Non-Technical Loss Detection Using Deep Reinforcement Learning for Feature Cost Efficiency and Imbalanced Dataset

Lee, Ji-Young; Sun, Young Ghyu; Sim, Isaac; Kim, Soo Hyun; Kim, Dong In; Kim, Jin Young

doi:10.1109/access.2022.3156948

Cited by 16 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accuracy, precision, area under the receiver operating characteristic curve (AUC) score, F 1 score, and recall are the performance metrics utilized in this paper to assess the performance of the proposed model 19 . These measures are the ones that are most frequently used in the ETD literature 46–49 . To calculate the aforementioned metrics, we need to calculate the confusion matrix.…”

Section: Discussion Of Simulation Resultsmentioning

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

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: Discussion Of Simulation Resultsmentioning

confidence: 99%

“…19 These measures are the ones that are most frequently used in the ETD literature. [46][47][48][49] To calculate the aforementioned metrics, we need to calculate the confusion matrix. Confusion matrix consists of four elements: false positives (FP), true positives (TP), false negatives (FN), and true negatives (TN).…”

Section: Performance Evaluation Measuresmentioning

confidence: 99%

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 authors highlight the issue of non‐technical loss (NTL) in the electricity grid system in their research paper [38], emphasizing the threat it poses to sustainability and stability. The proposed approach utilizing deep reinforcement learning (DRL) addresses the challenge of imbalanced electricity usage datasets and eliminates the need for extensive pre‐processing or dataset balancing.…”

Section: Literature Reviewmentioning

confidence: 99%

A novel deep learning technique to detect electricity theft in smart grids using AlexNet

Khan,

Shahid,

Alam

et al. 2024

IET Renewable Power Gen

View full text Add to dashboard Cite

Electricity theft (ET), which endangers public safety, interferes with the regular operation of grid infrastructure, and increases revenue losses, is a significant issue for power companies. To find ET, numerous machine learning, deep learning, and mathematically based algorithms have been published in the literature. However, these models do not yield the greatest results due to issues like the dimensionality curse, class imbalance, inappropriate hyper‐parameter tuning of machine learning, deep learning models etc. A hybrid DL model is presented for effectively detecting electricity thieves in smart grids while considering the abovementioned concerns. Pre‐processing techniques are first employed to clean up the data from the smart meters, and then the feature extraction technique, AlexNet is used to address the curse of dimensionality. An actual dataset of Chinese smart meters is used in simulations to assess the efficacy of the suggested approach. To conduct a comparative analysis, various benchmark models are implemented as well. This proposed model achieves accuracy, precision, recall, and F1‐score, up to 86%, 89%, 86%, and 84%, respectively.

show abstract

“…For effective NTL identification, the authors of [24] also employ a combined DL-boosting model. The authors of [27] introduce a DRL-based NTL detection method is applied to use partial input features for classification. 1D-CNN is applied as the neural network structure to improve the detection performance of time-series data.…”

Section: )Etd For Smart Gridmentioning

confidence: 99%

A Novel Deep Learning Model for Privacy based Blockchain with Electricity Theft Detection in Smart Grid

Johncy¹,

Shaji²,

M,A,Sarijari³

2023

Preprint

View full text Add to dashboard Cite

A lot of researches are being done in energy management system pertaining to intrusion detection to protect data privacy and a blockchain-based energy framework for smart-grids to detect both current and future cyberattacks. In these methods, learning-based ensemble models can assist in the identification of sophisticated malicious events while still preserving data privacy. In order to provide security, this paper proposes a privacy-based blockchain with distributed decentralized intrusion identification and electricity theft identification in smart-grids. The privacy based blockchain method is developed using BLS Short signature and hash functions. The intrusion detection method is employed by a hybrid framework leveraging Siamese Bi-LSTM for semantically discriminating malicious and authentic behaviors. In order to address the issue of class imbalance, we have used an RNN-GAN for the identification of electricity fraud. The RNN-GAN generates fake/synthesized theft samples that are very similar to actual theft instances using both supervised and unsupervised loss functions. RNN-GAN, on the other hand, even adjusts the weights of the points that are present on the accurate side of the decision boundary and keep the model from experiencing vanishing gradient problems. Additionally, batch normalization and dropout layers are used to improve the model's generalizability and speed of convergence. Our models' performance has reached great accuracy and a low error rate. Additionally, the statistical analysis demonstrates the effectiveness of the put-forth techniques.

show abstract

Non-Technical Loss Detection Using Deep Reinforcement Learning for Feature Cost Efficiency and Imbalanced Dataset

Abstract: Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.

Cited by 16 publications

References 25 publications

Electricity theft detection for energy optimization using deep learning models

Electricity theft detection for energy optimization using deep learning models

A novel deep learning technique to detect electricity theft in smart grids using AlexNet

A Novel Deep Learning Model for Privacy based Blockchain with Electricity Theft Detection in Smart Grid

Contact Info

Product

Resources

About