Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN)
Nowadays, wind power generation has become vital thanks to its advantages in cost, ecological friendliness, enormousness, and sustainability. However, the erratic and intermittent nature of this energy poses significant operational and management difficulties for power systems. Currently, the method...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/9/3792 |
| _version_ | 1797602676182089728 |
|---|---|
| author | Huu Khoa Minh Nguyen Quoc-Dung Phan Yuan-Kang Wu Quoc-Thang Phan |
| author_facet | Huu Khoa Minh Nguyen Quoc-Dung Phan Yuan-Kang Wu Quoc-Thang Phan |
| author_sort | Huu Khoa Minh Nguyen |
| collection | DOAJ |
| description | Nowadays, wind power generation has become vital thanks to its advantages in cost, ecological friendliness, enormousness, and sustainability. However, the erratic and intermittent nature of this energy poses significant operational and management difficulties for power systems. Currently, the methods of wind power forecasting (WPF) are various and numerous. An accurate forecasting method of WPF can help system dispatchers plan unit commitment and reduce the risk of the unreliability of electricity supply. In order to improve the accuracy of short-term prediction for wind power and address the multi-step ahead forecasting, this research presents a Stacked Temporal Convolutional Network (S-TCN) model. By using dilated causal convolutions and residual connections, the suggested solution addresses the issue of long-term dependencies and performance degradation of deep convolutional models in sequence prediction. The simulation outcomes demonstrate that the S-TCN model’s training procedure is extremely stable and has a powerful capacity for generalization. Besides, the performance of the proposed model shows a higher forecasting accuracy compared to other existing neural networks like the Vanilla Long Short-Term Memory model or the Bidirectional Long Short-Term Memory model. |
| first_indexed | 2024-03-11T04:19:57Z |
| format | Article |
| id | doaj.art-328e7f1a243c42c2afafbdbe4ed3ee59 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T04:19:57Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-328e7f1a243c42c2afafbdbe4ed3ee592023-11-17T22:51:48ZengMDPI AGEnergies1996-10732023-04-01169379210.3390/en16093792Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN)Huu Khoa Minh Nguyen0Quoc-Dung Phan1Yuan-Kang Wu2Quoc-Thang Phan3Faculty of Electrical and Electronics Engineering, Ho Chi Minh City University of Technology (HCMUT), 268 Ly Thuong Kiet Street, District 10, Ho Chi Minh City 70000, VietnamFaculty of Electrical and Electronics Engineering, Ho Chi Minh City University of Technology (HCMUT), 268 Ly Thuong Kiet Street, District 10, Ho Chi Minh City 70000, VietnamDepartment of Electrical Engineering, National Chung Cheng University, Chiayi 62102, TaiwanDepartment of Electrical Engineering, National Chung Cheng University, Chiayi 62102, TaiwanNowadays, wind power generation has become vital thanks to its advantages in cost, ecological friendliness, enormousness, and sustainability. However, the erratic and intermittent nature of this energy poses significant operational and management difficulties for power systems. Currently, the methods of wind power forecasting (WPF) are various and numerous. An accurate forecasting method of WPF can help system dispatchers plan unit commitment and reduce the risk of the unreliability of electricity supply. In order to improve the accuracy of short-term prediction for wind power and address the multi-step ahead forecasting, this research presents a Stacked Temporal Convolutional Network (S-TCN) model. By using dilated causal convolutions and residual connections, the suggested solution addresses the issue of long-term dependencies and performance degradation of deep convolutional models in sequence prediction. The simulation outcomes demonstrate that the S-TCN model’s training procedure is extremely stable and has a powerful capacity for generalization. Besides, the performance of the proposed model shows a higher forecasting accuracy compared to other existing neural networks like the Vanilla Long Short-Term Memory model or the Bidirectional Long Short-Term Memory model.https://www.mdpi.com/1996-1073/16/9/3792wind power forecastingmulti-step predictionsimilar time seriesStacked Temporal Convolutional Network (S-TCN) |
| spellingShingle | Huu Khoa Minh Nguyen Quoc-Dung Phan Yuan-Kang Wu Quoc-Thang Phan Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN) Energies wind power forecasting multi-step prediction similar time series Stacked Temporal Convolutional Network (S-TCN) |
| title | Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN) |
| title_full | Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN) |
| title_fullStr | Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN) |
| title_full_unstemmed | Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN) |
| title_short | Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN) |
| title_sort | multi step wind power forecasting with stacked temporal convolutional network s tcn |
| topic | wind power forecasting multi-step prediction similar time series Stacked Temporal Convolutional Network (S-TCN) |
| url | https://www.mdpi.com/1996-1073/16/9/3792 |
| work_keys_str_mv | AT huukhoaminhnguyen multistepwindpowerforecastingwithstackedtemporalconvolutionalnetworkstcn AT quocdungphan multistepwindpowerforecastingwithstackedtemporalconvolutionalnetworkstcn AT yuankangwu multistepwindpowerforecastingwithstackedtemporalconvolutionalnetworkstcn AT quocthangphan multistepwindpowerforecastingwithstackedtemporalconvolutionalnetworkstcn |