Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth
IntroductionUrban power load forecasting is essential for smart grid planning but is hindered by data imbalance issues. Traditional single-model approaches fail to address this effectively, while multi-model methods mitigate imbalance by splitting datasets but incur high costs and risk losing shared...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Sustainable Cities |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frsc.2024.1487109/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841527868441493504 |
|---|---|
| author | Haewon Byeon Azzah AlGhamdi Ismail Keshta Mukesh Soni Sultonali Mekhmonov Gurpreet Singh |
| author_facet | Haewon Byeon Azzah AlGhamdi Ismail Keshta Mukesh Soni Sultonali Mekhmonov Gurpreet Singh |
| author_sort | Haewon Byeon |
| collection | DOAJ |
| description | IntroductionUrban power load forecasting is essential for smart grid planning but is hindered by data imbalance issues. Traditional single-model approaches fail to address this effectively, while multi-model methods mitigate imbalance by splitting datasets but incur high costs and risk losing shared power distribution characteristics.MethodsA lightweight urban power load forecasting model (DLUPLF) is proposed, enhancing LSTM networks with contrastive loss in short-term sampling, a difference compensation mechanism, and a shared feature extraction layer to reduce costs. The model adjusts predictions by learning distribution differences and employs dynamic class-center contrastive learning loss for regularization. Its performance was evaluated through parameter tuning and comparative analysis.ResultsThe DLUPLF model demonstrated improved accuracy in forecasting imbalanced datasets while reducing computational costs. It preserved shared power distribution characteristics and outperformed traditional and multi-model approaches in efficiency and prediction accuracy.DiscussionDLUPLF effectively addresses data imbalance and model complexity challenges, making it a promising solution for urban power load forecasting. Future work will focus on real-time applications and broader smart grid systems. |
| format | Article |
| id | doaj-art-f739198bcbbf46aa809c237adf9b211d |
| institution | Kabale University |
| issn | 2624-9634 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Sustainable Cities |
| spelling | doaj-art-f739198bcbbf46aa809c237adf9b211d2025-01-15T06:10:48ZengFrontiers Media S.A.Frontiers in Sustainable Cities2624-96342025-01-01610.3389/frsc.2024.14871091487109Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growthHaewon Byeon0Azzah AlGhamdi1Ismail Keshta2Mukesh Soni3Sultonali Mekhmonov4Gurpreet Singh5Department of AI and Software, Inje University, Gimhae, Republic of KoreaComputer Information Systems Department, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, Khobar, Saudi ArabiaComputer Science and Information Systems Department, College of Applied Sciences, AlMaarefa University, Riyadh, Saudi ArabiaDr. D. Y. Patil Vidyapeeth, Pune, Dr. D. Y. Patil School of Science & Technology, Pune, IndiaThe Department of Corporate Finance and Securities First Vice-Rector for Academic Affairs, Tashkent State University of Economics, Tashkent, UzbekistanChitkara University Institute of Engineering and Technology, Chitkara University, Chandigarh, Punjab, IndiaIntroductionUrban power load forecasting is essential for smart grid planning but is hindered by data imbalance issues. Traditional single-model approaches fail to address this effectively, while multi-model methods mitigate imbalance by splitting datasets but incur high costs and risk losing shared power distribution characteristics.MethodsA lightweight urban power load forecasting model (DLUPLF) is proposed, enhancing LSTM networks with contrastive loss in short-term sampling, a difference compensation mechanism, and a shared feature extraction layer to reduce costs. The model adjusts predictions by learning distribution differences and employs dynamic class-center contrastive learning loss for regularization. Its performance was evaluated through parameter tuning and comparative analysis.ResultsThe DLUPLF model demonstrated improved accuracy in forecasting imbalanced datasets while reducing computational costs. It preserved shared power distribution characteristics and outperformed traditional and multi-model approaches in efficiency and prediction accuracy.DiscussionDLUPLF effectively addresses data imbalance and model complexity challenges, making it a promising solution for urban power load forecasting. Future work will focus on real-time applications and broader smart grid systems.https://www.frontiersin.org/articles/10.3389/frsc.2024.1487109/fulldeep learningpower load forecastingsmart energysustainable urban growthLSTMload distribution |
| spellingShingle | Haewon Byeon Azzah AlGhamdi Ismail Keshta Mukesh Soni Sultonali Mekhmonov Gurpreet Singh Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth Frontiers in Sustainable Cities deep learning power load forecasting smart energy sustainable urban growth LSTM load distribution |
| title | Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth |
| title_full | Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth |
| title_fullStr | Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth |
| title_full_unstemmed | Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth |
| title_short | Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth |
| title_sort | deep learning and smart energy based lightweight urban power load forecasting model for sustainable urban growth |
| topic | deep learning power load forecasting smart energy sustainable urban growth LSTM load distribution |
| url | https://www.frontiersin.org/articles/10.3389/frsc.2024.1487109/full |
| work_keys_str_mv | AT haewonbyeon deeplearningandsmartenergybasedlightweighturbanpowerloadforecastingmodelforsustainableurbangrowth AT azzahalghamdi deeplearningandsmartenergybasedlightweighturbanpowerloadforecastingmodelforsustainableurbangrowth AT ismailkeshta deeplearningandsmartenergybasedlightweighturbanpowerloadforecastingmodelforsustainableurbangrowth AT mukeshsoni deeplearningandsmartenergybasedlightweighturbanpowerloadforecastingmodelforsustainableurbangrowth AT sultonalimekhmonov deeplearningandsmartenergybasedlightweighturbanpowerloadforecastingmodelforsustainableurbangrowth AT gurpreetsingh deeplearningandsmartenergybasedlightweighturbanpowerloadforecastingmodelforsustainableurbangrowth |