ASFO-SVM-Based Intelligent Load Prediction for Microgrid Energy Optimization in Renewable Energy Systems
DOI:
https://doi.org/10.63623/e2qz5c21Keywords:
Adaptive sunflower optimization, Support vector machine, Electric load forecasting, Micro-grid, Intelligent forecasting systemAbstract
Accurate load forecasting is essential for efficient microgrid operation, stability, and planning. Traditional forecasting methods often suffer from limitations in handling nonlinear, complex, and dynamic load patterns, which can reduce accuracy and reliability. To overcome these challenges, this study proposes a hybrid framework that integrates the adaptive sunflower optimization (ASFO) algorithm with support vector machines (SVM) for short-term microgrid load forecasting. The ASFO algorithm is employed to optimize SVM hyperparameters, enhancing generalization capability and improving prediction accuracy. The baseline forecasting model recorded a mean absolute percentage error (MAPE) of 34.59%, indicating the need for optimization. After applying the proposed ASFO-SVM framework, forecasting errors were significantly reduced, achieving a minimum MAPE of 0.44% for summer weekdays and consistently remaining below 2% across all seasonal and daily horizons. Comparative analysis with existing models__including PSO-SVM, Random Forest, and standalone SVM__demonstrates that ASFO-SVM achieves up to a 62.30% improvement in accuracy while maintaining computational efficiency. The findings confirm that the ASFO-SVM approach provides a robust, accurate, and adaptable solution for microgrid load forecasting. This makes it a promising candidate for practical deployment in intelligent energy management systems, especially in scenarios requiring reliable decision-making under uncertainty.
References
[1]Raj JJD, Jayanthi M. Electricity demand forecasting using ML. 2023 3rd International Conference on Pervasive Computing and Social Networking (ICPCSN). IEEE, 2023, 547-551. DOI: 10.1109/ICPCSN58827.2023.00095
[2]Ozdemir G. Long-term electrical energy demand forecasting by using artificial intelligence/machine learning techniques. Electrical Engineering, 2024, 106(4), 5229-5251. DOI: 10.1007/s00202-024-02364-1
[3]Abd’Azeez TA, Olatomiwa L. A machine learning-powered energy consumption prediction system with API. Journal of Electrical Systems and Information Technology, 2025, 12(1), 50. DOI: 10.1186/s43067-025-00242-9
[4]Robandi I, Hasanah R N, Akil Y S, Guntur HL, Lystianingrum V, Djalal MR, et al. Short-term peak load forecasting using interval type-2 fuzzy logic-horse herd optimization algorithm in sulbagsel electricity system. International Journal of Intelligent Engineering & Systems, 2025, 18(1), 268-278. DOI: 10.22266/ijies2025.0229.19
[5]Nazir M U, Li J. Forecasting of electricity consumption in Pakistan based on integrating machine learning algorithms and Monte Carlo simulation. Electrical Engineering, 2025, 17, 7539-7559. DOI: 10.1007/s00202-024-02923-6
[6]Boranbayeva Z. Using artificial neural networks for electric load forecasting. Development of Pedagogical Technologies Inmodern Sciences, 2025, 4(4), 110-112. DOI: 10.5281/zenodo.15258976
[7]Li R, Chen X, Balezentis T, Streimikiene D, Niu Z. Multi-step least squares support vector machine modeling approach for forecasting short-term electricity demand with application. Neural Computing and Applications, 2021, 33, 301-320. DOI: 10.1007/s00521-020-04996-3
[8]Hu, Z, Bao, Y, Xiong T. Electricity Load Forecasting Using Support Vector Regression with Memetic Algorithms. The Scientific World Journal, 2013, 2013(1), 292575. DOI: 10.1155/2013/292575
[9]Román-Portabales A, López-Nores M, Pazos-Arias JJ. Systematic review of electricity demand forecast using ANN-based machine learning algorithms. Sensors, 2021, 21(13), 4544. DOI: 10.3390/s21134544
[10]Lahouar A, Ben JBH, Hadj Slama. Random forests model for one day ahead load forecasting. IREC2015 The Sixth International Renewable Energy Congress, 2015, 1-6. DOI: 10.1109/IREC.2015.7110975
[11]Kang T, Lim DY, Tayara H, Chong KT. Forecasting of power demands using deep learning. Applied Sciences, 2020, 10(20), 7241. DOI: 10.3390/app10207241
[12]Anand A, Suganthi L. Forecasting of electricity demand by hybrid ANN-PSO models. Deep Learning and Neural Networks: Concepts, Methodologies, Tools, and Applications. IGI Global, 2020, 865-882. DOI: 10.4018/978-1-7998-0414-7.ch048
[13]Tahiri MA, Karmouni H, Azzayani A, Sayyouri M, Qjidaa H. Fast 3D image reconstruction by separable moments based on Hahn and Krawtchouk polynomials. 2020 fourth international conference on intelligent computing in data sciences (ICDS). IEEE, 2020, 1-7. DOI: 10.1109/ICDS50568.2020.9268721
[14]Shafiei Chafi Z, Afrakhte H. (2021). Short-term load forecasting using neural network and particle swarm optimization (PSO) algorithm. Mathematical Problems in Engineering, 2021, 2021(1), 5598267. DOI: 10.1155/2021/5598267
[15]Hao J, Sun X, Feng Q. A Novel ensemble approach for the forecasting of energy demand based on the artificial bee colony algorithm. Energies, 2020, 13(3), 550. DOI: 10.3390/en13030550
[16]Awan SM, Aslam M, Khan, ZA, Saeed H. An efficient model based on artificial bee colony optimization algorithm with Neural Networks for electric load forecasting. Neural Computing and Applications, 2014, 25(7), 1967-1978. DOI: 10.1007/s00521-014-1685-y
[17]Mansouri H, Tahiri MA, Bencherqui A, Moustabchir H, Qjidaa H, Sayyouri M. Securing Color Images with an Innovative Hybrid Method Combining DNA Computing and Chaotic Systems. Statistics, Optimization & Information Computing, 2024, 12(3). DOI: 10.19139/soic-2310-5070-1952
[18]Anand A, Suganthi L. Hybrid GA-PSO optimization of artificial neural network for forecasting electricity demand. Energies, 2018, 11(4), 728. DOI: 10.3390/en11040728
[19]Zhu G, Peng S, Lao Y, Su Q, Sun Q. Short-Term electricity consumption forecasting based on the EMD-Fbprophet-LSTM method. Mathematical Problems in Engineering, 2021, 2021(1), 6613604. DOI: 10.1155/2021/6613604
[20]Saoud A, Recioui A. Load energy forecasting based on a hybrid PSO LSTM-AE model. Algerian Journal of Environmental Science and Technology, 2023, 9(1), 2938-2946.
[21]Kim TY, Cho SB. Particle swarm optimization-based CNN-LSTM networks for forecasting energy consumption. 2019 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2019, 1510-1516. DOI: 10.1109/CEC.2019.8789968
[22]Wang JQ, Du Y, Wang J. LSTM based long-term energy consumption prediction with periodicity. Energy, 2020, 197, 117197. DOI: 10.1016/j.energy.2020.117197
[23]Kasule A, Ayan K. Forecasting Uganda’s net electricity consumption using a hybrid PSO-ABC Algorithm. Arabian Journal for Science and Engineering, 2019, 44(4), 3021-3031. DOI: 10.1007/s13369-018-3383-z.
[24]Bedi J, Toshniwal D. Deep learning framework to forecast electricity demand. Applied Energy, 2019, 238, 1312-1326. DOI: 10.1016/j.apenergy.2019.01.113
[25]Zec L, Mikulović J, Žarković M. Application of artificial neural network to power consumption forecasting for the Sarajevo region. Electrical Engineering, 2025, 107(3), 3561-3572. DOI: 10.1007/s00202-024-02696-y
[26]Li LL, Qu LN, Lin GQ, Lim MK, Tseng ML. Improved butterfly optimization algorithm-support vector machine: Short-term wind power forecasting model. Soft Computing, 2025, 1-21. DOI: 10.1007/s00500-025-10694-w
[27]Gupta RK, Anjum A, Fowziya SA, Devi S, Anusuya M. A Hybrid CNN-XGAOA approach for photovoltaic power output prediction using environmental features. 2025 5th International Conference on Trends in Material Science and Inventive Materials (ICTMIM). IEEE, 2025, 908-913. DOI: 10.1109/ICTMIM65579.2025.10988147
[28]Wedhasari T. Electricity load forecasting using a hybrid artificial neural network and PSO approach. SENTRI: Jurnal Riset Ilmiah, 2025, 4(8), 1175-1187. DOI: 10.55681/sentri.v4i8.4373
[29]Aguilar Madrid E, Antonio N. Short-term electricity load forecasting with machine learning. Information, 2021, 12(2), 50. DOI: 10.3390/info12020050
[30]El Ghouate N, Bencherqui A, Mansouri H, Maloufy A., Tahiri MA, Karmouni H, et al. Improving the Kepler optimization algorithm with chaotic maps: Comprehensive performance evaluation and engineering applications. Artificial Intelligence Review, 2024, 57(11), 313. DOI: 10.1007/s10462-024-10857-5
[31]Gomes GF, da Cunha Jr SS, Ancelotti Jr AC. A sunflower optimization (SFO) algorithm applied to damage identification on laminated composite plates. Engineering with Computers, 2019, 35(2), 619-626. DOI: 10.1007/s00366-018-0620-8
[32]Bencherqui A, Tahiri M A, Karmouni H, Daoui A, Alfidi M, Jamil M, et al. Optimization of Meixner moments by the firefly algorithm for image analysis. International conference on digital technologies and applications. Cham: Springer International Publishing, 2022, 439-448. DOI: 10.1007/978-3-031-01942-5_44
[33]Rabab O, Tahiri MA, Bencherqui A, Amakdouf H, Jamil MO, Qjidaa H. Efficient localization and reconstruction of 3D objects using the new hybrid squire moment. 2022 International Conference on Intelligent Systems and Computer Vision (ISCV), Fez, Morocco, 2022, 1-8. DOI: 10.1109/ISCV54655.2022.9806086
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Arivoli Sundaramurthy, Ganesh Moorthy Jagadeesan, Karthikeyan Ramasamy, Chitra Vaithiyalingam (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
