An Attention Guided Semi-Supervised Learning Mechanism to Detect Electricity Frauds in the Distribution Systems

Aslam, Zeeshan; Ahmed, Fahad; Almogren, Ahmad; Shafiq, Muhammad; Javaid, Nadeem

doi:10.1109/access.2020.3042636

Cited by 33 publications

(16 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…to predict abnormal patterns from electricity data. In [18], [19], there are various consumption behaviors of different users. The consumption behavior of each customer gives different results.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Hybrid Deep Learning Model for Detection of Non-Technical Losses to Secure Smart Grids

et al. 2021

Self Cite

View full text Add to dashboard Cite

For dealing with the electricity theft detection in the smart grids, this article introduces a hybrid deep learning model. The model tackles various issues such as class imbalance problem, curse of dimensionality and low theft detection rate of the existing models. The model integrates the benefits of both GoogLeNet and gated recurrent unit (GRU). The one dimensional electricity consumption (EC) data is fed into GRU to remember the periodic patterns of electricity consumption. Whereas, GoogLeNet model is leveraged to extract the latent features from the two dimensional weekly stacked EC data. Furthermore, the time least square generative adversarial network (TLSGAN) is proposed to solve the class imbalance problem. The TLSGAN uses unsupervised and supervised loss functions to generate fake theft samples, which have high resemblance with real world theft samples. The standard generative adversarial network only updates the weights of those points that are available at the wrong side of the decision boundary. Whereas, TLSGAN even modifies the weights of those points that are available at the correct side of decision boundary that prevent the model from vanishing gradient problem. Moreover, dropout and batch normalization layers are utilized to enhance model's convergence speed and generalization ability. The proposed model is compared with different state-of-the-art classifiers including multilayer perceptron (MLP), support vector machine, naive bayes, logistic regression, MLP-long short term memory network and wide and deep convolutional neural network. It outperforms all classifiers by achieving 96% and 97% precision-recall area under the curve and receiver operating characteristics area under the curve, respectively.INDEX TERMS Electricity theft detection, gated recurrent unit, GoogLeNet, non-technical losses, smart grids, SGCC.

show abstract

Section: Related Workmentioning

confidence: 99%

“…So, it is possible to generate theft samples from normal samples. In [18], [19], the authors use 1D-Wasserstein GAN and adaptive synthetic (ADASYN) to generate duplicated copies of the minority class. In [2], [3], [10], SMOTE and ROS are leveraged to solve the uneven distribution of samples.…”

Section: Related Workmentioning

confidence: 99%

A Robust Hybrid Deep Learning Model for Detection of Non-Technical Losses to Secure Smart Grids

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, data‐driven artificial intelligence (AI) methods have drawn the attention from researchers 24 . In Reference 12, the authors proposed a semi‐supervised learning mechanism to detect ET. Area under the curve (AUC), Matthews correlation coefficient, F1‐score, and precision‐recall curve are used for performance evaluation.…”

Section: Related Workmentioning

confidence: 99%

Big data analytics for identifying electricity theft using machine learning approaches in microgrids for smart communities

Arif

Javaid

Aldegheishem

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Electricity theft (ET) causes major revenue loss in power utilities. It reduces the quality of supply, raises production cost, causes legal consumers to pay the higher cost, and impacts the economy as a whole. In this article, we use the State Grid Corporation of China (SGCC) dataset, which contains electricity consumption data of 1035 days for two classes: normal and fraudulent. In this work, ET detection model is proposed that consists of four steps: interpolation, data balancing, feature extraction, and classification. First, missing values of the dataset are recovered using the interpolation method. Second, resampling technique is implemented. ET consumers are 9% in the SGCC dataset that make the model inefficient to correctly classify both classes (normal and theft). A hybrid resampling technique is proposed, named synthetic minority oversampling technique with near miss. Third, residual network extracts the latent features from the SGCC dataset. Fourth, three tree based classifiers, such as decision tree (DT), random forest (RF), and adaptive boosting (AdaBoost) are applied to train the encoded feature vectors for classification. Besides, search for good hyperparameters is a challenging task, which is usually done manually and takes a considerable amount of time. To resolve this problem, Bayesian optimizer is used to simplify the tuning process of DT, RF, and AdaBoost. Finally, the results indicate that RF outperforms DT and AdaBoost.

show abstract

“…Two-dimensional electricity data are taken as input in [21], and a kind of wide and deep CNN model is trained to identify the non-periodic electricity theft and periodic normal power consumption. In [22], the relational denoising autoencoder is implemented to derive features and their associations in the high-dimensional imbalanced data of users, which helps improve the performance for electricity theft detection by maintaining the presence of features' associations. As a kind of spatiotemporal deep learning approaches, the stacked autoencoder (SAE) outperforms conventional machine learning approaches on electricity theft detection, which is evaluated in an IEEE 123-bus test feeder in [23].…”

Section: Introductionmentioning

confidence: 99%

Electricity Theft Detection Based on Stacked Autoencoder and the Undersampling and Resampling Based Random Forest Algorithm

et al. 2021

View full text Add to dashboard Cite

Electricity theft has been a major concern to the secure operation of power systems and the interests of power companies. Due to the different methods and types of electricity theft behaviors, it is difficult to determine the suspicion levels of consumers in the research of electricity theft detection. An electricity theft detection method based on stacked autoencoder (SAE) and the undersampling and resampling based random forest (UaRe-RF) algorithm is proposed in this work to formulate appropriate strategies for the practical electricity theft detection requirements of the power company. In the proposed method, the supervised SAE is first trained to extract electricity consumption features that are more adaptable to the classification algorithm for electricity theft detection. Then, the UaRe-RF algorithm is used to establish the class-balanced subsets and determine the suspicion level of each electricity theft user. Finally, two cases of different datasets of electricity consumers are studied for demonstrating the effectiveness of the proposed method, and the results show that higher classification accuracy and more targeted detection strategies can be achieved through the proposed method.

show abstract

An Attention Guided Semi-Supervised Learning Mechanism to Detect Electricity Frauds in the Distribution Systems

Cited by 33 publications

References 43 publications

A Robust Hybrid Deep Learning Model for Detection of Non-Technical Losses to Secure Smart Grids

A Robust Hybrid Deep Learning Model for Detection of Non-Technical Losses to Secure Smart Grids

Big data analytics for identifying electricity theft using machine learning approaches in microgrids for smart communities

Electricity Theft Detection Based on Stacked Autoencoder and the Undersampling and Resampling Based Random Forest Algorithm

Contact Info

Product

Resources

About