IRO Journals
Journal of Electrical Engineering and Automation

Autonomous Microgrid Management System with AI-Powered Load and Fault Prediction

Open Access
Published: 25 July, 2026
Pages: 222-232
  • Chellan P. , Chellan P.
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Dharani Daran M. , Dharani Daran M.
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Sivasubramani. G. , Sivasubramani. G.
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Vimaleshwaran S. , Vimaleshwaran S.
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Sathyamoorthi S. Sathyamoorthi S.
    Assistant Professor, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
    Assistant Professor, Department of Electrical and Electronics Engineering, NPR College of Engineering and Technology, Dindigul, India
view PDF
view PDF

How to Cite

P., Chellan, Dharani Daran M., Sivasubramani. G., Vimaleshwaran S., and Sathyamoorthi S. 2026. “Autonomous Microgrid Management System With AI-Powered Load and Fault Prediction”. Journal of Electrical Engineering and Automation 8 (3): 222-32. https://doi.org/10.36548/jeea.2026.3.005.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Microgrid System
Internet of Things (IoT)
Energy Monitoring
Load Forecasting
Fault Detection
Cloud Database
Smart Grid
Artificial Intelligence

Abstract

Intelligent monitoring and control of modern microgrids have become essential to increase the efficiency, reliability and fault tolerance of the microgrid. This research work proposes an autonomous microgrid management system with AI-powered load and fault prediction that combines renewable energy sources, IoT and cloud computing in one embedded system. The proposed system encompasses an ESP32 microcontroller that collects the values of voltage and current using sensors, calculates electrical parameters, and transfers data to the cloud database (Firebase) via Wi-Fi connection. A web dashboard is used to provide real-time monitoring of the system, while a machine learning algorithm is used to predict future load and detect abnormal states for proactive fault management. An automatic relay-based load control scheme is applied to protect the system from abnormal load faults. Experimental results have shown that the system operates stably with supply voltage in the range of 12.18-12.35 V, near-real-time cloud synchronization, and average prediction time of 145 ms. The proposed AI prediction model has achieved 95.3% accuracy, proving the feasibility of the proposed system design.

References

  1. Kumar, Munish, Ahmad Faiz Minai, Akhlaque A. Khan, and Satish Kumar. "IoT Based Energy Management System for Smart Grid." International Conference on Advances in Computing, Communication & Materials (ICACCM), IEEE, 2020, 121-125.
  2. Noori, Fateme, and Amir Noori Khezrabad. "AI Techniques for Smart Grid Load Forecasting: An Overview with Focus on External Factors." 14th Smart Grid Conference (SGC), IEEE, 2024, 1-9.
  3. Lee, Sang Hyeon, Tacklim Lee, Seunghwan Kim, and Sehyun Park. "Energy Consumption Prediction System Based on Deep Learning with Edge Computing." 2nd International Conference on Electronics Technology (ICET), IEEE, 2019, 473-477.
  4. Rahman Fahim, Shahriar, Subrata K. Sarker, S. M. Muyeen, Md Rafiqul Islam Sheikh, and Sajal K. Das. "Microgrid Fault Detection and Classification: Machine Learning Based Approach, Comparison, and Reviews." Energies 2020, vol. 13, no. 13, 3460.
  5. Su, Wenwei, and Yan Shi. "Distributed Energy Sharing Algorithm for Micro Grid energy System Based on Cloud Computing." IET Smart Cities 2024, vol. 6, no. 3, 225-236.
  6. Habbak, Hany, Mohamed Mahmoud, Khaled Metwally, Mostafa M. Fouda, and Mohamed I. Ibrahem. "Load Forecasting Techniques and Their Applications in Smart Grids." Energies 2023, vol. 16, no. 3, 1480.
  7. Bhavani, NP G., Ravi Kumar, Bhawani Sankar Panigrahi, Kishore Balasubramanian, B. Arunsundar, Zulkiflee Abdul-Samad, and Abha Singh. "Design and Implementation of IoT Integrated Monitoring and Control System of Renewable Energy in Smart Grid for Sustainable Computing Network." Sustainable computing: Informatics and systems 2022, vol. 35, 100769.
  8. Talaat, Mohamed, M. H. Elkholy, Adel Alblawi, and Taghreed Said. "Artificial Intelligence Applications for Microgrids Integration and Management of Hybrid Renewable Energy Sources." Artificial Intelligence Review 2023, vol. 56, no. 9, 10557-10611.
  9. Peter, Geno, Albert Alexander Stonier, Punit Gupta, Daniel Gavilanes, Manuel Masias Vergara, and Jong Lung sin. "Smart Fault Monitoring and Normalizing of a Power Distribution System Using IoT." Energies 2022, vol. 15, no. 21, 8206.
  10. Ali, Waleed, Abasin Ulasyar, Mussawir Ul Mehmood, Abraiz Khattak, Kashif Imran, Haris Sheh Zad, and Shibli Nisar. "Hierarchical Control of Microgrid Using IoT and Machine Learning Based Islanding Detection." IEEE Access 2021, vol. 9, 103019-103031.