Skip to content
naulon
Not checkedNot checked for notices yet.

Combating electricity fraud: Employing hybrid learning and computer vision for sustainable energy management

Jui-Sheng Chou, Nader Anwar Charaf, Dani Nugraha Limantono and 1 more

Energy Strategy Reviews · 2025

doi:10.1016/j.esr.2025.101798 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

Energy is the critical link between economic growth, social equity, and environmental sustainability. However, widespread electricity fraud poses a threat to the stability and integrity of the electricity market. Electricity fraud deliberately manipulates electricity consumption data, such as meter tampering and unauthorized bypassing, to reduce recorded usage. Traditional methods for detecting fraudulent activities often depend on extensive data preprocessing, such as outlier removal, which can introduce biases and reduce practical effectiveness. This paper presents an integrated approach that utilizes a comprehensive dataset, encompassing all customer energy consumption records. The study compares the classification performance of convolutional neural networks (CNNs), traditional machine learning models, and metaheuristic optimization algorithms in identifying fraudulent versus genuine users through detailed analysis and experimentation. The research employs data processing methods, including the Synthetic Minority Over-sampling Technique (SMOTE), to address data imbalance, as well as zero imputation and regression techniques to manage missing data. Additionally, the study explores hybrid and ensemble AI models that combine the best-performing algorithms to improve prediction accuracy. The performance of these models is rigorously evaluated using various performance metrics, with results showing that the machine learning model with hyperparameters optimized by a metaheuristic optimization algorithm achieved the highest prediction accuracy. This research aims to develop AI models for automatically detecting electricity fraud, helping utility companies minimize financial losses and ensure a more resilient and sustainable energy system.

Abstract licence: CC BY-NC-ND

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.