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{207128,
        author = {Mrs. Renjini E Nambiar and Mrs. Gayathri R and Mr. Kirit M Hothi and Mr. P. Balaji and Mr. Minnakanti Ajay Babu},
        title = {A Comprehensive Review of Edge-AI Frameworks for Predictive Fault Analysis in Smart Microgrids},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {4568-4570},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207128},
        abstract = {The integration of Internet of Things (IoT) devices in smart microgrids has generated massive amounts of telemetry data, making real-time fault detection a critical challenge. While cloud-based Artificial Intelligence (AI) has traditionally handled this analysis, its reliance on continuous high-bandwidth communication introduces latency, security risks, and operational bottlenecks. This paper presents a comprehensive review of the recent shift toward Edge-AI architectures in smart microgrids. By surveying contemporary literature, this review examines the core hardware components, lightweight machine learning algorithms, and communication protocols currently enabling localized predictive maintenance. Furthermore, a comparative analysis of recent methodologies is provided, highlighting the trade-offs between model accuracy and computational overhead. Finally, the paper identifies open challenges, such as data privacy and hardware constraints, and outlines future research directions for autonomous energy grids.},
        keywords = {Edge-AI, Smart Microgrid, Predictive Maintenance, Internet of Things (IoT), TinyML, Federated Learning.},
        month = {July},
        }