<![CDATA[Abstract—This research aims to detect energy abuse by utilizing clustering algorithms and Artificial Neural Networks (ANN). The dataset used consists of monthly energy consumption data from customers, which is processed using a combination of preprocessing techniques, clustering, and ANN models. The preprocessing step involves cleaning the data, normalization, and feature extraction to ensure the dataset is suitable for subsequent analysis. Clustering is carried out using the K-Means algorithm to group customers based on their consumption patterns, while the ANN model is used to classify and predict potential cases of energy abuse. The results indicate that the combination of the K-Means clustering algorithm and ANN provides a high level of accuracy in detecting suspicious energy consumption patterns. This approach effectively segments customers with similar consumption behaviors and identifies anomalies that may signify unauthorized energy use. The implementation of this methodology demonstrates its potential for energy providers to efficiently detect and reduce losses due to energy theft, ultimately contributing to improved energy management and distribution. The outcomes demonstrate the model’s scalability for broader deployment within energy distribution systems.]]>
Copyrights © 2025
