Stride-TCN for Energy Consumption Forecasting and Its Optimization
Forecasting, commonly used in econometrics, meteorology, or energy consumption prediction, is the field of study that deals with time series data to predict future trends. Former studies have revealed that both traditional statistical models and recent deep learning-based approaches have achieved go...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/19/9422 |
| _version_ | 1797480868749508608 |
|---|---|
| author | Le Hoang Anh Gwang Hyun Yu Dang Thanh Vu Jin Sul Kim Jung Il Lee Jun Churl Yoon Jin Young Kim |
| author_facet | Le Hoang Anh Gwang Hyun Yu Dang Thanh Vu Jin Sul Kim Jung Il Lee Jun Churl Yoon Jin Young Kim |
| author_sort | Le Hoang Anh |
| collection | DOAJ |
| description | Forecasting, commonly used in econometrics, meteorology, or energy consumption prediction, is the field of study that deals with time series data to predict future trends. Former studies have revealed that both traditional statistical models and recent deep learning-based approaches have achieved good performance in forecasting. In particular, temporal convolutional networks (TCNs) have proved their effectiveness in several time series benchmarks. However, presented TCN models are too heavy to deploy on resource-constrained systems, such as edge devices. As a resolution, this study proposes a stride–dilation mechanism for TCN that favors a lightweight model yet still achieves on-pair accuracy with the heavy counterparts. We also present the Chonnam National University (CNU) Electric Power Consumption dataset, the dataset of energy consumption measured at CNU by smart meters every hour. The experimental results indicate that our best model reduces the mean squared error by 32.7%, whereas the model size is only 1.6% compared to the baseline TCN. |
| first_indexed | 2024-03-09T22:07:17Z |
| format | Article |
| id | doaj.art-3f59fb3bd4f64a59851739da876daadf |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:07:17Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3f59fb3bd4f64a59851739da876daadf2023-11-23T19:39:15ZengMDPI AGApplied Sciences2076-34172022-09-011219942210.3390/app12199422Stride-TCN for Energy Consumption Forecasting and Its OptimizationLe Hoang Anh0Gwang Hyun Yu1Dang Thanh Vu2Jin Sul Kim3Jung Il Lee4Jun Churl Yoon5Jin Young Kim6Department of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, KoreaKorea Electric Power Research Institute (KEPRI), 105, Munji-ro, Yuseong-ku, Daejeon 34056, KoreaKorea Electric Power Corporation (KEPCO), 55, Jeollyeok-ro, Jeollanam-do, Naju-si 58322, KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, KoreaForecasting, commonly used in econometrics, meteorology, or energy consumption prediction, is the field of study that deals with time series data to predict future trends. Former studies have revealed that both traditional statistical models and recent deep learning-based approaches have achieved good performance in forecasting. In particular, temporal convolutional networks (TCNs) have proved their effectiveness in several time series benchmarks. However, presented TCN models are too heavy to deploy on resource-constrained systems, such as edge devices. As a resolution, this study proposes a stride–dilation mechanism for TCN that favors a lightweight model yet still achieves on-pair accuracy with the heavy counterparts. We also present the Chonnam National University (CNU) Electric Power Consumption dataset, the dataset of energy consumption measured at CNU by smart meters every hour. The experimental results indicate that our best model reduces the mean squared error by 32.7%, whereas the model size is only 1.6% compared to the baseline TCN.https://www.mdpi.com/2076-3417/12/19/9422temporal convolutional networksdeep learningtime-series forecasting |
| spellingShingle | Le Hoang Anh Gwang Hyun Yu Dang Thanh Vu Jin Sul Kim Jung Il Lee Jun Churl Yoon Jin Young Kim Stride-TCN for Energy Consumption Forecasting and Its Optimization Applied Sciences temporal convolutional networks deep learning time-series forecasting |
| title | Stride-TCN for Energy Consumption Forecasting and Its Optimization |
| title_full | Stride-TCN for Energy Consumption Forecasting and Its Optimization |
| title_fullStr | Stride-TCN for Energy Consumption Forecasting and Its Optimization |
| title_full_unstemmed | Stride-TCN for Energy Consumption Forecasting and Its Optimization |
| title_short | Stride-TCN for Energy Consumption Forecasting and Its Optimization |
| title_sort | stride tcn for energy consumption forecasting and its optimization |
| topic | temporal convolutional networks deep learning time-series forecasting |
| url | https://www.mdpi.com/2076-3417/12/19/9422 |
| work_keys_str_mv | AT lehoanganh stridetcnforenergyconsumptionforecastinganditsoptimization AT gwanghyunyu stridetcnforenergyconsumptionforecastinganditsoptimization AT dangthanhvu stridetcnforenergyconsumptionforecastinganditsoptimization AT jinsulkim stridetcnforenergyconsumptionforecastinganditsoptimization AT jungillee stridetcnforenergyconsumptionforecastinganditsoptimization AT junchurlyoon stridetcnforenergyconsumptionforecastinganditsoptimization AT jinyoungkim stridetcnforenergyconsumptionforecastinganditsoptimization |