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{183839,
        author = {Thallam Venkata Srikar and Chaithanya P and Eshwari A Madappa and Sukruth S},
        title = {SMART DETECTION OF ELECTRIC THEFT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {3439-3444},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183839},
        abstract = {Electricity theft presents a persistent challenge in modern electrical distribution systems, causing significant economic losses and undermining grid reliability. Conventional detection techniques often lack the capability to scale across vast networks and adapt to evolving theft mechanisms in real time. This paper proposes a cost-efficient hybrid solution that integrates embedded current sensing with a Graph Neural Network (GNN) for intelligent and contextual anomaly detection. The system is developed using ACS712 current sensors interfaced with an Arduino Uno, capturing real-time current data from household nodes. A GNN model is then trained on both real and synthetically generated datasets to classify power usage patterns as either legitimate or indicative of theft, utilizing the inherent topological structure of the network. The experimental results demonstrate that the proposed system achieves high accuracy, minimal inference latency, and reliable detection across varying load conditions. This approach shows strong potential for scalable deployment in smart grid infrastructures to enhance operational security and efficiency.},
        keywords = {Electricity theft detection, Graph Neural Networks (GNN), Smart grid, Embedded systems, Anomaly detection, ACS712 current sensor, Machine learning, Real-time monitoring, Power distribution network},
        month = {August},
        }