Abstract

Electricity theft presents a significant challenge to the power industry. This paper demonstrates an adaptive deep framework integrating dimensionality reduction, graph modeling, attention mechanisms, and dynamic feature refinement for improving theft detection. Principal Component Analysis squeezes consumption data while an Autoencoder extracts latent representations and denoises the input. A Gated Graph Convolutional Neural Network uses k-Nearest Neighbors to model local relationships, while Transformers capture long range global dependencies. Neural Ordinary Differential Equations then refine features over continuous time, improving adaptability to complex patterns. The framework achieves 94.01% accuracy with stratified 5-fold cross validation. However, class imbalance challenges the minority class detection, where synthetic data generation approaches aid in alleviating the disparity. The model has the scalable potential to advance the current energy management systems. Future work includes integrating Explainable AI techniques and real-time visibility to ensure proper and efficient classifications in electricity theft detection.

Department(s)

Engineering Management and Systems Engineering

Second Department

Electrical and Computer Engineering

Publication Status

Open Access

Keywords and Phrases

Complex Adaptive Systems; Deep Learning; Electricity Theft Detection; Power Systems; Smart Grid Analytics

International Standard Serial Number (ISSN)

1877-0509

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Elsevier, All rights reserved.

Publication Date

01 Jan 2025

Download

Full Text Link

Share

 
COinS