Self-adaptive evolutionary neural networks for high-precision short-term electric load forecasting
Abstract Reliable short-term electric load forecasting (STLF) is essential for enhancing grid stability, optimizing energy distribution, and minimizing operational costs in modern power systems. However, existing forecasting models, including statistical approaches and deep learning architectures su...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-05918-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849335117509558272 |
|---|---|
| author | Muhammad Abbas Yanbo Che Sarmad Maqsood Muhammad Zain Yousaf Mustafa Abdullah Wajid Khan Saqib Khalid Mohit Bajaj Mohammad Shabaz |
| author_facet | Muhammad Abbas Yanbo Che Sarmad Maqsood Muhammad Zain Yousaf Mustafa Abdullah Wajid Khan Saqib Khalid Mohit Bajaj Mohammad Shabaz |
| author_sort | Muhammad Abbas |
| collection | DOAJ |
| description | Abstract Reliable short-term electric load forecasting (STLF) is essential for enhancing grid stability, optimizing energy distribution, and minimizing operational costs in modern power systems. However, existing forecasting models, including statistical approaches and deep learning architectures such as multi-layer perceptron (MLP), struggle to capture complex nonlinear load variations while maintaining computational efficiency. To overcome these limitations, a self-adaptive Kolmogorov–Arnold network (SADE-KAN), an optimized forecasting framework that combines the power of Kolmogorov–Arnold networks (KAN) with self-adaptive differential evolution (SADE) is introduced to enhance both predictive accuracy and computational efficiency. Unlike conventional MLP models, KAN replaces fixed activation functions with spline-based learnable functions that offers greater flexibility in capturing temporal dependencies. However, these learnable activation functions introduce a new set of hyperparameters that require careful optimization to ensure efficient training and manage network complexity. To address this, SADE dynamically tunes these hyperparameters, ensuring an optimal balance between accuracy, complexity, and training efficiency. The proposed SADE-KAN model is validated on ISO-NE hourly load data (2019–2023, ~ 1 million observations) across multiple forecasting horizons (24, 48, 96, and 168 h). Experimental results demonstrate that SADE-KAN reduces mean absolute percentage error (MAPE) by up to 35% and root mean squared error (RMSE) by 38% compared to MLP models, while requiring 35% fewer learnable parameters. Despite a slightly higher training time, SADE-KAN significantly enhances generalization and robustness, capturing rapid load fluctuations more effectively than MLP, conventional KAN and other recently published advanced models. These findings establish SADE-KAN as a computationally efficient and highly accurate forecasting framework, offering a robust solution for real-time power system applications, demand response strategies, and energy market operations. |
| format | Article |
| id | doaj-art-f7e2d8b6faea489195adae2cedd49f23 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-f7e2d8b6faea489195adae2cedd49f232025-08-20T03:45:23ZengNature PortfolioScientific Reports2045-23222025-07-0115112110.1038/s41598-025-05918-wSelf-adaptive evolutionary neural networks for high-precision short-term electric load forecastingMuhammad Abbas0Yanbo Che1Sarmad Maqsood2Muhammad Zain Yousaf3Mustafa Abdullah4Wajid Khan5Saqib Khalid6Mohit Bajaj7Mohammad Shabaz8Key Laboratory of Smart Grid of Ministry of Education, School of Electrical and Information Engineering, Tianjin UniversityKey Laboratory of Smart Grid of Ministry of Education, School of Electrical and Information Engineering, Tianjin UniversityCentre of Real Time Computer Systems, Faculty of Informatics, Kaunas University of TechnologyCenter for Research on Microgrids (CROM), Huanjiang LaboratoryElectric Vehicles Engineering Department, Faculty of Engineering, Hourani Center for Applied Scientific Research, Al-Ahliyya Amman UniversityKey Laboratory of Smart Grid of Ministry of Education, School of Electrical and Information Engineering, Tianjin UniversitySchool of Electrical Engineering, The University of LahoreDepartment of Electrical Engineering, Graphic Era (Deemed to be University)Model Institute of Engineering and TechnologyAbstract Reliable short-term electric load forecasting (STLF) is essential for enhancing grid stability, optimizing energy distribution, and minimizing operational costs in modern power systems. However, existing forecasting models, including statistical approaches and deep learning architectures such as multi-layer perceptron (MLP), struggle to capture complex nonlinear load variations while maintaining computational efficiency. To overcome these limitations, a self-adaptive Kolmogorov–Arnold network (SADE-KAN), an optimized forecasting framework that combines the power of Kolmogorov–Arnold networks (KAN) with self-adaptive differential evolution (SADE) is introduced to enhance both predictive accuracy and computational efficiency. Unlike conventional MLP models, KAN replaces fixed activation functions with spline-based learnable functions that offers greater flexibility in capturing temporal dependencies. However, these learnable activation functions introduce a new set of hyperparameters that require careful optimization to ensure efficient training and manage network complexity. To address this, SADE dynamically tunes these hyperparameters, ensuring an optimal balance between accuracy, complexity, and training efficiency. The proposed SADE-KAN model is validated on ISO-NE hourly load data (2019–2023, ~ 1 million observations) across multiple forecasting horizons (24, 48, 96, and 168 h). Experimental results demonstrate that SADE-KAN reduces mean absolute percentage error (MAPE) by up to 35% and root mean squared error (RMSE) by 38% compared to MLP models, while requiring 35% fewer learnable parameters. Despite a slightly higher training time, SADE-KAN significantly enhances generalization and robustness, capturing rapid load fluctuations more effectively than MLP, conventional KAN and other recently published advanced models. These findings establish SADE-KAN as a computationally efficient and highly accurate forecasting framework, offering a robust solution for real-time power system applications, demand response strategies, and energy market operations.https://doi.org/10.1038/s41598-025-05918-wElectric load forecastingKolmogorov–Arnold networksMachine learningOptimizationPower systemsSelf-adaptive differential evolution |
| spellingShingle | Muhammad Abbas Yanbo Che Sarmad Maqsood Muhammad Zain Yousaf Mustafa Abdullah Wajid Khan Saqib Khalid Mohit Bajaj Mohammad Shabaz Self-adaptive evolutionary neural networks for high-precision short-term electric load forecasting Scientific Reports Electric load forecasting Kolmogorov–Arnold networks Machine learning Optimization Power systems Self-adaptive differential evolution |
| title | Self-adaptive evolutionary neural networks for high-precision short-term electric load forecasting |
| title_full | Self-adaptive evolutionary neural networks for high-precision short-term electric load forecasting |
| title_fullStr | Self-adaptive evolutionary neural networks for high-precision short-term electric load forecasting |
| title_full_unstemmed | Self-adaptive evolutionary neural networks for high-precision short-term electric load forecasting |
| title_short | Self-adaptive evolutionary neural networks for high-precision short-term electric load forecasting |
| title_sort | self adaptive evolutionary neural networks for high precision short term electric load forecasting |
| topic | Electric load forecasting Kolmogorov–Arnold networks Machine learning Optimization Power systems Self-adaptive differential evolution |
| url | https://doi.org/10.1038/s41598-025-05918-w |
| work_keys_str_mv | AT muhammadabbas selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT yanboche selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT sarmadmaqsood selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT muhammadzainyousaf selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT mustafaabdullah selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT wajidkhan selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT saqibkhalid selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT mohitbajaj selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting AT mohammadshabaz selfadaptiveevolutionaryneuralnetworksforhighprecisionshorttermelectricloadforecasting |