Machine-Learning-Augmented Sizing and Dispatch of PV-Grid-BESS Hybrid Microgrids to Achieve 100% Reliability at Lower LCOE: A Replicable Framework for Critical Facilities

References

[1] Alanazi, B. S. (2025). A comparative study of traditional statistical methods and machine learning techniques for improved predictive models. International Journal of Analysis and Applications, 23, 18. https://doi.org/10.28924/2291-8639-23-2025-18

[2] Aydin, E., & Iqbal, S. (2024, October). Reinforcement Learning-Based Optimization for Electric Vehicle Dispatch in Renewable Energy Integrated Power Systems. In 2024 IEEE Energy Conversion Congress and Exposition (ECCE) (pp. 1297-1304). IEEE.

[3] Babu, R. M., Islam, M. S., & Basher, E. (2025). Forecasting and optimization of a residential off-grid solar photovoltaic-battery energy storage system. Ecological Engineering & Environmental Technology (EEET), 26(9).

[4] Bakare, M. S., Abdulkarim, A., Shuaibu, A. N., & Muhamad, M. M. (2024). Predictive energy control for grid-connected industrial PV-battery systems using GEP-ANFIS. e-Prime-Advances in Electrical Engineering, Electronics and Energy, 9, 100647.

[5] Caballero, M. (2025). Integrated Optimization of Microgrid Design, Dispatch, and Technology Selection (Doctoral dissertation, University of Miami).

[6] Force, T. (2020). Resilience framework, methods, and metrics for the electricity sector. Technical Report PES-TR83, IEEE Power & Energy Society.

[7] Furqan, M., & Heleno, M. (2025). Cataloging US state policy patterns towards microgrid deployment. Energy Policy, 205, 114719.

[8] Giannopoulos, P. G., Malamas, V., & Dasaklis, T. K. (2024, December). Integration of Evolutionary Algorithms and Machine Learning techniques in routing-related problems: A review. In Proceedings of the 28th Pan-Hellenic Conference on Progress in Computing and Informatics (pp. 237-243).

[9] Ioannou, I., Javaid, S., Tan, Y., & Vassiliou, V. (2025). Autonomous Reinforcement Learning for Intelligent and Sustainable Autonomous Microgrid Energy Management. Electronics, 14(13), 2691.

[10] Kaur, R., Kumar, R., & Aggarwal, H. (2025). Systematic Review of Artificial Intelligence, Machine Learning, and Deep Learning in Machining Operations: Advancements, Challenges, and Future Directions. Archives of Computational Methods in Engineering, 1-54.

[11] Khalid, A., Stevenson, A., & Sarwat, A. I. (2021). Overview of technical specifications for grid-connected microgrid battery energy storage systems. IEEe Access, 9, 163554-163593.

[12] Marqusee, J., Becker, W., & Ericson, S. (2021). Resilience and economics of microgrids with PV, battery storage, and networked diesel generators. Advances in Applied Energy, 3, 100049.

[13] Matsuo, Y. (2022). Re-defining system LCOE: Costs and values of power sources. Energies, 15(18), 6845.

[14] McDonagh, S., O'Shea, R., Wall, D. M., Deane, J. P., & Murphy, J. D. (2018). Modelling of a power-to-gas system to predict the levelised cost of energy of an advanced renewable gaseous transport fuel. Applied Energy, 215, 444-456.

[15] Murshed, M., Chamana, M., Schmitt, K. E. K., Pol, S., Adeyanju, O., & Bayne, S. (2023). Sizing PV and BESS for grid-connected microgrid resilience: a data-driven hybrid optimization approach. Energies, 16(21), 7300.

[16] Naderi, Y., Hosseini, S. H., Savaghebi, M., Dahidah, M., & Guerrero, J. M. (2023). Multi-objective model predictive control for microgrid applications. International Journal of Electrical Power & Energy Systems, 154, 109441.

[17] Niksirat, E. (2025). Industry 4.0 Applications in Enhancing the Performance of Renewable Energy Systems: A Systematic Literature Review.

[18] Nwanevu, C., Oladipo, S. S., & Ajayi, A. O. (2024). Designing effective policy frameworks for the implementation of microgrids in developing countries: Opportunities, challenges and pathways to sustainable energy access. World Journal of Advanced Research and Reviews, 24(1), 1279–1294. https://doi.org/10.30574/wjarr.2024.24.1.3078

[19] Prakash, K., Ali, M., Siddique, M. N. I., Chand, A. A., Kumar, N. M., Dong, D., & Pota, H. R. (2022). A review of battery energy storage systems for ancillary services in distribution grids: Current status, challenges and future directions. Frontiers in Energy Research, 10, 971704.

[20] Rauf, A., Kassas, M., & Khalid, M. (2022). Data-driven optimal battery storage sizing for grid-connected hybrid distributed generations considering solar and wind uncertainty. Sustainability, 14(17), 11002.

[21] Sadikovic, A., & Novosel, D. (2025). Resilience Improvement Practices in the Power Industry. In Power Grid Resilience: Theory and Applications (pp. 523-554). Cham: Springer Nature Switzerland.

[22] Schwartz, L. C., Frick, N. M., Relf, G., Light, T., Schellenberg, J. A., & Sanstad, A. H. (2025). Clean Air as a Bonus for Achieving Energy-Related State Goals: A Review of Policies and Programs in 15 States.

[23] Ton, D. T., & Wang, W. P. (2015). A more resilient grid: The US department of energy joins with stakeholders in an R&D plan. IEEE Power and Energy Magazine, 13(3), 26-34.

@article{1714253,
      author = {Sean Tapiwa Kabera, Munashe Naphtali Mupa, Patronella Siphatisiwe Mtemeli, Peter Mangoro, Tazvitya Aubrey Chihota},
      title = {Machine-Learning-Augmented Sizing and Dispatch of PV-Grid-BESS Hybrid Microgrids to Achieve 100% Reliability at Lower LCOE: A Replicable Framework for Critical Facilities},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {8},
      pages = {1085-1094},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1714253.pdf},
      abstract = {The present paper presents a scalable machine-learning-enhanced model of sizing and dispatching photovoltaic (PV)-grid-battery energy storage system (BESS) hybrid microgrids with the objective of attaining 100 percent reliability and minimum levelized cost of energy (LCOE) of critical or essential facilities, including hospitals and data centers, in the United States. In an era when grid vulnerability has increased due to extreme weather, cyberattacks, and increasing demand, renewable integration is a sustainable solution, but intermittency remains a challenge. Conventional deterministic and stochastic approaches have tended to produce oversized systems, expensive systems, and inefficient reliability because of poor management of uncertainties, such as weather variability, tariffs, and outages. The given framework fills these gaps by expanding the previous reliability-cost optimization into a U.S.-oriented blueprint in line with the Department of Energy (DOE) resilience programs, such as Grace Resilience and Innovation Partnerships (GRIP). Single-diode PV equations, dynamics of kinetic BESS, net metering, and the stochastic Monte Carlo simulations of uncertainties are included in the system modeling. ML augmentation uses XGBoost surrogates to optimize multi-objective (sizing at LPSP=0) and real-time dispatch (PPO/TD3) using reward functions based on cost and reliability. The replicability will be guaranteed by step-by-step procedures that are adjusted to the regional policies, incentives (e.g., IRA tax credits), and software such as HOMER Pro, DER-CAM, and the information of NSRDB, OpenEI, and EIA. Case studies confirm the strategy: a Californian hospital is able to reduce its LCOE (15%, from 0.085 to 0.072/kWh) with 100 percent reliability, using a high solar-to-net metering; a data center in Texas does the same, cutting LCOE by 15 percent (0.092 to 0.078/kWh) during a hurricane risk. Sensitivity analysis verifies that it is strong against degradation and outages. There are also data dependencies and computation requirements, and the consequences are the implications of scalable deployments of DOE-aligned outage reduction in national costs. Real-world pilots and digital twins will be used in the future.},
      keywords = {Hybrid Microgrids, PV-Grid-BESS, Machine Learning, Reinforcement Learning, LCOE Optimization, Reliability Metrics, Grid Resilience, DOE GRIP, Net Metering, Critical Facilities},
      month = {February},
  }