Novel solar forecasting scheme modelled by mixer dual path network and based on sky images
The prediction of global horizontal irradiance has become an effective technique to address the intermittence issue of photovoltaic (PV) power generation. This article proposes a novel deep neural network(DNN), named Mixer Dual Path Network (Mixer-DPN), for promising solar forecasting. It shares com...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | e-Prime: Advances in Electrical Engineering, Electronics and Energy |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772671123002103 |
| _version_ | 1797388628703313920 |
|---|---|
| author | Tongsen Zhu Xuan Jiao Xingshuo Li Xuening Yin Yang Du Shuye Ding Weidong Xiao |
| author_facet | Tongsen Zhu Xuan Jiao Xingshuo Li Xuening Yin Yang Du Shuye Ding Weidong Xiao |
| author_sort | Tongsen Zhu |
| collection | DOAJ |
| description | The prediction of global horizontal irradiance has become an effective technique to address the intermittence issue of photovoltaic (PV) power generation. This article proposes a novel deep neural network(DNN), named Mixer Dual Path Network (Mixer-DPN), for promising solar forecasting. It shares common features of cloud images and maintains the flexibility to explore new features through dual-path architecture by combining the Mixer layer and Dual Path Network. Therefore, the proposed model can provide more accurate prediction results compared to the classical DNN-based predictors. Moreover, the proposed model shows a faster convergence speed and smaller model size, which makes it suitable for a practical global horizontal irradiance. The merits of the proposed model are verified by testing it with the data from National Renewable Energy Laboratory comparing it with other DNN-based prediction models. Studies have shown that the new model has achieved excellent results in MSE, MAE and other indicators, and the R2 prediction accuracy rate has increased by 14% compared with the baseline model. |
| first_indexed | 2024-03-08T22:43:32Z |
| format | Article |
| id | doaj.art-afb2db9fe2434bedbcb55ba8b07c816a |
| institution | Directory Open Access Journal |
| issn | 2772-6711 |
| language | English |
| last_indexed | 2024-03-08T22:43:32Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | e-Prime: Advances in Electrical Engineering, Electronics and Energy |
| spelling | doaj.art-afb2db9fe2434bedbcb55ba8b07c816a2023-12-17T06:43:22ZengElseviere-Prime: Advances in Electrical Engineering, Electronics and Energy2772-67112023-12-016100315Novel solar forecasting scheme modelled by mixer dual path network and based on sky imagesTongsen Zhu0Xuan Jiao1Xingshuo Li2Xuening Yin3Yang Du4Shuye Ding5Weidong Xiao6Nanjing Normal University, Nanjing, ChinaThe University of Sydney, Sydney, AustraliaCorresponding author.; Nanjing Normal University, Nanjing, ChinaNanjing Normal University, Nanjing, ChinaJames Cook University, Cairns, AustraliaNanjing Normal University, Nanjing, ChinaThe University of Sydney, Sydney, AustraliaThe prediction of global horizontal irradiance has become an effective technique to address the intermittence issue of photovoltaic (PV) power generation. This article proposes a novel deep neural network(DNN), named Mixer Dual Path Network (Mixer-DPN), for promising solar forecasting. It shares common features of cloud images and maintains the flexibility to explore new features through dual-path architecture by combining the Mixer layer and Dual Path Network. Therefore, the proposed model can provide more accurate prediction results compared to the classical DNN-based predictors. Moreover, the proposed model shows a faster convergence speed and smaller model size, which makes it suitable for a practical global horizontal irradiance. The merits of the proposed model are verified by testing it with the data from National Renewable Energy Laboratory comparing it with other DNN-based prediction models. Studies have shown that the new model has achieved excellent results in MSE, MAE and other indicators, and the R2 prediction accuracy rate has increased by 14% compared with the baseline model.http://www.sciencedirect.com/science/article/pii/S2772671123002103Deep learning (DL)Solar forecastingDual path network (DPN)Convmixer architecture |
| spellingShingle | Tongsen Zhu Xuan Jiao Xingshuo Li Xuening Yin Yang Du Shuye Ding Weidong Xiao Novel solar forecasting scheme modelled by mixer dual path network and based on sky images e-Prime: Advances in Electrical Engineering, Electronics and Energy Deep learning (DL) Solar forecasting Dual path network (DPN) Convmixer architecture |
| title | Novel solar forecasting scheme modelled by mixer dual path network and based on sky images |
| title_full | Novel solar forecasting scheme modelled by mixer dual path network and based on sky images |
| title_fullStr | Novel solar forecasting scheme modelled by mixer dual path network and based on sky images |
| title_full_unstemmed | Novel solar forecasting scheme modelled by mixer dual path network and based on sky images |
| title_short | Novel solar forecasting scheme modelled by mixer dual path network and based on sky images |
| title_sort | novel solar forecasting scheme modelled by mixer dual path network and based on sky images |
| topic | Deep learning (DL) Solar forecasting Dual path network (DPN) Convmixer architecture |
| url | http://www.sciencedirect.com/science/article/pii/S2772671123002103 |
| work_keys_str_mv | AT tongsenzhu novelsolarforecastingschememodelledbymixerdualpathnetworkandbasedonskyimages AT xuanjiao novelsolarforecastingschememodelledbymixerdualpathnetworkandbasedonskyimages AT xingshuoli novelsolarforecastingschememodelledbymixerdualpathnetworkandbasedonskyimages AT xueningyin novelsolarforecastingschememodelledbymixerdualpathnetworkandbasedonskyimages AT yangdu novelsolarforecastingschememodelledbymixerdualpathnetworkandbasedonskyimages AT shuyeding novelsolarforecastingschememodelledbymixerdualpathnetworkandbasedonskyimages AT weidongxiao novelsolarforecastingschememodelledbymixerdualpathnetworkandbasedonskyimages |