article · Frontiers in Energy Research
Electricity theft causes substantial financial losses for power utilities globally. Traditional detection models frequently struggle with high-dimensional datasets and severe imbalances in electricity consumption records. To address these challenges, a hybrid machine learning approach combining a Multi-Layer Perceptron and Gated Recurrent Units was developed. The process involves preprocessing data from the Chinese National Grid Corporation and addressing class imbalance using a k-means Synthetic Minority Oversampling Technique. The hybrid architecture then analyses the purified consumption records. Model consistency was verified using three distinct training and testing data splits, with performance assessed via graphical analyses and statistical tests. The resulting framework demonstrated higher accuracy and operational efficiency than alternative baseline models, including Alexnet, standalone Gated Recurrent Units, Bidirectional Gated Recurrent Units, and standard Recurrent Neural Networks.
Electricity theft leads to significant revenue losses and operational challenges for power utilities worldwide. Improving automated detection helps network operators identify irregular and fraudulent usage patterns more reliably. By effectively handling highly skewed consumption data, machine learning solutions support smart grid resilience, helping utilities protect revenue and improve resource allocation across distribution networks.
This technology is relevant to power utilities, smart grid operators, and energy management software providers seeking to reduce non-technical losses. The system represents applied research tested on historical data from the Chinese National Grid Corporation. While it demonstrates strong comparative performance against standard algorithms, moving towards real-world deployment would require integration into live smart meter data streams and operational control centres.
AI-generated from the published abstract. Always read the original work before citing.
Nowadays, electricity theft is a major issue in many countries and poses a significant financial loss for global power utilities. Conventional Electricity Theft Detection (ETD) models face challenges such as the curse of dimensionality and highly imbalanced electricity consumption data distribution. To overcome these problems, a hybrid system Multi-Layer Perceptron (MLP) approach with Gated Recurrent Units (GRU) is proposed in this work. The proposed hybrid system is applied to analyze and solve electricity theft using data from the Chinese National Grid Corporation (CNGC). In the proposed hybrid system, first, preprocess the data; second, balance the data using the k-means Synthetic Minority Oversampling Technique (SMOTE) technique; third, apply the GTU model to the extracted purified data; fourth, apply the MLP model to the extracted purified data; and finally, evaluate the performance of the proposed system using different performance measures such as graphical analysis and a statistical test. To verify the consistency of our proposed hybrid system, we use three different ratios for training and testing the dataset. The outcomes show that the proposed hybrid system for ETD is highly accurate and efficient compared to the other models like Alexnet, GRU, Bidirectional Gated Recurrent Unit (BGRU) and Recurrent Neural Network (RNN).
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3389/fenrg.2024.1383090
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
