Skip to main navigation Skip to search Skip to main content

TRANS-DEEP: an optimized deep learning framework for electricity theft detection in smart grids

  • PMAS-Arid Agriculture University Rawalpindi
  • Prince Sultan University

Research output: Contribution to journal › Article › peer-review

1   Link opens in a new tab Citation (SciVal)
4 Downloads (Pure)

Abstract

Electricity theft significantly impacts power utilities, causing financial losses and compromising system reliability. Traditional detection methods, such as manual inspections and basic comparisons, lack scalability and accuracy when applied to large datasets. This article introduces TRANS-DEEP, an advanced methodology that integrates sophisticated techniques to effectively detect electricity theft and overcome these limitations. The proposed approach includes data collection and preprocessing, followed by Variational Autoencoder (VAE)-based anomaly detection to identify irregularities in consumption data. The Adaptive Synthetic Sampling (ADASYN) method is employed for data balancing to address class imbalance, complemented by Generative Adversarial Networks (GANs) for dataset enrichment. A Bidirectional Long Short-Term Memory Network (BiLSTM) is used for feature extraction, capturing sequential and temporal dependencies. Finally, a Transformer-based model leverages self-attention mechanisms for effective theft detection by focusing on the critical features identified by BiLSTM. TRANS-DEEP was trained and tested to evaluate its ability to enhance detection accuracy and robustness, outperforming existing computer-based methods. The experimental results demonstrate the superiority of the proposed methodology, achieving high accuracy rates of 94.66% for Smart Meter Datasets (SMD)-I, 96.34% for SMD-II, and 95.12% for SMD-III in detecting electricity theft.
Original languageEnglish
Article numbere3402
Number of pages26
JournalPeerJ Computer Science
Volume12
Early online date9 Feb 2026
DOIs
Publication statusPublished - 9 Feb 2026

Bibliographical note

Copyright © 2026 Mustafa et al. Distributed under Creative Commons CC-BY 4.0.

Data Access Statement

The code is available in the article Supplemental Files: https://peerj.com/articles/cs-3402/#supplemental-information.

The data is available at GitHub: https://github.com/henryRDlab/ ElectricityTheftDetection.

The data is available at Mendeley: https://data.mendeley.com/datasets/c3c7329tjj/3.

The data is available at Kaggle: https://www.kaggle.com/datasets/ahmedrady66/theft-
detection-scheme-in-smart-grids.

Funding

Prince Sultan University paid the Article Processing Charges (APC) of this publication.

Funders
Prince Sultan University

    UN SDGs

    This output contributes to the following UN Sustainable Development Goals (SDGs)

    1. SDG 7 - Affordable and Clean Energy
      SDG 7 Affordable and Clean Energy

    Keywords

    • Smart grids
    • Electricity theft
    • BiLSTM
    • Transformer model
    • Self-attention mechanism

    Fingerprint

    Dive into the research topics of 'TRANS-DEEP: an optimized deep learning framework for electricity theft detection in smart grids'. Together they form a unique fingerprint.

    Cite this