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

Xia, Rui; Gao, Yunpeng; Yanqing, Zhu; Gu, Dexi; Wang, Jiangzhao

doi:10.1016/j.epsr.2022.108886

Cited by 17 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• SVM: Nonlinear SVM's training complexity mostly lies between O n ( ) 2 and O n ( ) 3 , where n is the number of instances. 67,68 74 • SSA: Time complexity of SSA is given as O tNd ( ), where t is the number of iterations, N is the number of salps (population size), and d is the problem dimensionality (number of variables).…”

Section: Ablation Results and Computational Complexitymentioning

confidence: 99%

“…Electricity makes a significant contribution to the lives of human beings, where nearly everyone in the world has access to it. With its vast usage throughout the world, some issues such as electricity loss happen that need to be tackled 1–3 . On the basis of the distribution system operators' opinion, the categorization of electricity loss can be done into technical loss (TL) and nontechnical loss (NTL) 4 .…”

Section: Introductionmentioning

confidence: 99%

“…With its vast usage throughout the world, some issues such as electricity loss happen that need to be tackled. [1][2][3] On the basis of the distribution system operators' opinion, the categorization of electricity loss can be done into technical loss (TL) and nontechnical loss (NTL). 4 TL is a type of electricity loss that takes place within the power distribution network due to heating and burning up of the hardware devices involved in electricity transfer, such as electric transformers, cables, conductors, and other equipment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Electricity theft detection for energy optimization using deep learning models

Pamir,

Javaid,

Javed

et al. 2023

Energy Science & Engineering

View full text Add to dashboard Cite

The rapid increase in nontechnical loss (NTL) has become a principal concern for distribution system operators (DSOs) over the years. Electricity theft makes up a major part of NTL. It causes losses for the DSOs and also deteriorates the quality of electricity. The introduction of advanced metering infrastructure along with the upgradation of the traditional grids to the smart grids (SGs) has helped the electric utilities to collect the electricity consumption (EC) readings of consumers, which further empowers the machine learning (ML) algorithms to be exploited for efficient electricity theft detection (ETD). However, there are still some shortcomings, such as class imbalance, curse of dimensionality, and bypassing the automated tuning of hyperparameters in the existing ML‐based theft classification schemes that limit their performances. Therefore, it is essential to develop a novel approach to deal with these problems and efficiently detect electricity theft in SGs. Using the salp swarm algorithm (SSA), gate convolutional autoencoder (GCAE), and cost‐sensitive learning and long short‐term memory (CSLSTM), an effective ETD model named SSA–GCAE–CSLSTM is proposed in this work. Furthermore, a hybrid GCAE model is developed via the combination of gated recurrent unit and convolutional autoencoder. The proposed model comprises five submodules: (1) data preparation, (2) data balancing, (3) dimensionality reduction, (4) hyperparameters' optimization, and (5) electricity theft classification. The real‐time EC data provided by the state grid corporation of China are used for performance evaluations via extensive simulations. The proposed model is compared with two basic models, CSLSTM and GCAE–CSLSTM, along with seven benchmarks, support vector machine, decision tree, extra trees, random forest, adaptive boosting, extreme gradient boosting, and convolutional neural network. The results exhibit that SSA–GCAE–CSLSTM yields 99.45% precision, 95.93% F1 score, 92.25% accuracy, and 71.13% area under the receiver operating characteristic curve score, and surpasses the other models in terms of ETD.

show abstract

Section: Ablation Results and Computational Complexitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Electricity theft detection for energy optimization using deep learning models

Pamir,

Javaid,

Javed

et al. 2023

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…The evaluation metrics showed 94.53% and 0.9513 for accuracy and AUC, respectively. Sravan and Dipu in reference [18] also followed the class balancing approach. The authors implemented ensemble techniques to detect electricity theft using a dataset of 5000 customers.…”

Section: Literature Reviewmentioning

confidence: 99%

Exploiting machine learning to tackle peculiar consumption of electricity in power grids: A step towards building green smart cities

Ali,

Khan,

Javaid

et al. 2024

IET Generation Trans & Dist

View full text Add to dashboard Cite

The increasing demand for electricity in daily life highlights the need for Smart Cities (SC) to use energy efficiently. Both technical and Non‐Technical Losses (NTL), particularly those resulting from electricity theft, present powerful obstacles; NTL alone can reach billions of dollars. Although Machine Learning (ML) based approaches for NTL detection have been embraced by numerous utilities, there is still a lack of thorough analysis of these methods. Limited research exists on NTL identification evaluation criteria and unbalanced data management in the context of SC. This research compares ML algorithms and data balancing methods to optimize electricity consumption detection. The given research applied the 15 ML techniques of Logistic regression, Bernoulli naive Bayes, Gaussian naive Bayes, K‐Nearest Neighbour, perceptron, passive‐aggressive classifier, quadratic discriminant analysis, SGD classifier, ridge classifier, linear discriminant analysis, decision tree, nearest centroid classifier, multi‐nomial naive Bayes, complement naive Bayes and dummy classifier. While SMOTE, AdaSyn, NRAS, and CCR are considered for data balancing. AUC, F1‐score, and seven relevant performance metrics were used for comparison. We have also implemented SHapely Additive exPlanations (SHAP) for feature importance and model interpretation. Results show varying classifier performance with different balancing methods, emphasizing data preprocessing's role in NTL detection for smart grid security.

show abstract

“…Northeast group LLC reported that worldwide, $96 billion are lost due to electricity theft yearly (Appiah et al, 2023). These unfortunate losses in revenue necessitate the need for efficient detection and confirmation techniques (Delgado-Gomes et al, 2015;Xu et al, 2023;Zhao et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Detection and confirmation of electricity thefts in Advanced Metering Infrastructure by Long Short-Term Memory and fuzzy inference system models

Otuoze,

Mustafa,

Sultana

et al. 2024

Nig. J. Technol. Dev.

View full text Add to dashboard Cite

The successful implementation of Smart Grids heavily relies on energy efficiency, particularly through the Advanced Metering Infrastructure (AMI) and Smart Electricity Meters (SEM). However, cyber-attacks pose a threat to SEM, with electricity theft being a primary motivation. Despite the valuable data provided by SEM for analytical purposes, existing methods to identify theft involve cumbersome and costly on-site inspections. This research proposes an electricity theft detection model using the Long Short-Term Memory (LSTM) network. The model employs a collective anomaly approach, defining prediction errors through a threshold and forecast horizon. Suspicious consumption profiles are analysed, and a fuzzy inference system (FIS) implemented in MATLAB 2021b is used to model security risks based on these profiles. The study utilizes energy consumption data from four diverse consumer profiles (consumers 1, 2, 3, and 4) to develop consumer-specific LSTM models for detection and an FIS model for confirmation. Tampered consumer data is identified and confirmed based on selected AMI parameters. While all consumers exhibit suspicious profiles at times, only consumers 2 and 3 are confirmed as engaging in electricity theft. This research provides a robust approach to detecting and verifying fraudulent consumption profiles within the context of AMI, offering a more reliable dimension to theft detection and confirmation.

show abstract

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

Cited by 17 publications

References 28 publications

Electricity theft detection for energy optimization using deep learning models

Electricity theft detection for energy optimization using deep learning models

Exploiting machine learning to tackle peculiar consumption of electricity in power grids: A step towards building green smart cities

Detection and confirmation of electricity thefts in Advanced Metering Infrastructure by Long Short-Term Memory and fuzzy inference system models

Contact Info

Product

Resources

About