Filters








544 Hits in 6.5 sec

Electricity Theft Detection in Power Grids with Deep Learning and Random Forests

Shuan Li, Yinghua Han, Xu Yao, Song Yingchen, Jinkuan Wang, Qiang Zhao
2019 Journal of Electrical and Computer Engineering  
automatic electricity theft detection is presented in this paper.  ...  As one of the major factors of the nontechnical losses (NTLs) in distribution networks, the electricity theft causes significant harm to power grids, which influences power supply quality and reduces operating  ...  In [23] , a wide and deep convolutional neural network (CNN) model was developed and applied to analyse the electricity theft in smart grids.  ... 
doi:10.1155/2019/4136874 fatcat:c3v7lyxgs5h4jbkf5pbcxcxtva

An Ensemble Deep Convolutional Neural Network Model for Electricity Theft Detection in Smart Grids [article]

Hossein Mohammadi Rouzbahani, Hadis Karimipour, Lei Lei
2021 arXiv   pre-print
Electricity Theft Detection (EDT) algorithms are typically used for such purpose since this Non-Technical Loss (NTL) may lead to significant challenges in the power system.  ...  As the first layer of the model, a random under bagging technique is applied to deal with the imbalance data, and then Deep Convolutional Neural Networks (DCNN) are utilized on each subset.  ...  [22] proposed a Decision Tree and SVM-Based method to detect and locate real-time electricity theft in smart grids. Random forest is another method that has been conducted in [23] .  ... 
arXiv:2102.06039v1 fatcat:76tin3xdi5fdnm6rkr3wmy4akq

EnsembleNTLDetect: An Intelligent Framework for Electricity Theft Detection in Smart Grid [article]

Yogesh Kulkarni, Sayf Hussain Z, Krithi Ramamritham, Nivethitha Somu
2021 arXiv   pre-print
In this paper, we present EnsembleNTLDetect, a robust and scalable electricity theft detection framework that employs a set of efficient data pre-processing techniques and machine learning models to accurately  ...  over the state-of-the-art electricity theft detection models in terms of various quality metrics.  ...  with Random Forest [46] , and XGBoost [47] classifiers as base learners were designed for accurate classification of genuine consumers and electricity thieves with high detection rates and less false  ... 
arXiv:2110.04502v1 fatcat:2ar2ergmxndmzligywy4s5w4yu

Detection of Non-Technical Losses using SOSTLink and Bidirectional Gated Recurrent Unit to Secure Smart Meters

Hira Gul, Nadeem Javaid, Ibrar Ullah, Ali Mustafa Qamar, Muhammad Khalil Afzal, Gyanendra Prasad Joshi
2020 Applied Sciences  
The energy demand leads to increase in electricity theft (ET) in distribution side.  ...  Fluctuation in energy consumption patterns indicates electricity theft. Utilities bear losses of millions of dollar every year.  ...  Sigmoid activation function is used in LR, with values ranging from 0 to 1. Random Forest The building block of Random Forest (RF) is multiple DT.  ... 
doi:10.3390/app10093151 fatcat:5l6j6zmnave63kq4mf4kkovtre

Energy Theft Detection in an Edge Data Center Using Deep Learning

Guixue Cheng, Zhemin Zhang, Qilin Li, Yun Li, Wenxing Jin, Junming Huang
2021 Mathematical Problems in Engineering  
To better realize the energy theft detection function at the edge, we proposed an energy theft detection method based on the power consumption information acquisition system of power enterprises.  ...  In the edge data center, the random forest (RF) algorithm is used to classify the extracted features.  ...  At present, the most commonly used method is combined with smart grid detection.  ... 
doi:10.1155/2021/9938475 fatcat:y5zgdheasbg4xle6y6x54mfuru

Multi-Scale DenseNet-Based Electricity Theft Detection [article]

Bo Li, Kele Xu, Xiaoyan Cui, Yiheng Wang, Xinbo Ai, Yanbo Wang
2018 arXiv   pre-print
Timely identification of the electricity theft in the power system is crucial for the safety and availability of the system.  ...  Electricity theft detection issue has drawn lots of attention during last decades.  ...  the electricity theft detection.  ... 
arXiv:1805.09591v1 fatcat:u2qnq7qggffefbf5rkcjf33mh4

A Systematic Review on Supervised Learning Techniques in Electricity Theft Detection

Sohrab Alam, Electrical Engineering Department, University of Engineering and Technology, Peshawar, Pakistan, Majid Ashraf, Salman Alam, Electrical Engineering Department, University of Engineering and Technology, Peshawar, Pakistan, Electrical Engineering Department, University of Engineering and Technology, Peshawar, Pakistan
2022 International Journal of Engineering Works  
The primary raw data suffers from an ununiform distribution of one class over the other class in the case of machine learning(ML) and Deep learning(DL).  ...  In smart grids, the term non-technical losses impose challenges to perform classification, optimization, data analytics, and regression analysis in almost all areas of realworld research.  ...  The latter one is based on Machine learning and deep learning, which draw the usage pattern based on the smart meter data to detect ET.  ... 
doi:10.34259/ijew.22.9022227 fatcat:qmdfy2aolvemtiybetisutabzq

Detection of Electricity Theft Behavior Based on Improved Synthetic Minority Oversampling Technique and Random Forest Classifier

Zhengwei Qu, Hongwen Li, Yunjing Wang, Jiaxi Zhang, Ahmed Abu-Siada, Yunxiao Yao
2020 Energies  
To improve the auditing efficiency of grid enterprises, a new electricity theft detection method based on improved synthetic minority oversampling technique (SMOTE) and improve random forest (RF) method  ...  Effective detection of electricity theft is essential to maintain power system reliability.  ...  In [17] , in order to detect and localize the occurrence of theft in grid-tied microgrids, A Stochastic Petri Net (SPN) with a low sampling rate was used to first detect the random occurrence of theft  ... 
doi:10.3390/en13082039 fatcat:uxt3jhuszjdoblguce5hmmpxgq

Artificial Intelligence Techniques in Smart Grid: A Survey

Olufemi A. Omitaomu, Haoran Niu
2021 Smart Cities  
This survey presents a structured review of the existing research into some common AI techniques applied to load forecasting, power grid stability assessment, faults detection, and security problems in  ...  the smart grid and power systems.  ...  [155] demonstrated a novel hybrid CNN-random forest model for automatic electricity theft detection, which significantly influences power supply quality and operating profits.  ... 
doi:10.3390/smartcities4020029 doaj:85074e6b64e546c8b5b61351aad66daa fatcat:2n46ot2yeveuxitvrfce6drne4

A Combined Deep Learning and Ensemble Learning Methodology to Avoid Electricity Theft in Smart Grids

Zeeshan Aslam, Nadeem Javaid, Ashfaq Ahmad, Abrar Ahmed, Sardar Muhammad Gulfam
2020 Energies  
In this regard, LSTM–UNet–Adaboost combines the advantages of deep learning (LSTM-UNet) along with ensemble learning (Adaboost) for ETD.  ...  Electricity is widely used around 80% of the world. Electricity theft has dangerous effects on utilities in terms of power efficiency and costs billions of dollars per annum.  ...  • To increase the model's theft detection performance and stability, deep learning LSTM and UNet are combined with an ensemble learning Adaboost.  ... 
doi:10.3390/en13215599 fatcat:iajo64yt4fhfjcvw2vcthydfoe

Electricity Theft Detection in Smart Grid Systems: A CNN-LSTM Based Approach

Md. Nazmul Hasan, Rafia Nishat Toma, Abdullah-Al Nahid, M M Manjurul Islam, Jong-Myon Kim
2019 Energies  
Utilizing this data, machine learning and deep learning techniques can accurately identify electricity theft users.  ...  In this paper, an electricity theft detection system is proposed based on a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) architecture.  ...  A wide and deep CNN structure was proposed in [7] to detect electricity theft in smart grid environments. Hybrid deep learning techniques have been utilized in recent times for load forecasting.  ... 
doi:10.3390/en12173310 fatcat:wgshofbvwfgrbebyrauwp57lsa

Application of Machine Learning Algorithm in Managing Deviant Consumer Behaviors and Enhancing Public Service

Shantanu Dubey, Prashant Salwan, Nitin Kumar Agarwal
2022 Journal of Global Information Management  
The key learning from this paper is that even if data is noisy, it is possible to create a Machine Learning Model to detect NTL with 80 percentage plus accuracy.  ...  NTLs affect the operations of power systems by overloading lines and transformers, resulting in voltage imbalances and, thereby, impacting services.  ...  In our study /experiment, we implement Random Forest with Principal component analysis (PCA) and Neural Network MLbased theft detection model.  ... 
doi:10.4018/jgim.292064 fatcat:gx4ycsedl5gurdmevx2n74fszu

A Novel Method CNN-LSTM Ensembler based on Black Widow and Blue Monkey Optimizer for Electricity Theft Detection

Abdulwahab Ali Almazroi, Nasir Ayub
2021 IEEE Access  
CONCLUSION AND FUTUREWORK In this work, we have applied novel optimization techniques BMO and BWO to the deep learning model CNN embedded LSTM (CNN-LSTM) for electricity theft detection.  ...  In [21] , author used Light GBM, XGBoost, and Cat Boost Learning (CBL) to detect NTL. The concept of smart grids heralds a new age of detecting energy theft.  ...  In the future, we will apply more novel optimization methods, hybrid ML, and deep learning techniques to handle a huge amount of data for classification/detection.  ... 
doi:10.1109/access.2021.3119575 fatcat:smo5uucthrhrfpgujkazwtlvcm

Smart Grid: A Survey of Architectural Elements, Machine Learning and Deep Learning Applications and Future Directions [article]

Navod Neranjan Thilakarathne, Mohan Krishna Kagita, Dr. Surekha Lanka, Hussain Ahmad
2020 arXiv   pre-print
This paper explores and surveys the Smart grid architectural elements, machine learning, and deep learning-based applications and approaches in the context of the Smart grid.  ...  The Smart grid (SG), generally known as the next-generation power grid emerged as a replacement for ill-suited power systems in the 21st century.  ...  In this paper, we surveyed and summarized machine learning and deep learning based applications that are introduced and devised in the context of the Smart grid.  ... 
arXiv:2010.08094v1 fatcat:b63nrnsg2bepvokxujhlxkx2tu

Abnormal Detection of Electricity Consumption of User Based on Particle Swarm Optimization and Long Short Term Memory With the Attention Mechanism

Jiahao Bian, Lei Wang, Rafal Scherer, Marcin Wozniak, Pengchao Zhang, Wei Wei
2021 IEEE Access  
memory (Attention-LSTM), LSTM, gated recurrent unit (GRU), support vector regression (SVR), random forest (RF) and linear regression (LR) to verify the effectiveness and accuracy of the method used in  ...  detection performance of the model for various electricity theft behaviors.  ...  Xu et al. in [15] constructed a random forest model, using sparseness combined with anomalous cumulant index to judge the anomaly of the sample, and the detection effect is good.  ... 
doi:10.1109/access.2021.3062675 fatcat:zzmwzim27nah7it4xuoxaasrbm
« Previous Showing results 1 — 15 out of 544 results