• Home
  • Search
  • Detecting electricity theft in smart grids using optimized machine learning ensemble techniques and eXplainable AI
  • https://doi.org/10.1016/j.egyr.2025.09.019Copy DOI Icon

Detecting electricity theft in smart grids using optimized machine learning ensemble techniques and eXplainable AI

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Electricity theft remains a significant challenge for modern power systems causing major financial damage to utility providers. With increasing adoption of advanced metering infrastructure in smart grids, energy efficiency and real-time monitoring have improved but the vulnerability of smart meters to tampering and cyber manipulation introduces new threats. To address these concerns at scale, this study proposes a cloud-based machine learning framework for intelligent electricity theft detection in residential sectors. The cloud-based setup, utilizing a Google Colab environment, facilitates centralized data processing, streamlined deployment, and real-time decision support. This study systematically resolves several critical limitations in existing approaches. Firstly, it addresses the severe class imbalance in real-world datasets, which significantly underrepresent theft cases compared to honest consumption. The synthetic minority oversampling technique is used to equalize representation and enable fair learning. Second, recognizing that synthetic oversampling can introduce noise and class overlap, a post-balancing noise reduction mechanism is integrated to refine the dataset and eliminate ambiguous samples. Third, by combining the interpretability of Decision Trees (DT) and the robustness of Random Forests (RF), an ensemble model named DTRF is proposed to enhance variance control and generalization. To improve the predictive performance of DTRF, the Firefly Algorithm (FA) is used to smartly adjust the model’s settings based on the specific features of the dataset. The proposed models are tested on two publicly available real-world datasets, Pakistan Residential Electricity Consumption (PRECON) and State Grid Corporation of China (SGCC), showing consistent improvements over standard models in various measures. On the PRECON dataset, the DTRF model outperforms baseline models and achieves a 25.68% reduction in log loss, a 31.23% decrease in Hamming loss, a 3.52% improvement in Cohen’s Kappa (CK), and a 4.10% increase in Jaccard score. The proposed DTRF-FA model further achieves a 40.97% reduction in log loss, a 36.38% decrease in Hamming loss, a 2.71% improvement in CK, and a 3.17% increase in the Jaccard score relative to the DTRF model. On the SGCC dataset, the DTRF model outperforms baselines with a 33.34% drop in Hamming loss, a 3.86% increase in CK, a 3.70% rise in the Jaccard score, and a 1.92% gain in the F1-score. The DTRF-FA model achieves a 75.00% reduction in Hamming loss, a 5.63% gain in CK, a 5.82% rise in Jaccard score, a 2.95% improvement in F1-score, and a 5.39% increase in Matthews correlation coefficient over the DTRF baseline. These improvements affirm the models’ ability to balance sensitivity and specificity while maintaining low false positive and false negative rates. Finally, to promote interpretability and transparency essential for stakeholder trust and regulatory compliance, the framework integrates two powerful explainable artificial intelligence techniques. Local Interpretable Model-agnostic Explanations (LIME) is used to generate local, instance-level explanations of individual predictions, while SHapley Additive exPlanations (SHAP) provides a global view of feature importance using cooperative game theory. By combining LIME and SHAP, the framework helps practitioners understand models’ decisions in detail and as a whole ensuring that it is accurate, clear, adaptable, and suitable for use in the smart grid settings.

Similar Papers
  • PDF
  • Research Article
  • Citations26

RFE Based Feature Selection and KNNOR Based Data Balancing for Electricity Theft Detection Using BiLSTM-LogitBoost Stacking Ensemble Model

  • Jan 01, 2022
  • IEEE Access
  • Pamir +5
  • Conference Article
  • Citations10

DE-RUSBoost: An Efficient Electricity Theft Detection Scheme with Additive Communication Layer

  • Jun 01, 2020
  • Sana Mujeeb +4
  • Research Article
  • Citations24

Electricity theft detection for energy optimization using deep learning models

  • Aug 14, 2023
  • Energy Science & Engineering
  • Pamir +5
  • PDF
  • Research Article
  • Citations82

Towards Sustainable Energy Efficiency With Intelligent Electricity Theft Detection in Smart Grids Emphasising Enhanced Neural Networks

  • Jan 01, 2021
  • IEEE Access
  • Abdulaziz Aldegheishem +5
  • Research Article
  • Citations3

Using SHAP and LIME to Explain Machine Learning Models Predicting Comorbid Depression and Stroke From Daily Dietary Nutrient Intake in a US Population‐Based Study

  • Dec 30, 2025
  • Food Science & Nutrition
  • Hongwei Liu +4
  • PDF
  • Research Article
  • Citations60

A Combined Deep Learning and Ensemble Learning Methodology to Avoid Electricity Theft in Smart Grids

  • Oct 26, 2020
  • Energies
  • Zeeshan Aslam +4
  • PDF
  • Research Article
  • Citations28

A PLSTM, AlexNet and ESNN Based Ensemble Learning Model for Detecting Electricity Theft in Smart Grids

  • Jan 01, 2021
  • IEEE Access
  • Nadeem Javaid
  • Research Article
  • Citations89

Explainable artificial intelligence model for identifying COVID-19 gene biomarkers

  • Feb 01, 2023
  • Computers in Biology and Medicine
  • Fatma Hilal Yagin +6
  • PDF
  • Research Article
  • Citations21

Electricity Theft Detection With Automatic Labeling and Enhanced RUSBoost Classification Using Differential Evolution and Jaya Algorithm

  • Jan 01, 2021
  • IEEE Access
  • Sana Mujeeb +6
  • Research Article

Comparative Analysis of Explainable AI Frameworks (LIME and SHAP) in Loan Approval Systems

  • Dec 08, 2025
  • International Journal of Information Engineering and Electronic Business
  • Isaac Terngu Adom +3
  • Research Article
  • Citations14

Predictive Data Analytics for Electricity Fraud Detection Using Tuned CNN Ensembler in Smart Grid

  • Nov 21, 2022
  • Forecasting
  • Nasir Ayub +4
  • Research Article
  • Citations29

Deep learning-based electricity theft prediction in non-smart grid environments

  • Jul 26, 2024
  • Heliyon
  • Sheikh Muhammad Saqib +6
  • Research Article
  • Citations1

DYNAMIC GENERATIVE RESIDUAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR ELECTRICITY THEFT DETECTION

  • Dec 27, 2024
  • Turkish Journal of Computer and Mathematics Education (TURCOMAT)
  • Raghuvaran Ch +3
  • Conference Article

Analyzing the Role of LIME and SHAP in Explainable DoS Attack Detection for IoT Systems

  • Dec 10, 2025
  • Aditi Paul +3
  • Research Article
  • Citations31

An attention-based wide and deep CNN with dilated convolutions for detecting electricity theft considering imbalanced data

  • Jan 01, 2023
  • Electric Power Systems Research
  • Rui Xia +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.