Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network
To fully mine the relationship between temporal features in load data, improve the accuracy and efficiency of short-term load forecasting and overcome the difficulties caused by load nonlinearity and volatility in accurate load forecasting. In this paper, a hybrid neural network short-term load fore...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9417229/ |
| _version_ | 1818864012578783232 |
|---|---|
| author | Hanhong Shi Lei Wang Rafal Scherer Marcin Wozniak Pengchao Zhang Wei Wei |
| author_facet | Hanhong Shi Lei Wang Rafal Scherer Marcin Wozniak Pengchao Zhang Wei Wei |
| author_sort | Hanhong Shi |
| collection | DOAJ |
| description | To fully mine the relationship between temporal features in load data, improve the accuracy and efficiency of short-term load forecasting and overcome the difficulties caused by load nonlinearity and volatility in accurate load forecasting. In this paper, a hybrid neural network short-term load forecasting model based on temporal convolutional network (TCN) and gated recurrent unit (GRU) is proposed. Firstly, the correlation between meteorological features and load is measured with the distance correlation coefficient, and the fixed-length sliding time window method is used to reconstruct the features. Next, temporal convolutional network is adopted to extract the hidden historical information and time relationship including meteorological features, electricity price, etc., and a better-performing gated recurrent unit is utilized for perdition. Furthermore, the state-of-the-art AdaBelief optimizer and Attention mechanism are utilized to enhance the prediction accuracy and efficiency. The effectiveness and superiority of the proposed model are verified by load and weather data from Spain and PJM power system data. Short-term load forecasting results in different periods and comprehensive comparisons with the performance of different models show that the proposed model can provide accurate load forecasting results rather quickly. The highlights of this paper are that temporal convolutional network and gated recurrent unit are combined for load forecasting for the first time, and the forecasting performance is improved by the novel optimizer AdaBelief and feature selection based on distance correlation coefficient. |
| first_indexed | 2024-12-19T10:24:53Z |
| format | Article |
| id | doaj.art-6c48211a13f14dff8e780b3446899443 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T10:24:53Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6c48211a13f14dff8e780b34468994432022-12-21T20:25:57ZengIEEEIEEE Access2169-35362021-01-019669656698110.1109/ACCESS.2021.30763139417229Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural NetworkHanhong Shi0https://orcid.org/0000-0003-3295-6325Lei Wang1https://orcid.org/0000-0002-8967-8795Rafal Scherer2https://orcid.org/0000-0001-9592-262XMarcin Wozniak3https://orcid.org/0000-0002-9073-5347Pengchao Zhang4https://orcid.org/0000-0003-3738-9155Wei Wei5https://orcid.org/0000-0002-7566-2995Shaanxi Key Laboratory of Industrial Automation, Shaanxi University of Technology, Hanzhong, ChinaShaanxi Key Laboratory of Industrial Automation, Shaanxi University of Technology, Hanzhong, ChinaInstitute of Computational Intelligence, Czestochowa University of Technology, Czestochowa, PolandFaculty of Applied Mathematics, Silesian University of Technology, Gliwice, PolandShaanxi Key Laboratory of Industrial Automation, Shaanxi University of Technology, Hanzhong, ChinaShaanxi Key Laboratory for Network Computing and Security Technology, Xi’an University of Technology, Xi’an, ChinaTo fully mine the relationship between temporal features in load data, improve the accuracy and efficiency of short-term load forecasting and overcome the difficulties caused by load nonlinearity and volatility in accurate load forecasting. In this paper, a hybrid neural network short-term load forecasting model based on temporal convolutional network (TCN) and gated recurrent unit (GRU) is proposed. Firstly, the correlation between meteorological features and load is measured with the distance correlation coefficient, and the fixed-length sliding time window method is used to reconstruct the features. Next, temporal convolutional network is adopted to extract the hidden historical information and time relationship including meteorological features, electricity price, etc., and a better-performing gated recurrent unit is utilized for perdition. Furthermore, the state-of-the-art AdaBelief optimizer and Attention mechanism are utilized to enhance the prediction accuracy and efficiency. The effectiveness and superiority of the proposed model are verified by load and weather data from Spain and PJM power system data. Short-term load forecasting results in different periods and comprehensive comparisons with the performance of different models show that the proposed model can provide accurate load forecasting results rather quickly. The highlights of this paper are that temporal convolutional network and gated recurrent unit are combined for load forecasting for the first time, and the forecasting performance is improved by the novel optimizer AdaBelief and feature selection based on distance correlation coefficient.https://ieeexplore.ieee.org/document/9417229/Short-term load forecastingdistance correlation coefficientadabelieftemporal convolution networkgated recurrent unitattention mechanism |
| spellingShingle | Hanhong Shi Lei Wang Rafal Scherer Marcin Wozniak Pengchao Zhang Wei Wei Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network IEEE Access Short-term load forecasting distance correlation coefficient adabelief temporal convolution network gated recurrent unit attention mechanism |
| title | Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network |
| title_full | Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network |
| title_fullStr | Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network |
| title_full_unstemmed | Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network |
| title_short | Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network |
| title_sort | short term load forecasting based on adabelief optimized temporal convolutional network and gated recurrent unit hybrid neural network |
| topic | Short-term load forecasting distance correlation coefficient adabelief temporal convolution network gated recurrent unit attention mechanism |
| url | https://ieeexplore.ieee.org/document/9417229/ |
| work_keys_str_mv | AT hanhongshi shorttermloadforecastingbasedonadabeliefoptimizedtemporalconvolutionalnetworkandgatedrecurrentunithybridneuralnetwork AT leiwang shorttermloadforecastingbasedonadabeliefoptimizedtemporalconvolutionalnetworkandgatedrecurrentunithybridneuralnetwork AT rafalscherer shorttermloadforecastingbasedonadabeliefoptimizedtemporalconvolutionalnetworkandgatedrecurrentunithybridneuralnetwork AT marcinwozniak shorttermloadforecastingbasedonadabeliefoptimizedtemporalconvolutionalnetworkandgatedrecurrentunithybridneuralnetwork AT pengchaozhang shorttermloadforecastingbasedonadabeliefoptimizedtemporalconvolutionalnetworkandgatedrecurrentunithybridneuralnetwork AT weiwei shorttermloadforecastingbasedonadabeliefoptimizedtemporalconvolutionalnetworkandgatedrecurrentunithybridneuralnetwork |