CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting
Integrated Energy Systems (IES) are an important way to improve the efficiency of energy, promote closer connections between various energy systems, and reduce carbon emissions. The transformation between electricity, heating, and cooling loads into each other makes the dynamic characteristics of mu...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/21/3481 |
| _version_ | 1797468494167539712 |
|---|---|
| author | Bowen Ren Cunqiang Huang Laijun Chen Shengwei Mei Juan An Xingwen Liu Hengrui Ma |
| author_facet | Bowen Ren Cunqiang Huang Laijun Chen Shengwei Mei Juan An Xingwen Liu Hengrui Ma |
| author_sort | Bowen Ren |
| collection | DOAJ |
| description | Integrated Energy Systems (IES) are an important way to improve the efficiency of energy, promote closer connections between various energy systems, and reduce carbon emissions. The transformation between electricity, heating, and cooling loads into each other makes the dynamic characteristics of multiple loads more complex and brings challenges to the accurate forecasting of multi-energy loads. In order to further improve the accuracy of IES short-term load forecasting, we propose the Convolutional Neural Network, the Long Short-Term Memory Network, and Auto-Regression (CLSTM-AR) combined with the multi-dimensional feature fusion (MFFCLA). In detail, CLSTM can extract the coupling and periodic characteristics implied in IES load data from multiple time dimensions. AR takes load data as the input to extract features of sequential auto-correlation over adjacent time periods. Then, the diverse and effective features extracted by CLSTM, LSTM, and AR can be fused using the multi-dimensional feature fusion technique. Ultimately, the model achieves the accurate prediction of multiple loads. In conclusion, compared with other forecasting models, the case study results show that MFFCLA has higher forecasting precision compared with the comparable model in the short-term multi-energy load forecasting performance of electricity, heating, and cooling. The accuracy of MFFCLA can help to optimize and dispatch IES to make better use of renewable energy. |
| first_indexed | 2024-03-09T19:08:16Z |
| format | Article |
| id | doaj.art-4cce4bfe36e4417ba417ae6b8bcd53d3 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T19:08:16Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-4cce4bfe36e4417ba417ae6b8bcd53d32023-11-24T04:24:39ZengMDPI AGElectronics2079-92922022-10-011121348110.3390/electronics11213481CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load ForecastingBowen Ren0Cunqiang Huang1Laijun Chen2Shengwei Mei3Juan An4Xingwen Liu5Hengrui Ma6Qinghai Key Lab of Efficient Utilization of Clean Energy (Tus-Institute for Renewable Energy), University of Qinghai, Xining 810016, ChinaInstitute of Economic Technology State Grid Qinghai Electric Power Company, Xining 810008, ChinaQinghai Key Lab of Efficient Utilization of Clean Energy (Tus-Institute for Renewable Energy), University of Qinghai, Xining 810016, ChinaQinghai Key Lab of Efficient Utilization of Clean Energy (Tus-Institute for Renewable Energy), University of Qinghai, Xining 810016, ChinaInstitute of Economic Technology State Grid Qinghai Electric Power Company, Xining 810008, ChinaInstitute of Economic Technology State Grid Qinghai Electric Power Company, Xining 810008, ChinaQinghai Key Lab of Efficient Utilization of Clean Energy (Tus-Institute for Renewable Energy), University of Qinghai, Xining 810016, ChinaIntegrated Energy Systems (IES) are an important way to improve the efficiency of energy, promote closer connections between various energy systems, and reduce carbon emissions. The transformation between electricity, heating, and cooling loads into each other makes the dynamic characteristics of multiple loads more complex and brings challenges to the accurate forecasting of multi-energy loads. In order to further improve the accuracy of IES short-term load forecasting, we propose the Convolutional Neural Network, the Long Short-Term Memory Network, and Auto-Regression (CLSTM-AR) combined with the multi-dimensional feature fusion (MFFCLA). In detail, CLSTM can extract the coupling and periodic characteristics implied in IES load data from multiple time dimensions. AR takes load data as the input to extract features of sequential auto-correlation over adjacent time periods. Then, the diverse and effective features extracted by CLSTM, LSTM, and AR can be fused using the multi-dimensional feature fusion technique. Ultimately, the model achieves the accurate prediction of multiple loads. In conclusion, compared with other forecasting models, the case study results show that MFFCLA has higher forecasting precision compared with the comparable model in the short-term multi-energy load forecasting performance of electricity, heating, and cooling. The accuracy of MFFCLA can help to optimize and dispatch IES to make better use of renewable energy.https://www.mdpi.com/2079-9292/11/21/3481integrated energy systemsmulti-energy load forecastingfeature confusionCLSTM |
| spellingShingle | Bowen Ren Cunqiang Huang Laijun Chen Shengwei Mei Juan An Xingwen Liu Hengrui Ma CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting Electronics integrated energy systems multi-energy load forecasting feature confusion CLSTM |
| title | CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting |
| title_full | CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting |
| title_fullStr | CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting |
| title_full_unstemmed | CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting |
| title_short | CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting |
| title_sort | clstm ar based multi dimensional feature fusion for multi energy load forecasting |
| topic | integrated energy systems multi-energy load forecasting feature confusion CLSTM |
| url | https://www.mdpi.com/2079-9292/11/21/3481 |
| work_keys_str_mv | AT bowenren clstmarbasedmultidimensionalfeaturefusionformultienergyloadforecasting AT cunqianghuang clstmarbasedmultidimensionalfeaturefusionformultienergyloadforecasting AT laijunchen clstmarbasedmultidimensionalfeaturefusionformultienergyloadforecasting AT shengweimei clstmarbasedmultidimensionalfeaturefusionformultienergyloadforecasting AT juanan clstmarbasedmultidimensionalfeaturefusionformultienergyloadforecasting AT xingwenliu clstmarbasedmultidimensionalfeaturefusionformultienergyloadforecasting AT hengruima clstmarbasedmultidimensionalfeaturefusionformultienergyloadforecasting |