DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution
In the face of increasing irregular temperature patterns and climate shifts, the need for accurate power consumption prediction is becoming increasingly important to ensure a steady supply of electricity. Existing deep learning models have sought to improve prediction accuracy but commonly require g...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/22/7662 |
| _version_ | 1797459407800369152 |
|---|---|
| author | Le Hoang Anh Gwang-Hyun Yu Dang Thanh Vu Hyoung-Gook Kim Jin-Young Kim |
| author_facet | Le Hoang Anh Gwang-Hyun Yu Dang Thanh Vu Hyoung-Gook Kim Jin-Young Kim |
| author_sort | Le Hoang Anh |
| collection | DOAJ |
| description | In the face of increasing irregular temperature patterns and climate shifts, the need for accurate power consumption prediction is becoming increasingly important to ensure a steady supply of electricity. Existing deep learning models have sought to improve prediction accuracy but commonly require greater computational demands. In this research, on the other hand, we introduce DelayNet, a lightweight deep learning model that maintains model efficiency while accommodating extended time sequences. Our DelayNet is designed based on the observation that electronic series data exhibit recurring irregular patterns over time. Furthermore, we present two substantial datasets of electricity consumption records from South Korean buildings spanning nearly two years. Empirical findings demonstrate the model’s performance, achieving 21.23%, 43.60%, 17.05% and 21.71% improvement compared to recurrent neural networks, gated-recurrent units, temporal convolutional neural networks and ARIMA models, as well as greatly reducing model complexity and computational requirements. These findings indicate the potential for micro-level power consumption planning, as lightweight models can be implemented on edge devices. |
| first_indexed | 2024-03-09T16:51:47Z |
| format | Article |
| id | doaj.art-7814fc5e32d94980951a4d03320e428c |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T16:51:47Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-7814fc5e32d94980951a4d03320e428c2023-11-24T14:40:43ZengMDPI AGEnergies1996-10732023-11-011622766210.3390/en16227662DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated ConvolutionLe Hoang Anh0Gwang-Hyun Yu1Dang Thanh Vu2Hyoung-Gook Kim3Jin-Young Kim4Department of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of KoreaDepartment of Electronic Convergence Engineering, Kwangwoon University, 20 Gwangun-ro, Nowon-gu, Seoul 01897, Republic of KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of KoreaIn the face of increasing irregular temperature patterns and climate shifts, the need for accurate power consumption prediction is becoming increasingly important to ensure a steady supply of electricity. Existing deep learning models have sought to improve prediction accuracy but commonly require greater computational demands. In this research, on the other hand, we introduce DelayNet, a lightweight deep learning model that maintains model efficiency while accommodating extended time sequences. Our DelayNet is designed based on the observation that electronic series data exhibit recurring irregular patterns over time. Furthermore, we present two substantial datasets of electricity consumption records from South Korean buildings spanning nearly two years. Empirical findings demonstrate the model’s performance, achieving 21.23%, 43.60%, 17.05% and 21.71% improvement compared to recurrent neural networks, gated-recurrent units, temporal convolutional neural networks and ARIMA models, as well as greatly reducing model complexity and computational requirements. These findings indicate the potential for micro-level power consumption planning, as lightweight models can be implemented on edge devices.https://www.mdpi.com/1996-1073/16/22/7662temporal convolutional neural Networktime-delayforecasting |
| spellingShingle | Le Hoang Anh Gwang-Hyun Yu Dang Thanh Vu Hyoung-Gook Kim Jin-Young Kim DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution Energies temporal convolutional neural Network time-delay forecasting |
| title | DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution |
| title_full | DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution |
| title_fullStr | DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution |
| title_full_unstemmed | DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution |
| title_short | DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution |
| title_sort | delaynet enhancing temporal feature extraction for electronic consumption forecasting with delayed dilated convolution |
| topic | temporal convolutional neural Network time-delay forecasting |
| url | https://www.mdpi.com/1996-1073/16/22/7662 |
| work_keys_str_mv | AT lehoanganh delaynetenhancingtemporalfeatureextractionforelectronicconsumptionforecastingwithdelayeddilatedconvolution AT gwanghyunyu delaynetenhancingtemporalfeatureextractionforelectronicconsumptionforecastingwithdelayeddilatedconvolution AT dangthanhvu delaynetenhancingtemporalfeatureextractionforelectronicconsumptionforecastingwithdelayeddilatedconvolution AT hyounggookkim delaynetenhancingtemporalfeatureextractionforelectronicconsumptionforecastingwithdelayeddilatedconvolution AT jinyoungkim delaynetenhancingtemporalfeatureextractionforelectronicconsumptionforecastingwithdelayeddilatedconvolution |