Intelligent Management of Photovoltaic-Diesel Microgrids with Battery Energy Storage

https://doi.org/10.58571/CNCA.AMCA.2025.045

Resumen: Este trabajo propone un sistema integrado de Machine Learning para la gestión inteligente de microrredes hibridas fotovoltaica-diésel con almacenamiento en baterías. El sistema combina una arquitectura de redes neuronales convolucionales con memoria a largo plazo para predicción de demanda, un clasificador de bosque aleatorio para identificación de estados operativos, y un optimizador por enjambre de partículas con configuración automática para despacho energético. Los resultados demuestran mejoras del 23.5% en costos operativos y 31.2% en reducción de emisiones CO2, validando la efectividad de la arquitectura secuencial integrada con actualización horaria para optimización de microrredes.

¿Cómo citar?

Arengas Acosta, J., Segundo-Ramírez, J. & Visairo-Cruz, N. (2025). Intelligent Management of Photovoltaic-Diesel Microgrids with Battery Energy Storage. Memorias del Congreso Nacional de Control Automático 2025, pp. 262-267. https://doi.org/10.58571/CNCA.AMCA.2025.045

Palabras clave

Machine learning, microgrids, renewable energy, optimization, neural networks, Random Forest, metaheuristic optimization, energy management, hybrid systems, battery storage.

• Ajayi, O., Mirjafari, M., Idowu, P., and Ullah, M. (2024). Explainable ai for fault detection and classification in microgrids. In 2024 IEEE Energy Conversion Congress and Exposition (ECCE), 1835–1840.
• Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.
• Bidram, A. and Davoudi, A. (2012). Hierarchical structure of microgrids control system. IEEE Transactions on Smart Grid, 3(4), 1963–1976.
• Chen, C., Duan, S., Cai, T., and Liu, B. (2018). Smart energy management system for optimal microgrid economic operation. IET Renewable Power Generation, 5(3), 258–267.
• Dobos, A. (2014). Pvwatts version 5 manual. Technical Report NREL/TP-6A20-62641, NREL.
• Garcia, M., Silva, R., Rodriguez, A., and Lopez, P. (2023). Random forest classification for microgrid operational state detection. IEEE Transactions on Power Systems, 38(4), 2891–2902.
• Guerrero, J., Vasquez, J., Matas, J., de Vicuña, L., and Castilla, M. (2011). Hierarchical control of droopcontrolled ac and dc microgrids. IEEE Transactions on Industrial Electronics, 58(1), 158–172.
• Hatziargyriou, N. (2014). Microgrids: Architectures and Control. Wiley-IEEE Press.
• Hirsch, A., Parag, Y., and Guerrero, J. (2018). Microgrids: A review of technologies, key drivers, and outstanding issues. Renewable and Sustainable Energy Reviews, 90, 402–411.
• Jing, W., Lai, C.,Wong, S., andWong, M. (2017). Batterysupercapacitor hybrid energy storage system in standalone dc microgrids. IET Renewable Power Generation, 11(4), 461–469.
• Kamireddy, R., Yasmeeena, B., Bhamidi, L., Avanthika, D., and Lella, V. (2025). Bi-lstm based electrical load prediction model for a microgrid community area of panama city. In 2025 Fourth International Conference on Power, Control and Computing Technologies (ICPC2T), 102–106.
• Kumar, A., Singh, B., and Shahani, D. (2019). Grid integration of renewable energy sources: Challenges and solutions. IEEE Access, 7, 142859–142870.
• Li, H., Wang, Z., Hong, T., and Parker, M. (2020). Characterizing patterns and variability of building electric load profiles. Applied Energy, 264, 114721.
• Liu, J., Yang, X., Zhang, K., and Li, W. (2023). Gru-based energy prediction and pso optimization for microgrid operation. Applied Energy, 342, 121234.
• Mahmoud, T., Dong, Z., and Ma, J. (2018). Advanced approach for optimal wind power generation prediction. Renewable Energy, 126, 254–269.
• Meng, L., Sanseverino, E., Luna, A., Dragicevic, T., Vasquez, J., and Guerrero, J. (2017). Microgrid supervisory controllers and energy management systems. Renewable and Sustainable Energy Reviews, 80, 1407–1425.
• Mohamed, F. and Koivo, H. (2010). System modelling and online optimal management of microgrid. International Journal of Electrical Power & Energy Systems, 32(5), 398–407.
• Olivares, D., Mehrizi-Sani, A., Etemadi, A., et al. (2014). Trends in microgrid control. IEEE Transactions on Smart Grid, 5(4), 1905–1919.
• Parhizi, S., Lotfi, H., Khodaei, A., and Bahramirad, S. (2015). State of the art in research on microgrids: A review. IEEE Access, 3, 890–925.
• Raza, M. and Khosravi, A. (2015). A review on artificial intelligence based load demand forecasting techniques. Renewable and Sustainable Energy Reviews, 50, 1352– 1372.
• Ross, M., Abbey, C., Bouffard, F., and Joos, G. (2018). Microgrid economic dispatch with energy storage systems. IEEE Transactions on Smart Grid, 9(4), 3039–3047.
• SEMARNAT (2020). Contribución determinada a nivel nacional: México. Secretaría de Medio Ambiente y Recursos Naturales. SENER (2023). Programa de desarrollo del sistema eléctrico nacional 2023-2037. Secretaría de Energía, México.
• Shi, H., Xu, M., and Li, R. (2018). Deep learning for household load forecasting. IEEE Transactions on Smart Grid, 9(5), 5271–5280.
• Tsikalakis, A. and Hatziargyriou, N. (2008). Centralized control for optimizing microgrids operation. IEEE Transactions on Energy Conversion, 23(1), 241–248.
• un, T., Ozansoy, C., and Zayegh, A. (2011). Recent developments in microgrids and example cases. Renewable and Sustainable Energy Reviews, 15(8), 4030–4041.
• Wang, K., Qi, X., and Liu, H. (2019). Photovoltaic power forecasting based lstm-convolutional network. Energy, 189, 116225.
• Wang, Y., Wang, S., and Wang, Z. (2024). An improved pso-based multi-objective optimization scheduling of microgrid considering environmental costs. In 2024 IEEE 13th Data Driven Control and Learning Systems Conference (DDCLS), 327–332.
• Zhang, L., Chen, Y.,Wang, H., and Liu, M. (2024). Hybrid lstm-svm approach for microgrid load forecasting and optimization. IEEE Transactions on Smart Grid, 15(2), 1456–1467.
• Zia, M., Elbouchikhi, E., and Benbouzid, M. (2018). Microgrids energy management systems: A critical review. Applied Energy, 222, 1033–1055.