Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network
Abstract With the diversification of users’ energy demands, accurate load forecasting is an important prerequisite for optimal scheduling and economic operation of the system, but a single‐load forecasting method cannot effectively predict multi‐energy loads accurately. Therefore, this paper propose...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | IET Generation, Transmission & Distribution |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/gtd2.13083 |
| _version_ | 1797356784912957440 |
|---|---|
| author | Fei Li Chenjun Sun Wei Han Tongyu Yan Gang Li Zhenbing Zhao Yi Sun |
| author_facet | Fei Li Chenjun Sun Wei Han Tongyu Yan Gang Li Zhenbing Zhao Yi Sun |
| author_sort | Fei Li |
| collection | DOAJ |
| description | Abstract With the diversification of users’ energy demands, accurate load forecasting is an important prerequisite for optimal scheduling and economic operation of the system, but a single‐load forecasting method cannot effectively predict multi‐energy loads accurately. Therefore, this paper proposes a multi‐energy load forecasting method based on bidirectional long short‐term memory (BiLSTM) and parallel feature extraction networks. Firstly, residual network and convolutional block attention module were used to extract the spatial coupling features of multi‐energy load data. Secondly, BiLSTM is used to capture the temporal features and long‐term dependencies in the load data, and the spatial coupling features are fused to obtain non‐linear prediction results. Finally, the non‐linear prediction results and the linear prediction results obtained by using multi‐energy linear regression were linearly superimposed to obtain the final prediction results. In this paper, IES load data of Tempe Campus of Arizona State University was used to verify and compared with several existing methods, and the results showed that Weighted Mean Absolute Percentage Error decreased by more than 20%. |
| first_indexed | 2024-03-08T14:32:36Z |
| format | Article |
| id | doaj.art-fff520cf9c4e42099b44b168ddbe8119 |
| institution | Directory Open Access Journal |
| issn | 1751-8687 1751-8695 |
| language | English |
| last_indexed | 2024-03-08T14:32:36Z |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Generation, Transmission & Distribution |
| spelling | doaj.art-fff520cf9c4e42099b44b168ddbe81192024-01-12T08:04:57ZengWileyIET Generation, Transmission & Distribution1751-86871751-86952024-01-0118119020110.1049/gtd2.13083Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction networkFei Li0Chenjun Sun1Wei Han2Tongyu Yan3Gang Li4Zhenbing Zhao5Yi Sun6School of Electrical and Electronic Engineering North China Electric Power University Beijing ChinaState Grid Hebei Information & Telecommunication Branch Hebei, Shijiazhuang ChinaDepartment of Electronic & Communication Engineering North China Electric Power University Baoding Hebei ChinaState Grid Fujian Electric Power Research Institute Fuzhou Fujian ChinaDepartment of Computer North China Electric Power University Baoding Hebei ChinaDepartment of Electronic & Communication Engineering North China Electric Power University Baoding Hebei ChinaSchool of Electrical and Electronic Engineering North China Electric Power University Beijing ChinaAbstract With the diversification of users’ energy demands, accurate load forecasting is an important prerequisite for optimal scheduling and economic operation of the system, but a single‐load forecasting method cannot effectively predict multi‐energy loads accurately. Therefore, this paper proposes a multi‐energy load forecasting method based on bidirectional long short‐term memory (BiLSTM) and parallel feature extraction networks. Firstly, residual network and convolutional block attention module were used to extract the spatial coupling features of multi‐energy load data. Secondly, BiLSTM is used to capture the temporal features and long‐term dependencies in the load data, and the spatial coupling features are fused to obtain non‐linear prediction results. Finally, the non‐linear prediction results and the linear prediction results obtained by using multi‐energy linear regression were linearly superimposed to obtain the final prediction results. In this paper, IES load data of Tempe Campus of Arizona State University was used to verify and compared with several existing methods, and the results showed that Weighted Mean Absolute Percentage Error decreased by more than 20%.https://doi.org/10.1049/gtd2.13083convolutional neural netsfeature extractionload forecasting |
| spellingShingle | Fei Li Chenjun Sun Wei Han Tongyu Yan Gang Li Zhenbing Zhao Yi Sun Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network IET Generation, Transmission & Distribution convolutional neural nets feature extraction load forecasting |
| title | Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network |
| title_full | Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network |
| title_fullStr | Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network |
| title_full_unstemmed | Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network |
| title_short | Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network |
| title_sort | medium term load forecasting of power system based on bilstm and parallel feature extraction network |
| topic | convolutional neural nets feature extraction load forecasting |
| url | https://doi.org/10.1049/gtd2.13083 |
| work_keys_str_mv | AT feili mediumtermloadforecastingofpowersystembasedonbilstmandparallelfeatureextractionnetwork AT chenjunsun mediumtermloadforecastingofpowersystembasedonbilstmandparallelfeatureextractionnetwork AT weihan mediumtermloadforecastingofpowersystembasedonbilstmandparallelfeatureextractionnetwork AT tongyuyan mediumtermloadforecastingofpowersystembasedonbilstmandparallelfeatureextractionnetwork AT gangli mediumtermloadforecastingofpowersystembasedonbilstmandparallelfeatureextractionnetwork AT zhenbingzhao mediumtermloadforecastingofpowersystembasedonbilstmandparallelfeatureextractionnetwork AT yisun mediumtermloadforecastingofpowersystembasedonbilstmandparallelfeatureextractionnetwork |