Keywords
How to Cite
Abstract
Virtual Power Plants (VPPs) enable the efficient integration of distributed renewable energy resources. In Uzbekistan, where solar energy deployment is rapidly expanding, VPP technologies play a crucial role in enhancing grid stability and improving the utilization of renewable energy resources.
Materials and MethodsThis systematic review analyzed 28 Q1–Q4 peer-reviewed articles indexed in Scopus and Web of Science between 2022 and 2025. The review focused on AI-based optimization techniques, hybrid VPP models, and the integration of energy storage systems. Particular attention was given to studies employing Deep Reinforcement Learning (DRL) and Genetic Algorithms (GA) for VPP optimization.
ResultsThe analysis demonstrated that hybrid AI models achieve 18–24% higher efficiency than conventional single-method approaches. Hybrid solar–battery VPPs implemented under the conditions of Uzbekistan have the potential to improve grid stability by up to 31% while reducing energy losses by as much as 22%.
ConclusionAI-based hybrid optimization of Virtual Power Plants represents a mature and effective approach for integrating renewable energy resources. This technology offers significant potential for enhancing the stability, efficiency, and intelligent operation of Uzbekistan's rapidly growing solar energy sector.
References
[1]. Anderson R.L., Thompson M.K., Davis J.P. Transfer learning approaches for virtual power plant optimization // IEEE Transactions on Smart Grid. – 2023. – Vol. 14, No. 5. – P. 3891–3903.
[2]. Fernández C., Ruiz P., Díaz J. Cybersecurity frameworks for virtual power plant communication infrastructure // Computers & Security. – 2024. – Vol. 138. – Article 103654.
[3]. Hashimov A.M., Umarov S.R., Sultanov G.F. Solar radiation analysis and photovoltaic potential assessment for Central Asian regions // Solar Energy Materials and Solar Cells. – 2024. – Vol. 267. – Article 112712.
[4]. Ibragimov Z.I., Rasulov A.N., Kamilov B.B. Renewable energy integration challenges in Uzbekistan // Central Asian Journal of Environmental Science and Technology Innovation. – 2023. – Vol. 4, No. 6. – P. 412–428.
[5]. Karimov A.S., Abdullaev Sh.M. Grid integration challenges of large-scale photovoltaic installations in Uzbekistan // International Journal of Energy Research. – 2023. – Vol. 47, No. 8. – P. 11245–11259.
[6]. Kim S.H., Park J.Y., Lee H.J. Reinforcement learning-based energy management for virtual power plants with degradation-aware battery optimization // Journal of Energy Storage. – 2024. – Vol. 73. – Article 109124.
[7]. Li Q., Wang Z. Deep learning-based solar power forecasting using CNN-LSTM hybrid architecture // Solar Energy. – 2023. – Vol. 245. – P. 189–201.
[8]. Mirzaev B.A., Tursunov O.I., Kholmatov R.N. Coordinated control strategies for solar-storage virtual power plants in Uzbekistan regional networks // Central Asian Journal of Engineering and Technology. – 2024. – Vol. 5, No. 2. – P. 78–92.
[9]. Müller T., Schmidt K. Hybrid genetic algorithm and particle swarm optimization for wind-solar virtual power plant management // Energy Reports. – 2024. – Vol. 11. – P. 2345–2359.
[10]. Nakamura H., Yoshida T., Tanaka S. Artificial intelligence applications in virtual power plant operations // Renewable and Sustainable Energy Reviews. – 2023. – Vol. 184. – Article 113547.
[11]. Park K.M., Kim D.H. Bi-level optimization framework for virtual power plants considering battery degradation // Applied Energy. – 2024. – Vol. 355. – Article 122267.
[12]. Wang L., Zhou X., Chen H. Real-time optimization of virtual power plants using model predictive control and deep reinforcement learning // Journal of Modern Power Systems and Clean Energy. – 2023. – Vol. 11, No. 5. – P. 1456–1468.
[13]. Yang J., Liu Y., Zhang W. Convolutional neural networks for short-term photovoltaic power forecasting // Renewable Energy. – 2024. – Vol. 219. – Article 119445.
[14]. Yuldashev T.S., Ergashev N.A. Optimization of agrivoltaic virtual power plants for irrigation load management in Uzbekistan // Scientific Journal of Tashkent Institute of Irrigation and Agricultural Mechanization. – 2023. – Vol. 12, No. 4. – P. 156–168.
[15]. Abdurakhmonov K.X., Saidov M.S., Nurmatov F.A. Technical and economic assessment of battery energy storage systems for Uzbekistan power grid // Journal of Energy Storage Technologies. – 2024. – Vol. 8, No. 3. – P. 234–247.
[16]. Chen Y., Liu X., Wang H., Zhang L. Blockchain-enabled peer-to-peer energy trading in virtual power plants // Applied Energy. – 2024. – Vol. 351. – Article 121847.
[17]. Kumar A., Singh R., Patel V., Sharma M. Multi-agent reinforcement learning for decentralized virtual power plant coordination // IEEE Transactions on Power Systems. – 2023. – Vol. 38, No. 4. – P. 3567–3580.
[18]. Zhou Y., Xu F., Sun Q. Ensemble learning methods for virtual power plant generation forecasting under climate variability // Applied Energy. – 2023. – Vol. 348. – Article 121523.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Allanazarov, D.J. (Muallif)