• P. ELAIYARAJA
• S.BABU

Electricity theft poses a major problem for utility companies, leading to financial losses, safety risks, and increased costs for legitimate consumers. With the deployment of smart grids and Advanced Metering Infrastructure (AMI), large volumes of consumption data are generated, offering a promising avenue for detecting such anomalies using machine learning techniques. This paper presents a novel approach to electricity theft detection in smart grids, leveraging Artificial Neural Networks (ANN) and Deep Neural Networks (DNN). The proposed methodology involves the collection of consumption data, followed by preprocessing techniques such as data imputation, normalization, and feature extraction in both time and frequency domains. These features are then fed into ANN and DNN models, which classify the data as either normal or indicative of theft. To address challenges like class imbalance and missing data, techniques like synthetic data generation and interpolation are applied. Experimental results show the effectiveness of the proposed method in accurately detecting electricity theft while minimizing false positives, providing a robust and scalable solution for real-time monitoring and theft prevention in smart grids.

Electricity theft, smart grids, machine learning, deep neural networks, artificial neural networks, anomaly detection, advanced metering infrastructure, data pre-processing, feature extraction, class imbalance, synthetic data generation, real-time monitoring

"A Review on Real-time Electricity Theft Detection in Smart Grids using ANN and DNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.c465-c472, November-2024, Available :http://www.jetir.org/papers/JETIR2411257.pdf

"A Review on Real-time Electricity Theft Detection in Smart Grids using ANN and DNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. ppc465-c472, November-2024, Available at : http://www.jetir.org/papers/JETIR2411257.pdf