An improved LSTM-Seq2Seq-based forecasting method for electricity load
Power load forecasting has gained considerable research interest in recent years. The power load is vulnerable to randomness and uncertainty during power grid operations. Therefore, it is crucial to effectively predict the electric load and improve the accuracy of the prediction. This study proposes...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.1093667/full |
| _version_ | 1797943574504931328 |
|---|---|
| author | Yangyang Mu Ming Wang Xuehan Zheng He Gao He Gao |
| author_facet | Yangyang Mu Ming Wang Xuehan Zheng He Gao He Gao |
| author_sort | Yangyang Mu |
| collection | DOAJ |
| description | Power load forecasting has gained considerable research interest in recent years. The power load is vulnerable to randomness and uncertainty during power grid operations. Therefore, it is crucial to effectively predict the electric load and improve the accuracy of the prediction. This study proposes a novel power load forecasting method based on an improved long short-term memory (LSTM) neural network. Thus, an long short-term memory neural network model is established for power load forecasting, which supports variable-length inputs and outputs. The conventional convolutional neural network (CNN) and recurrent neural network (RNN) cannot reflect the sequence dependence between the output labels. Therefore, the LSTM-Seq2Seq prediction model was established by combining the sequence-to-sequence (Seq2Seq) structure with that of the long short-term memory model to improve the prediction accuracy. Four prediction models, i.e., long short-term memory, deep belief network (DBN), support vector machine (SVM), and LSTM-Seq2Seq, were simulated and tested on two different datasets. The results demonstrated the effectiveness of the proposed LSTM-Seq2Seq method. In the future, this model can be extended to more prediction application scenarios. |
| first_indexed | 2024-04-10T20:26:20Z |
| format | Article |
| id | doaj.art-5c4b3e61724649c0a0d902df5b641a98 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-10T20:26:20Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-5c4b3e61724649c0a0d902df5b641a982023-01-25T10:25:04ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-01-011010.3389/fenrg.2022.10936671093667An improved LSTM-Seq2Seq-based forecasting method for electricity loadYangyang Mu0Ming Wang1Xuehan Zheng2He Gao3He Gao4School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, ChinaSchool of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, ChinaSchool of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, ChinaSchool of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, ChinaShandong Zhengchen Technology Co., Ltd, Jinan, ChinaPower load forecasting has gained considerable research interest in recent years. The power load is vulnerable to randomness and uncertainty during power grid operations. Therefore, it is crucial to effectively predict the electric load and improve the accuracy of the prediction. This study proposes a novel power load forecasting method based on an improved long short-term memory (LSTM) neural network. Thus, an long short-term memory neural network model is established for power load forecasting, which supports variable-length inputs and outputs. The conventional convolutional neural network (CNN) and recurrent neural network (RNN) cannot reflect the sequence dependence between the output labels. Therefore, the LSTM-Seq2Seq prediction model was established by combining the sequence-to-sequence (Seq2Seq) structure with that of the long short-term memory model to improve the prediction accuracy. Four prediction models, i.e., long short-term memory, deep belief network (DBN), support vector machine (SVM), and LSTM-Seq2Seq, were simulated and tested on two different datasets. The results demonstrated the effectiveness of the proposed LSTM-Seq2Seq method. In the future, this model can be extended to more prediction application scenarios.https://www.frontiersin.org/articles/10.3389/fenrg.2022.1093667/fullpower load forecastingLSTM neural networksmart gridseq2seqdeep learning |
| spellingShingle | Yangyang Mu Ming Wang Xuehan Zheng He Gao He Gao An improved LSTM-Seq2Seq-based forecasting method for electricity load Frontiers in Energy Research power load forecasting LSTM neural network smart grid seq2seq deep learning |
| title | An improved LSTM-Seq2Seq-based forecasting method for electricity load |
| title_full | An improved LSTM-Seq2Seq-based forecasting method for electricity load |
| title_fullStr | An improved LSTM-Seq2Seq-based forecasting method for electricity load |
| title_full_unstemmed | An improved LSTM-Seq2Seq-based forecasting method for electricity load |
| title_short | An improved LSTM-Seq2Seq-based forecasting method for electricity load |
| title_sort | improved lstm seq2seq based forecasting method for electricity load |
| topic | power load forecasting LSTM neural network smart grid seq2seq deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.1093667/full |
| work_keys_str_mv | AT yangyangmu animprovedlstmseq2seqbasedforecastingmethodforelectricityload AT mingwang animprovedlstmseq2seqbasedforecastingmethodforelectricityload AT xuehanzheng animprovedlstmseq2seqbasedforecastingmethodforelectricityload AT hegao animprovedlstmseq2seqbasedforecastingmethodforelectricityload AT hegao animprovedlstmseq2seqbasedforecastingmethodforelectricityload AT yangyangmu improvedlstmseq2seqbasedforecastingmethodforelectricityload AT mingwang improvedlstmseq2seqbasedforecastingmethodforelectricityload AT xuehanzheng improvedlstmseq2seqbasedforecastingmethodforelectricityload AT hegao improvedlstmseq2seqbasedforecastingmethodforelectricityload AT hegao improvedlstmseq2seqbasedforecastingmethodforelectricityload |