Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203927,
        author = {S.E.Daniela and S.Ananthi and K.S.Lincy and P.S.Maheswari and J. Kavitha},
        title = {Edge AI-Driven Predictive Maintenance Framework for Smart Electrical Grids Using IoT Sensor Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {1251-1255},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203927},
        abstract = {This paper presents a power-systems-centric predictive maintenance framework for smart electrical grid infrastructure that integrates IoT multi-modal sensor measurements with edge AI inference. Grounded in classical electrical fault theory — including symmetrical component analysis, transformer equivalent circuit modelling, and IEC protection relay standards — the framework employs real-time monitoring of current, voltage, temperature, vibration, and power quality parameters across three voltage levels (132 kV, 33 kV, 11 kV). A lightweight LSTM-CNN model quantized via TensorFlow Lite is deployed on edge nodes at substation level, achieving 97.3% fault detection accuracy with a latency of 11.4 ms. Federated Averaging with differential privacy enables distributed model updates without exposing raw grid telemetry. Validation on the EPRI Smart Grid Dataset demonstrates 97.1% bandwidth reduction versus cloud-only approaches and full offline operational capability. The proposed framework bridges IEC 61850 communication standards, classical power system protection, and modern edge intelligence to deliver practical, standards-compliant predictive maintenance for next-generation smart grids.},
        keywords = {Smart grid protection; transformer monitoring; symmetrical components; predictive maintenance; IEC 61850; edge computing; IoT sensors; federated learning; fault detection.},
        month = {June},
        }