A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory network
Abstract The instability of solar energy is the biggest challenge to its successful integration with modern power grids, and accurate prediction of long‐term solar radiation can effectively solve this problem. In this study, we proposed a novel long‐term solar radiation prediction model based on tim...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-11-01
|
| Series: | Energy Science & Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ese3.1875 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841557275243708416 |
|---|---|
| author | Zhaoshuang He Xue Zhang Min Li Shaoquan Wang Gongwei Xiao |
| author_facet | Zhaoshuang He Xue Zhang Min Li Shaoquan Wang Gongwei Xiao |
| author_sort | Zhaoshuang He |
| collection | DOAJ |
| description | Abstract The instability of solar energy is the biggest challenge to its successful integration with modern power grids, and accurate prediction of long‐term solar radiation can effectively solve this problem. In this study, we proposed a novel long‐term solar radiation prediction model based on time series imaging and bidirectional long short‐term memory network. First, inspired by the computer vision algorithm, the recursive graph algorithm is used to transform the one‐dimensional time series into two‐dimensional images, and then convolutional neural network is used to extract the features from the images, thus, the deeper features in the original solar radiation data can be mined. Second, to solve the problem of low accuracy of long‐term solar radiation prediction, a hybrid model BiLSTM‐Transformer is used to predict long‐term solar radiation. The hybrid prediction model can capture the long‐term dependencies, thereby further improving the accuracy of the prediction model. The experimental results show that the hybrid model proposed in this study is superior to other single models and hybrid models in long‐term solar radiation prediction accuracy. The accuracy and stability of the hybrid model are verified by many tests. |
| format | Article |
| id | doaj-art-f0a19ceecf364d05b95847ffb1cb10f2 |
| institution | Kabale University |
| issn | 2050-0505 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Energy Science & Engineering |
| spelling | doaj-art-f0a19ceecf364d05b95847ffb1cb10f22025-01-06T14:45:33ZengWileyEnergy Science & Engineering2050-05052024-11-0112114876489310.1002/ese3.1875A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory networkZhaoshuang He0Xue Zhang1Min Li2Shaoquan Wang3Gongwei Xiao4School of Telecommunication and Information Engineering Xi'an University of Posts & Telecommunication Xi'an ChinaSchool of Telecommunication and Information Engineering Xi'an University of Posts & Telecommunication Xi'an ChinaSchool of Information Science and Engineering Lanzhou University Lanzhou ChinaSchool of Telecommunication and Information Engineering Xi'an University of Posts & Telecommunication Xi'an ChinaSchool of Telecommunication and Information Engineering Xi'an University of Posts & Telecommunication Xi'an ChinaAbstract The instability of solar energy is the biggest challenge to its successful integration with modern power grids, and accurate prediction of long‐term solar radiation can effectively solve this problem. In this study, we proposed a novel long‐term solar radiation prediction model based on time series imaging and bidirectional long short‐term memory network. First, inspired by the computer vision algorithm, the recursive graph algorithm is used to transform the one‐dimensional time series into two‐dimensional images, and then convolutional neural network is used to extract the features from the images, thus, the deeper features in the original solar radiation data can be mined. Second, to solve the problem of low accuracy of long‐term solar radiation prediction, a hybrid model BiLSTM‐Transformer is used to predict long‐term solar radiation. The hybrid prediction model can capture the long‐term dependencies, thereby further improving the accuracy of the prediction model. The experimental results show that the hybrid model proposed in this study is superior to other single models and hybrid models in long‐term solar radiation prediction accuracy. The accuracy and stability of the hybrid model are verified by many tests.https://doi.org/10.1002/ese3.1875bidirectional long short‐term memory networkconvolutional neural networkssolar radiation predictiontime series imagingTransformer |
| spellingShingle | Zhaoshuang He Xue Zhang Min Li Shaoquan Wang Gongwei Xiao A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory network Energy Science & Engineering bidirectional long short‐term memory network convolutional neural networks solar radiation prediction time series imaging Transformer |
| title | A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory network |
| title_full | A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory network |
| title_fullStr | A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory network |
| title_full_unstemmed | A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory network |
| title_short | A novel solar radiation forecasting model based on time series imaging and bidirectional long short‐term memory network |
| title_sort | novel solar radiation forecasting model based on time series imaging and bidirectional long short term memory network |
| topic | bidirectional long short‐term memory network convolutional neural networks solar radiation prediction time series imaging Transformer |
| url | https://doi.org/10.1002/ese3.1875 |
| work_keys_str_mv | AT zhaoshuanghe anovelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT xuezhang anovelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT minli anovelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT shaoquanwang anovelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT gongweixiao anovelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT zhaoshuanghe novelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT xuezhang novelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT minli novelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT shaoquanwang novelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork AT gongweixiao novelsolarradiationforecastingmodelbasedontimeseriesimagingandbidirectionallongshorttermmemorynetwork |