Research on a load forecasting model based on ACMD and BiGRU-Attention
To lessen the impact of fluctuation and randomness of the user-side load on the load forecasting accuracy， a BiGRU-Attention （bidirectional gated recurrent unit with attention） short-term load forecasting model based on ACMD （adaptive chirp mode decomposition） and the Attention mechanism is proposed...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
zhejiang electric power
2023-06-01
|
| Series: | Zhejiang dianli |
| Subjects: | |
| Online Access: | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=ca10cb95-ee2b-4d45-9978-976e5009bce7 |
| _version_ | 1797788221079289856 |
|---|---|
| author | SHEN Jianliang LAI Jun ZHANG Yi WANG Jianfeng ZHONG Zan YANG Ping |
| author_facet | SHEN Jianliang LAI Jun ZHANG Yi WANG Jianfeng ZHONG Zan YANG Ping |
| author_sort | SHEN Jianliang |
| collection | DOAJ |
| description | To lessen the impact of fluctuation and randomness of the user-side load on the load forecasting accuracy， a BiGRU-Attention （bidirectional gated recurrent unit with attention） short-term load forecasting model based on ACMD （adaptive chirp mode decomposition） and the Attention mechanism is proposed. Firstly， ACMD is used to decompose the load time series into several relatively regular subcomponents； then， the BiGRU model is used to predict the subcomponents and sum them up to obtain the final prediction results. To highlight the influence of important information， the Attention mechanism is introduced into the BiGRU model to give corresponding weights to the implied states of the BiGRU network. The sparrow search algorithm is used for the optimal selection of model hyperparameters to reduce the impact of misselection of model hyperparameters. An open data set is used for example analysis that is compared with a single model and combined model respectively. The results show that the method is superior in prediction. |
| first_indexed | 2024-03-13T01:32:31Z |
| format | Article |
| id | doaj.art-e9d35f8d98124874ab67d330d80baf2f |
| institution | Directory Open Access Journal |
| issn | 1007-1881 |
| language | zho |
| last_indexed | 2024-03-13T01:32:31Z |
| publishDate | 2023-06-01 |
| publisher | zhejiang electric power |
| record_format | Article |
| series | Zhejiang dianli |
| spelling | doaj.art-e9d35f8d98124874ab67d330d80baf2f2023-07-04T06:43:14Zzhozhejiang electric powerZhejiang dianli1007-18812023-06-01426707710.19585/j.zjdl.2023060081007-1881（2023）06-0070-08Research on a load forecasting model based on ACMD and BiGRU-AttentionSHEN Jianliang0LAI Jun1ZHANG Yi2WANG Jianfeng3ZHONG Zan4YANG Ping5State Grid Huzhou Power Supply Company, Huzhou, Hangzhou 313000, ChinaState Grid Huzhou Power Supply Company, Huzhou, Hangzhou 313000, ChinaState Grid Huzhou Power Supply Company, Huzhou, Hangzhou 313000, ChinaState Grid Huzhou Power Supply Company, Huzhou, Hangzhou 313000, ChinaState Grid Huzhou Power Supply Company, Huzhou, Hangzhou 313000, ChinaCollege of Electrical Engineering, Sichuan University, Chengdu 610065, ChinaTo lessen the impact of fluctuation and randomness of the user-side load on the load forecasting accuracy， a BiGRU-Attention （bidirectional gated recurrent unit with attention） short-term load forecasting model based on ACMD （adaptive chirp mode decomposition） and the Attention mechanism is proposed. Firstly， ACMD is used to decompose the load time series into several relatively regular subcomponents； then， the BiGRU model is used to predict the subcomponents and sum them up to obtain the final prediction results. To highlight the influence of important information， the Attention mechanism is introduced into the BiGRU model to give corresponding weights to the implied states of the BiGRU network. The sparrow search algorithm is used for the optimal selection of model hyperparameters to reduce the impact of misselection of model hyperparameters. An open data set is used for example analysis that is compared with a single model and combined model respectively. The results show that the method is superior in prediction.https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=ca10cb95-ee2b-4d45-9978-976e5009bce7load forecastingbigruacmdsparrow search algorithmattention mechanism |
| spellingShingle | SHEN Jianliang LAI Jun ZHANG Yi WANG Jianfeng ZHONG Zan YANG Ping Research on a load forecasting model based on ACMD and BiGRU-Attention Zhejiang dianli load forecasting bigru acmd sparrow search algorithm attention mechanism |
| title | Research on a load forecasting model based on ACMD and BiGRU-Attention |
| title_full | Research on a load forecasting model based on ACMD and BiGRU-Attention |
| title_fullStr | Research on a load forecasting model based on ACMD and BiGRU-Attention |
| title_full_unstemmed | Research on a load forecasting model based on ACMD and BiGRU-Attention |
| title_short | Research on a load forecasting model based on ACMD and BiGRU-Attention |
| title_sort | research on a load forecasting model based on acmd and bigru attention |
| topic | load forecasting bigru acmd sparrow search algorithm attention mechanism |
| url | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=ca10cb95-ee2b-4d45-9978-976e5009bce7 |
| work_keys_str_mv | AT shenjianliang researchonaloadforecastingmodelbasedonacmdandbigruattention AT laijun researchonaloadforecastingmodelbasedonacmdandbigruattention AT zhangyi researchonaloadforecastingmodelbasedonacmdandbigruattention AT wangjianfeng researchonaloadforecastingmodelbasedonacmdandbigruattention AT zhongzan researchonaloadforecastingmodelbasedonacmdandbigruattention AT yangping researchonaloadforecastingmodelbasedonacmdandbigruattention |