Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural Network
To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross valida...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/4/1925 |
| _version_ | 1811153843545702400 |
|---|---|
| author | Hui Liang Jiahui Wu Hua Zhang Jian Yang |
| author_facet | Hui Liang Jiahui Wu Hua Zhang Jian Yang |
| author_sort | Hui Liang |
| collection | DOAJ |
| description | To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. |
| first_indexed | 2024-03-11T08:52:30Z |
| format | Article |
| id | doaj.art-20847e1bb0be4b2e97cea1d5e3463839 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T08:52:30Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-20847e1bb0be4b2e97cea1d5e34638392023-11-16T20:19:41ZengMDPI AGEnergies1996-10732023-02-01164192510.3390/en16041925Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural NetworkHui Liang0Jiahui Wu1Hua Zhang2Jian Yang3School of Electrical Engineering, Xinjiang University, Urumqi 830017, ChinaSchool of Electrical Engineering, Xinjiang University, Urumqi 830017, ChinaCGN New Energy Investment (Shenzhen) Co., Ltd., Xinjiang Branch, Urumqi 830011, ChinaCGN New Energy Investment (Shenzhen) Co., Ltd., Xinjiang Branch, Urumqi 830011, ChinaTo solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model.https://www.mdpi.com/1996-1073/16/4/1925load forecastingtemporal convolutional networkefficient channel attentionrecursive feature elimination with cross validationlong short-term memory |
| spellingShingle | Hui Liang Jiahui Wu Hua Zhang Jian Yang Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural Network Energies load forecasting temporal convolutional network efficient channel attention recursive feature elimination with cross validation long short-term memory |
| title | Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural Network |
| title_full | Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural Network |
| title_fullStr | Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural Network |
| title_full_unstemmed | Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural Network |
| title_short | Two-Stage Short-Term Power Load Forecasting Based on RFECV Feature Selection Algorithm and a TCN–ECA–LSTM Neural Network |
| title_sort | two stage short term power load forecasting based on rfecv feature selection algorithm and a tcn eca lstm neural network |
| topic | load forecasting temporal convolutional network efficient channel attention recursive feature elimination with cross validation long short-term memory |
| url | https://www.mdpi.com/1996-1073/16/4/1925 |
| work_keys_str_mv | AT huiliang twostageshorttermpowerloadforecastingbasedonrfecvfeatureselectionalgorithmandatcnecalstmneuralnetwork AT jiahuiwu twostageshorttermpowerloadforecastingbasedonrfecvfeatureselectionalgorithmandatcnecalstmneuralnetwork AT huazhang twostageshorttermpowerloadforecastingbasedonrfecvfeatureselectionalgorithmandatcnecalstmneuralnetwork AT jianyang twostageshorttermpowerloadforecastingbasedonrfecvfeatureselectionalgorithmandatcnecalstmneuralnetwork |