Developing Machine Learning Algorithm for Energy Supply Optimization in Virtual Power Plants

Document Type : Article

Authors

1 Department of Industrial Engineering, Yazd University, Yazd, Iran.

2 Department of Electrical Engineering, Yazd University, Yazd, Iran.

10.24200/j65.2025.66704.2433

Abstract

This research addresses the challenge of optimizing energy dispatch in restructured power markets by evaluating a Virtual Power Plant (VPP) model that integrates demand-side storage. The study aims to close the gap between energy supply and demand by employing two optimization methodologies: a precise Mixed-Integer Linear Programming (MILP) model and a hybrid algorithm based on an Extreme Learning Machine and a Genetic Algorithm (ELM-GA), which is computationally efficient. The VPP model incorporates a diverse portfolio of generation units (diesel, hydroelectric, solar, wind), supply-side storage, and a prosumer, with demand-side management actualized through a water storage system. The objectives are to maximize VPP profitability while minimizing hydroelectric energy losses and pump operational costs. Tested on a standard IEEE 24-bus system with real-world data, the results show that a VPP with demand-side storage is 1.5 times less costly than a traditional grid without storage. Furthermore, the VPP framework is 1.7 times more cost-effective than a traditional grid structure. For large-scale problems, the ELM-GA algorithm delivers near-optimal solutions (4.4% optimality gap) 16 times faster than MILP, highlighting its potential for rapid, reliable energy management and policy-making.

Keywords

Main Subjects

References

  1. References

     

    1. Awerbuch, S. and Preston, A., 1997. The Virtual Utility: Accounting, Technology & Competitive Aspects of the Emerging Industry. Springer: Berlin/Heidelberg. https://books.google.com/books?hl=en&lr=&id=BX3rBwAAQBAJ&oi=fnd&pg=PR13&dq=1.%09Awerbuch,+S.,+Preston,+A,.+1997.+The+Virtual+Utility:+Accounting,+Technology+%26+Competitive+Aspects+of+the++++Emerging+Industry.+Springer:+Berlin/Heidelberg&ots=n5ySfEIyFp&sig=64S7tKZufYrpka9Zw4gI429REpM
    2. Borenstein, S. and Bushnell, J., 2015. The U.S. electricity industry after 20 years of restructuring. National Bureau of Economic Research, 7(1), pp.437-463. https://doi.org/10.1146/annurev-economics-080614-115630
    3. Narkhede, M., Chatterji, S. and Ghosh, S., 2013. Multi objective optimal dispatch in a virtual power plant using genetic algorithm. International Conference on Renewable Energy and Sustainable Energy. https://doi.org/10.1109/ICRESE.2013.6927822
    4. Mao, T., Guo, X., Xie, P., Zhou, J., Zhou, B., Han, S., Wu, W. and Sun., L., 2020. Virtual power plant platforms and their applications in practice: a brief review. 2020 IEEE Sustainable Power and Energy Conference (iSPEC) 2071-2076. IEEE. 10.1109/iSPEC50848.2020.9351147
    5. Abdelaziz, Y. A., Hegazy, Y. G., Elkhattam, W. and Othman, M., 2013. Virtual power plant: The future of power delivery systems. Second European Workshop on Renewable Energy Systems. 1-2. https://www.academia.edu/download/72762869/VIRTUAL_POWER_PLANT_THE_FUTURE_OF_POWER_20211015-20727-10e0k2l.pdf
    6. Rouzbahani, H. M., Karimipour, H. and Lei, L., 2021. A review on virtual power plant for energy management. Sustainable Energy Technologies and Assessments, 47, pp. https://doi.org/10.1016/j.seta.2021.101370
    7. Warren, P., 2014. A review of demand-side management policy in the UK. Renewable and Sustainable Energy Reviews, 29, pp.941-951. https://doi.org/10.1016/j.rser.2013.09.009
    8. Park, S. and Son, S., 2020. Interaction-based virtual power plant operation methodology for distribution system operator’s voltage management. Applied Energy, 271, pp. https://doi.org/10.1016/j.apenergy.2020.115222
    9. Aguilar, J., Bordons, C. and Arce, A., 2021. Chance Constraints and Machine Learning integration for uncertainty management in Virtual Power Plants operating in simultaneous energy markets. International Journal of Electrical Power & Energy Systems, 133, pp. https://doi.org/10.1016/j.ijepes.2021.107304
    10. Nandkeolyar, S. and KumarRay, P., 2022. Multi objective demand side storage dispatch using hybrid extreme learning machine trained neural networks in a smart grid. Journal of Energy Storage, 51, pp. https://doi.org/10.1016/j.est.2022.104439
    11. Kabirifar, M., Pourghaderi, N. and Moeini-Aghtaie, M., 2022. Optimal operation strategy of virtual power plant considering EVs and ESSs. Scheduling and Operation of Virtual Power Plants, 257-297. https://doi.org/10.1016/B978-0-32-385267-8.00017-2
    12. Ali, Y., 2023. A novel machine learning-based power trading algorithm (MLPTA) for demand side management (DSM). 2023 International Conference on Emerging Power Technologies (ICEPT) 1-5. IEEE. https://doi.org/10.1109/ICEPT58859.2023.10152394
    13. Karimi, H., Jadid, S. and Hasanzadeh, S., 2023. Optimal-sustainable multi-energy management of microgrid systems considering integration of renewable energy resources: A multi-layer four-objective optimization. Sustainable Production and Consumption, 36, pp.126-138. https://doi.org/10.1016/j.spc.2022.12.025
    14. Ahmadian, A., Ponnambalam, K., Almansoori, A. and Elkamel, A., 2023. Optimal management of a virtual power plant consisting of renewable energy resources and electric vehicles using mixed-integer linear programming and deep learning. Energies, 16(2), pp. https://doi.org/10.3390/en16021000
    15. Singh, S., Subburaj, V., Sivakumar, K., Kumar, R., Muthuramam, M. S., Rastogi, R., Patil, V. R. and Rajaram, A., 2024. Optimum power forecasting technique for hybrid renewable energy systems using deep learning. Electric Power Components and Systems, pp.1-18. https://doi.org/10.1080/15325008.2024.2316251
    16. Zhaoxia, X., Jiakai, N., Guerrero, J. and Hongwei, F., 2017. Multiple time-scale optimization scheduling for islanded microgrids including PV, wind turbine, diesel generator and batteries. IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, pp.2594-2599. IEEE. https://doi.org/10.1109/IECON.2017.8216436
    17. Ullah, Z., Arshad, and Hassanin, H., 2017. Modeling, optimization, and analysis of a virtual power plant demand response mechanism for the internal electricity market considering the uncertainty of renewable energy sources. Energies, 15(14), pp.5296. https://doi.org/10.3390/en15145296
    18. Fleischer, C., Waag, W., Bai, Z. and Sauer, D.U., 2013. Adaptive on-line state-of-available-power prediction of lithium-ion batteries. Journal of Power Electronics, 13(4), pp.516-527. https://doi.org/10.6113/JPE.2013.13.4.516
    19. Dehghani, B., Lotfi, M. and Sedighi, A., 2024. Development of machine learning algorithm for energy supply management in virtual power plant. https://ganj.irandoc.ac.ir/#/articles/0e46b15100029e1032001d2255207137. [In Persian]

     

     

Sharif Journal of Industrial Engineering & Management
Volume 41, Issue 2 - Serial Number 2
February 2026
Pages 111-125

Files

Share

How to cite

Statistics