Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network
Abstract Short‐term load forecasting is the basis of power system operation and analysis and is of great significance for the stable operation of power systems. To solve the problems of insufficient mining of the intrinsic information of load data, randomness, and non‐linearity, and to improve the a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-04-01
|
| Series: | IET Generation, Transmission & Distribution |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/gtd2.13151 |
| _version_ | 1797201348468408320 |
|---|---|
| author | Zhongwei Zhao Wenfang Lin |
| author_facet | Zhongwei Zhao Wenfang Lin |
| author_sort | Zhongwei Zhao |
| collection | DOAJ |
| description | Abstract Short‐term load forecasting is the basis of power system operation and analysis and is of great significance for the stable operation of power systems. To solve the problems of insufficient mining of the intrinsic information of load data, randomness, and non‐linearity, and to improve the accuracy of load prediction, the authors propose a short‐term power load prediction model based on empirical wavelet transform (EWT) decomposition and the temporal convolutional network (TCN). First, the Pearson coefficient is used to eliminate the less relevant influencing factors to reduce the complexity of the model. Then, the EWT algorithm is used to decompose the original load signal to fully exploit the load data time domain and frequency domain information, while solving the problems of non‐linearity and randomness. Finally, the decomposed subsequences are input to the TCN network for prediction superposition to obtain the final results. The experimental results show that, compared with the single models TCN, gated recurrent units (GRU), and long short‐term memory (LSTM), and the hybrid models EWT‐GRU, EWT‐LSTM, and VMD‐TCN, the R2 of the short‐term power load forecasting model based on EWT‐TCN is improved by 0.2099%, 0.2519%, 0.3453%, 0.0334%, 0.1766%, and 0.1228%, respectively. |
| first_indexed | 2024-04-24T07:46:07Z |
| format | Article |
| id | doaj.art-bfffb847bd244e0b9bd6805ddd44e89c |
| institution | Directory Open Access Journal |
| issn | 1751-8687 1751-8695 |
| language | English |
| last_indexed | 2024-04-24T07:46:07Z |
| publishDate | 2024-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Generation, Transmission & Distribution |
| spelling | doaj.art-bfffb847bd244e0b9bd6805ddd44e89c2024-04-19T03:19:17ZengWileyIET Generation, Transmission & Distribution1751-86871751-86952024-04-011881672168310.1049/gtd2.13151Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional networkZhongwei Zhao0Wenfang Lin1IEE Department Zhejiang Gongshang University Hangzhou ChinaIEE Department Zhejiang Gongshang University Hangzhou ChinaAbstract Short‐term load forecasting is the basis of power system operation and analysis and is of great significance for the stable operation of power systems. To solve the problems of insufficient mining of the intrinsic information of load data, randomness, and non‐linearity, and to improve the accuracy of load prediction, the authors propose a short‐term power load prediction model based on empirical wavelet transform (EWT) decomposition and the temporal convolutional network (TCN). First, the Pearson coefficient is used to eliminate the less relevant influencing factors to reduce the complexity of the model. Then, the EWT algorithm is used to decompose the original load signal to fully exploit the load data time domain and frequency domain information, while solving the problems of non‐linearity and randomness. Finally, the decomposed subsequences are input to the TCN network for prediction superposition to obtain the final results. The experimental results show that, compared with the single models TCN, gated recurrent units (GRU), and long short‐term memory (LSTM), and the hybrid models EWT‐GRU, EWT‐LSTM, and VMD‐TCN, the R2 of the short‐term power load forecasting model based on EWT‐TCN is improved by 0.2099%, 0.2519%, 0.3453%, 0.0334%, 0.1766%, and 0.1228%, respectively.https://doi.org/10.1049/gtd2.13151data analysisload forecastingneural netssignal processing |
| spellingShingle | Zhongwei Zhao Wenfang Lin Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network IET Generation, Transmission & Distribution data analysis load forecasting neural nets signal processing |
| title | Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network |
| title_full | Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network |
| title_fullStr | Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network |
| title_full_unstemmed | Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network |
| title_short | Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network |
| title_sort | short term electric load forecasting based on empirical wavelet transform and temporal convolutional network |
| topic | data analysis load forecasting neural nets signal processing |
| url | https://doi.org/10.1049/gtd2.13151 |
| work_keys_str_mv | AT zhongweizhao shorttermelectricloadforecastingbasedonempiricalwavelettransformandtemporalconvolutionalnetwork AT wenfanglin shorttermelectricloadforecastingbasedonempiricalwavelettransformandtemporalconvolutionalnetwork |