A hybrid temporal convolutional network and Prophet model for power load forecasting
Abstract Accurate and effective power system load forecasting is an important prerequisite for the safe and stable operation of the power grid and the normal production and operation of society. In recent years, convolutional neural networks (CNNs) have been widely used in time series prediction due...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-12-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-022-00952-x |
| _version_ | 1797769257697673216 |
|---|---|
| author | Jinyuan Mo Rui Wang Mengda Cao Kang Yang Xu Yang Tao Zhang |
| author_facet | Jinyuan Mo Rui Wang Mengda Cao Kang Yang Xu Yang Tao Zhang |
| author_sort | Jinyuan Mo |
| collection | DOAJ |
| description | Abstract Accurate and effective power system load forecasting is an important prerequisite for the safe and stable operation of the power grid and the normal production and operation of society. In recent years, convolutional neural networks (CNNs) have been widely used in time series prediction due to their parallel computing and other characteristics, but it is difficult for CNNs to capture the relationship of sequence context and meanwhile, it easily leads to information leakage. To avoid the drawbacks of CNNs, we adopt a temporal convolutional network (TCN), specially designed for time series. TCN combines causal convolution, dilated convolution, and residual connection, and fully considers the causal correlation between historical data and future data. Considering that the power load data has strong periodicity and is greatly influenced by seasons and holidays, we adopt the Prophet model to decompose the load data and fit the trend component, season component, and holiday component. We use TCN and Prophet to forecast the power load data respectively, and then use the least square method to fuse the two models, and make use of their respective advantages to improve the forecasting accuracy. Experiments show that the proposed TCN-Prophet model has a higher prediction accuracy than the classic ARIMA, RNN, LSTM, GRU, and some ensemble models, and can provide more effective decision-making references for power grid departments. |
| first_indexed | 2024-03-12T21:06:22Z |
| format | Article |
| id | doaj.art-c7e98adbfdaf4b6db14b14ca4863b919 |
| institution | Directory Open Access Journal |
| issn | 2199-4536 2198-6053 |
| language | English |
| last_indexed | 2024-03-12T21:06:22Z |
| publishDate | 2022-12-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj.art-c7e98adbfdaf4b6db14b14ca4863b9192023-07-30T11:28:15ZengSpringerComplex & Intelligent Systems2199-45362198-60532022-12-01944249426110.1007/s40747-022-00952-xA hybrid temporal convolutional network and Prophet model for power load forecastingJinyuan Mo0Rui Wang1Mengda Cao2Kang Yang3Xu Yang4Tao Zhang5College of System Engineering, National University of Defense TechnologyCollege of System Engineering, National University of Defense TechnologyCollege of System Engineering, National University of Defense TechnologyCollege of System Engineering, National University of Defense TechnologyCollege of System Engineering, National University of Defense TechnologyCollege of System Engineering, National University of Defense TechnologyAbstract Accurate and effective power system load forecasting is an important prerequisite for the safe and stable operation of the power grid and the normal production and operation of society. In recent years, convolutional neural networks (CNNs) have been widely used in time series prediction due to their parallel computing and other characteristics, but it is difficult for CNNs to capture the relationship of sequence context and meanwhile, it easily leads to information leakage. To avoid the drawbacks of CNNs, we adopt a temporal convolutional network (TCN), specially designed for time series. TCN combines causal convolution, dilated convolution, and residual connection, and fully considers the causal correlation between historical data and future data. Considering that the power load data has strong periodicity and is greatly influenced by seasons and holidays, we adopt the Prophet model to decompose the load data and fit the trend component, season component, and holiday component. We use TCN and Prophet to forecast the power load data respectively, and then use the least square method to fuse the two models, and make use of their respective advantages to improve the forecasting accuracy. Experiments show that the proposed TCN-Prophet model has a higher prediction accuracy than the classic ARIMA, RNN, LSTM, GRU, and some ensemble models, and can provide more effective decision-making references for power grid departments.https://doi.org/10.1007/s40747-022-00952-xPower load forecastingTemporal convolutional networkProphet modelLeast square method |
| spellingShingle | Jinyuan Mo Rui Wang Mengda Cao Kang Yang Xu Yang Tao Zhang A hybrid temporal convolutional network and Prophet model for power load forecasting Complex & Intelligent Systems Power load forecasting Temporal convolutional network Prophet model Least square method |
| title | A hybrid temporal convolutional network and Prophet model for power load forecasting |
| title_full | A hybrid temporal convolutional network and Prophet model for power load forecasting |
| title_fullStr | A hybrid temporal convolutional network and Prophet model for power load forecasting |
| title_full_unstemmed | A hybrid temporal convolutional network and Prophet model for power load forecasting |
| title_short | A hybrid temporal convolutional network and Prophet model for power load forecasting |
| title_sort | hybrid temporal convolutional network and prophet model for power load forecasting |
| topic | Power load forecasting Temporal convolutional network Prophet model Least square method |
| url | https://doi.org/10.1007/s40747-022-00952-x |
| work_keys_str_mv | AT jinyuanmo ahybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT ruiwang ahybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT mengdacao ahybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT kangyang ahybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT xuyang ahybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT taozhang ahybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT jinyuanmo hybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT ruiwang hybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT mengdacao hybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT kangyang hybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT xuyang hybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting AT taozhang hybridtemporalconvolutionalnetworkandprophetmodelforpowerloadforecasting |