Non-Technical Loss Detection in Power Grids with Statistical Profile Images Based on Semi-Supervised Learning

Li, Jiangteng; Wang, Fei

doi:10.3390/s20010236

Cited by 20 publications

(21 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another contribution using a dataset from a Chinese company is presented in [19]. The authors have used the timeseries data to convert it into image form which is helpful in longer run for analyzing the consumer's consumption behavior.…”

Section: Literature Reviewmentioning

confidence: 99%

Treating Class Imbalance in Non-Technical Loss Detection: An Exploratory Analysis of a Real Dataset

et al. 2021

View full text Add to dashboard Cite

Non-Technical Loss (NTL) is a major concern for many electric supply companies due to the financial impact caused as a result of suspect consumption activities. A range of machine learning classifiers have been tested across multiple synthesized and real datasets in order to combat NTL. An important characteristic that exists in these datasets is the imbalance distribution of the classes. When the focus is in predicting the minority class of suspect activities, the impact of sensitivity of the classifiers to the class imbalance becomes more important. In this paper, we evaluate the performance of a range of classifiers with under-sampling and over-sampling techniques. The results are compared with the untreated imbalance dataset. In addition, we compare the performance of the classifiers using penalized classification model. Lastly, the paper presents an exploratory analysis of using different sampling techniques on NTL detection in a real dataset and identify the best performing classifiers. We conclude that logistic regression is the most sensitive to the sampling techniques as the change of its recall is measured around 50% for all sampling techniques while random forest is the least sensitive to the sampling technique as the change of its precision is observed between 1% − 6% for all sampling techniques.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Treating Class Imbalance in Non-Technical Loss Detection: An Exploratory Analysis of a Real Dataset

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Even if the clusters form a shape, referred to herein as theft/non-theft, the shapes are not homogeneous-isotropic, so the clusters are localized in space, and that is the essence of the proof. Work [64] by Wang et al and work [65] by Wu et al, are "t-distributed stochastic neighbor embedding" (T-SNE) graphs, which are an alternative to the PCA graphs-worth observing as good examples of classes signatures, which depicted "dimensionality reduction". In fact, there are more signatures that have been depicted in previous works, seven of which were sampled by this group, after which we stopped sampling.…”

Section: Theoretical Computation Of the Effect Of Distance Between Electric Device Signatures Over Mix-up Probability Between Electrical mentioning

confidence: 99%

A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements

Calamaro¹,

Donko²,

Shmilovitz³

2021

Energies

View full text Add to dashboard Cite

The central problems of some of the existing Non-Intrusive Load Monitoring (NILM) algorithms are indicated as: (1) higher required electrical device identification accuracy; (2) the fact that they enable training over a larger device count; and (3) their ability to be trained faster, limiting them from usage in industrial premises and external grids due to their sensitivity to various device types found in residential premises. The algorithm accuracy is higher compared to previous work and is capable of training over at least thirteen electrical devices collaboratively, a number that could be much higher if such a dataset is generated. The algorithm trains the data around 1.8×108 faster due to a higher sampling rate. These improvements potentially enable the algorithm to be suitable for future “grids and industrial premises load identification” systems. The algorithm builds on new principles: an electro-spectral features preprocessor, a faster waveform sampling sensor, a shorter required duration for the recorded data set, and the use of current waveforms vs. energy load profile, as was the case in previous NILM algorithms. Since the algorithm is intended for operation in any industrial premises or grid location, fast training is required. Known classification algorithms are comparatively trained using the proposed preprocessor over residential datasets, and in addition, the algorithm is compared to five known low-sampling NILM rate algorithms. The proposed spectral algorithm achieved 98% accuracy in terms of device identification over two international datasets, which is higher than the usual success of NILM algorithms.

show abstract

“…Likewise, authors in [38] design a deep generative model, termed as semi-supervised autoencoder (SSAE), which makes use of semi-supervised information for ETD. A similar case is presented in [39] where a mean teacher based semi-supervised mechanism is used for the identification of NTL. In [40], the advantages of semi-supervised EC data is obtained by utilizing the semi-supervised SVM for the detection of abnormal consumers.…”

Section: ) Semi-supervised Solutionsmentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

Non-Technical Loss Detection in Power Grids with Statistical Profile Images Based on Semi-Supervised Learning

Cited by 20 publications

References 28 publications

Treating Class Imbalance in Non-Technical Loss Detection: An Exploratory Analysis of a Real Dataset

Treating Class Imbalance in Non-Technical Loss Detection: An Exploratory Analysis of a Real Dataset

A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements

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

Contact Info

Product

Resources

About