Е-Публикации
Технически университет - София

Abstract: The large-scale integration of renewable energy sources (RES) introduces challenges of volatility, flexibility, and cybersecurity in modern power systems. Virtual Power Plants (VPPs) have emerged as digital aggregators that can coordinate distributed energy resources (DERs) to enhance grid stability and improve market participation. While numerous studies have reviewed VPP operations, most remain descriptive and lack comparative, architectural, and practical insights. This paper contributes in four main directions. First, we provide a comparative analysis between classical optimization methods (e.g., MILP, MINLP, stochastic programming) and emerging AI-based approaches (e.g., machine learning, reinforcement learning, federated learning). A structured comparison highlights strengths, weaknesses, and applicability under different operational conditions. Second, we propose a future AI-based VPP architecture, structured in layered form to integrate DERs, communication protocols, advanced optimization intelligence, and market interfaces. Third, a minisimulation case study is presented, contrasting classical MILP scheduling with reinforcement learning under forecast uncertainty. Results demonstrate that AI-based control achieves up to 8 % cost reduction while maintaining flexibility, though at the expense of transparency and computational complexity. Finally, we offer policy and industry recommendations, emphasizing hybrid frameworks, standardization, explainability, and cybersecurity. The findings suggest that hybrid VPP control, combining mathematical rigor with adaptive AI, will be essential for next-generation power systems. This work provides both researchers and practitioners with a roadmap toward resilient, scalable, and trustworthy VPP operations.

References

1. T. Zhang and G. Strbac, "Novel Artificial Intelligence Applications in Energy: A Systematic review, " Energies, vol. 18, no. 14, p. 3747, Jul. 2025, doi: 10.3390/en18143747.
2. S. Sierla, M. Pourakbari-Kasmaei, and V. Vyatkin, "A taxonomy of machine learning applications for virtual power plants and home/building energy management systems, " Automation in Construction, vol. 136, p. 104174, Feb. 2022, doi: 10.1016/j.autcon.2022.104174.
3. J. Li, W. Liang, Y. Liu, N. Zhou, T. Qian, and Q. Hu, "Deep Learning-Based Method for Operation Dispatch Strategy generation of virtual power plants, " Processes, vol. 13, no. 7, p. 2213, Jul. 2025, doi: 10.3390/pr13072213.
4. D. Yu, X. Zhao, Y. Wang, L. Jiang, and H. Liu, "Research on energy management of a virtual power plant based on the improved Cooperative Particle Swarm Optimization Algorithm, " Frontiers in Energy Research, vol. 10, Feb. 2022, doi: 10.3389/fenrg.2022.785569.
5. D. Yu, X. Zhao, Y. Wang, L. Jiang, and H. Liu, "Research on energy management of a virtual power plant based on the improved Cooperative Particle Swarm Optimization Algorithm, " Frontiers in Energy Research, vol. 10, Feb. 2022, doi: 10.3389/fenrg.2022.785569.
6. H. Ye, H. Huang, Y. He, M. Xu, Y. Yang and Y. Qiao, "Optimal Scheduling Method of Virtual Power Plant Based on Model Predictive Control, " 2023 3rd International Conference on Energy, Power and Electrical Engineering (EPEE), Wuhan, China, 2023, pp. 1439-1443, doi: 10.1109/EPEE59859.2023.10352051.
7. R. Ran, C. Zhao, Y. You, and Z. Xiong, "Application of virtual power plant in integrated smart energy substation, " 2022 7th Asia Conference on Power and Electrical Engineering (ACPEE), pp. 519-523, Apr. 2022, doi: 10.1109/acpee53904.2022.9784045.
8. W. Shuang, C. Boyuan, Y. Zhongguang, G. Lingyu, and D. Yang, "Optimized operation method of virtual power plant considering energy storage capacity configuration, " 2022 China International Conference on Electricity Distribution (CICED), pp. 462-467, Sep. 2024, doi: 10.1109/ciced63421.2024.10754091.
9. Q. Fang, N. Liang, Z. Liu and M. Miao, "Optimization Scheduling of Virtual Power Plant with Concentrated Solar Power Plant Considering Carbon Trading and Demand Response, " 2023 IEEE International Conference on Power Science and Technology (ICPST), Kunming, China, 2023, pp. 717-722, doi: 10.1109/ICPST56889.2023.10165555..
10. B.-P. Dobrin, L. Toma, H. Farhang, R.-A. Istrate, N. Anton and M. Sǎnduleac, "Modelling and Simulation of Virtual Power Plants, " 2022 International Conference and Exposition on Electrical And Power Engineering (EPE), Iasi, Romania, 2022, pp. 627-632, doi: 10.1109/EPE56121.2022.9959845.
11. W. Zhang et al., "Virtual power plant integration with smart grids: a Review, " 2022 IEEE 5th International Electrical and Energy Conference (CIEEC), Nangjing, China, 2022, pp. 4755-4759, doi: 10.1109/CIEEC54735.2022.9846220.
12. W. Xin, W. Xudong, X. Lei, L. Chang and L. Bo, "Research on scheduling strategy of virtual power plant based on multi-objective optimization of load-generating side, " 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), Changchun, China, 2023, pp. 1295-1298, doi: 10.1109/EEBDA56825.2023.10090584.
13. G. Todorov, I. Kralov, I. Koprev, H. Vasilev, and I. Naydenova, "Coal Share Reduction Options for Power Generation during the Energy Transition: A Bulgarian Perspective, " Energies, vol. 17, no. 4, p. 929, Feb. 2024, doi: 10.3390/en17040929

Issue