltage distribution network becomes difficult to predict. However, edge computing in the distribution network enable local processing of data to improve the real‐time and reliability of the forecasting service. In this regard, this paper proposes a distributed photovoltaic short‐term power forecasting model based on lightweight AI algorithms. Firstly, based on the Pearson correlation coefficient method, an analysis is conducted on the historical operational data in the network to extract important meteorological features that are correlated with the photovoltaic power output. Secondly, a distributed photovoltaic power forecasting model for the distribution network is constructed based on the Xception and attention mechanism. Finally, the model is trained using pruning, which involves removing redundant parts of the model, resulting in a compact and efficient forecasting model. By conducting validation on real‐world datasets, the results demonstrate that the model presented in this article possesses a smaller size and higher forecasting accuracy compared to other state‐of‐the‐art forecasting models.https://doi.org/10.1049/rpg2.13093artificial intelligencedistributed controldistribution networks |
| spellingShingle | Yuanliang Fan Han Wu Jianli Lin Zewen Li Lingfei Li Xinghua Huang Weiming Chen Jian Zhao A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network IET Renewable Power Generation artificial intelligence distributed control distribution networks |
| title | A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network |
| title_full | A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network |
| title_fullStr | A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network |
| title_full_unstemmed | A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network |
| title_short | A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network |
| title_sort | distributed photovoltaic short term power forecasting model based on lightweight ai for edge computing in low voltage distribution network |
| topic | artificial intelligence distributed control distribution networks |
| url | https://doi.org/10.1049/rpg2.13093 |
| work_keys_str_mv | AT yuanliangfan adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT hanwu adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT jianlilin adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT zewenli adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT lingfeili adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT xinghuahuang adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT weimingchen adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT jianzhao adistributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT yuanliangfan distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT hanwu distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT jianlilin distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT zewenli distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT lingfeili distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT xinghuahuang distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT weimingchen distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork AT jianzhao distributedphotovoltaicshorttermpowerforecastingmodelbasedonlightweightaiforedgecomputinginlowvoltagedistributionnetwork |