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{195492,
        author = {E. Archana and Dr. B. Shankar Nayak and M. Sai Revanth and B. Kavya},
        title = {SMART GRID IRREGULARITY DETECTION IN ELECTRICAL POWER SYSTEMS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {435-440},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195492},
        abstract = {Smart grids are dealing with some tough challenges because household energy use can be pretty unpredictable appliances turning on and off at strange hours, and people using energy in different ways. Instead of just relying on consistent usage patterns, this tool keeps an eye on electricity usage in real-time, using K-Means clustering to identify unusual activities like power surges, leaks, or tampering. Unlike traditional monthly bills that often overlook these issues, this tool dives into the specifics for each device to catch problems quickly. If something seems off, users get alerts via SMS, and they can view the findings on a visual dashboard created with Streamlit. Reports are accessible anytime, and the breakdowns go deeper than just totals users can see details for individual appliances. Plus, updates happen every second. This method was tested with both simulated data and some actual small-scale data, and it showed impressive results in identifying issues. For power companies and consumers looking to manage energy flow better, reduce waste, or stay more engaged, this solution really shines with its hands-on approach.},
        keywords = {Smart Grid, Anomaly Detection, Unsupervised Learning, K-Means Clustering, Power Systems, Non-Technical Losses, Streamlit, Real-Time Monitoring.},
        month = {April},
        }