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...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Abbas, Yanbo Che, Sarmad Maqsood, Muhammad Zain Yousaf, Mustafa Abdullah, Wajid Khan, Saqib Khalid, Mohit Bajaj, Mohammad Shabaz
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