Autors: Stanchev, P. A., Hinova, I. S.
Title: Optimization of Energy Consumption in Industrial Enterprises Through an AI-Based Microgrid Management Strategy
Keywords: Battery Energy Management, Forecasting, Microgrid, Optimization, Reinforcement Learning

Abstract: In this study, an intelligent microgrid management strategy with local production from photovoltaic panels and a battery, applicable to small and medium-sized enterprises (SMEs), is developed and evaluated. Through a simulation environment built on real data on consumption, production, and market price of electricity, two Reinforcement Learning (RL) models are trained and compared: Deep Q-Network (DQN) and Proximal Policy Optimization (PPO). The system includes predictive modules for PV, Load, and price, as well as dynamic battery behavior with capacity and charging mode constraints. The RL agent makes decisions to charge, discharge, or idle, to minimize costs and increase the use of locally produced energy.

References

  1. E. Kuznetsova, Y.-F. Li, C. Ruiz, E. Zio, G. Ault, and K. Bell, "Reinforcement learning for microgrid energy management, " Energy, vol. 59, pp. 133-146, Jul. 2013, doi: 10.1016/j.energy.2013.05.060.
  2. S. Upadhyay, I. Ahmed, and L. Mihet-Popa, "Energy management system for an industrial microgrid using Optimization Algorithms-Based Reinforcement Learning Technique, " Energies, vol. 17, no. 16, p. 3898, Aug. 2024, doi: 10.3390/en17163898.
  3. K. H. Ali, "Efficient use of PV in a Microgrid using Reinforcement Learning, " Quaid-e-Awam University Research Journal of Engineering Science & Technology, vol. 21, no. 1, pp. 105-112, Jun. 2023, doi: 10.52584/qrj.2101.13.
  4. H. Shuai, X. Ai, J. Fang, W. Yao, and J. Wen, "Double deep QLearning based Real-Time Optimization Strategy for microgrids, " arXiv (Cornell University), Jan. 2021, doi: 10.48550/arxiv.2107.12545.
  5. L. Tightiz and J. Yoo, "A novel deep reinforcement learning based business model arrangement for Korean net-zero residential micro-grid considering whole stakeholders' interests, " ISA Transactions, vol. 137, pp. 471-491, Dec. 2022, doi: 10.1016/j.isatra.2022.12.008.
  6. S. Chen, J. Liu, Z. Cui, Z. Chen, H. Wang, and W. Xiao, "A deep reinforcement learning approach for microgrid energy transmission dispatching, " Applied Sciences, vol. 14, no. 9, p. 3682, Apr. 2024, doi: 10.3390/app14093682.
  7. B. She, F. Li, H. Cui, J. Zhang, and R. Bo, "Fusion of Model-free Reinforcement Learning with Microgrid Control: Review and Vision, " arXiv (Cornell University), Jan. 2022, doi: 10.48550/arxiv.2206.11398.
  8. M. Cauz, A. Bolland, B. Miftari, L. Perret, N. Wyrsch, and C. Ballif, "Reinforcement learning for joint design and control of Battery-PV Systems, " 34th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems (ECOS 2021), pp. 3131-3142, Jan. 2023, doi: 10.52202/069564-0281.
  9. D. J. B. Harrold, J. Cao, and Z. Fan, "Renewable energy integration and microgrid energy trading using multi-agent deep reinforcement learning, " Applied Energy, vol. 318, p. 119151, May 2022, doi: 10.1016/j.apenergy.2022.119151.
  10. R. Subramanya, S. A. Sierla, and V. Vyatkin, "Exploiting battery Storages with Reinforcement Learning: A review for energy professionals, " IEEE Access, vol. 10, pp. 54484-54506, Jan. 2022, doi: 10.1109/access.2022.3176446.

Issue

2025 10th International Conference on Energy Efficiency and Agricultural Engineering, EE and AE 2025 - Conference Proceedings, 2026, Albania, https://doi.org/10.1109/EEAE65901.2025.11273476

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus