Detection of non-technical losses using advanced metering infrastructure and deep recurrent neural networks

Chatterjee, Soham; Archana, Vaidheeswaran; Suresh, K.S.; Saha, Rohit; Gupta, Raghav; Doshi, Fenil

doi:10.1109/eeeic.2017.7977665

Cited by 14 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, an increasing interest is found in the use of the combination of multiple classifiers, the use of multiple evaluation metrics to correctly figure out the losses, and the post-processing phase, etc. Multiple combinations of classifiers have been tested for the detection of NTL which includes wide and deep CNN [4], recurrent neural network (RNN) [5], fuzzy logic [6], CatBoost [2], etc. Apart from classification, a number of other techniques have been tested which includes association rule mining [7], hierarchical clustering [8], outlier detection techniques [9], etc.…”

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

“…In Chatterjee et al (2017), the authors have used deep recurrent neural networks to identify NTL. The data used is related to advanced metering infrastructure (AMI).…”

Section: Consumption-data Based Techniquesmentioning

confidence: 99%

Performance analysis of machine learning classifiers for non-technical loss detection

Ghori

Imran

Nawaz

et al. 2020

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Power companies are responsible for producing and transferring the required amount of electricity from grid stations to individual households. Many countries suffer huge losses in billions of dollars due to non-technical loss (NTL) in power supply companies. To deal with NTL, many machine learning classifiers have been employed in recent time. However, few has been studied about the performance evaluation metrics that are used in NTL detection to evaluate how good or bad the classifier is in predicting the non-technical loss. This paper first uses three classifiers: random forest, K-nearest neighbors and linear support vector machine to predict the occurrence of NTL in a real dataset of an electric supply company containing approximately 80,000 monthly consumption records. Then, it computes 14 performance evaluation metrics across the three classifiers and identify the key scientific relationships between them. These relationships provide insights into deciding which classifier can be more useful under given scenarios for NTL detection. This work can be proved to be a baseline not only for the NTL detection in power industry but also for the selection of appropriate performance evaluation metrics for NTL detection.

show abstract

“…Technical and Non-Technical losses are the two categories into which these power losses can be divided. Unauthorized tapping of distribution lines and poles, refusal to pay bills, meter tampering and circumventing meters, official bribery, and defective meters are some examples of non-technical losses [2]. Non-technical losses are understudied, and the majority of power utilities do not keep records of these losses' data.…”

Section: Introductionmentioning

confidence: 99%

“…Figure 9: Framework of a Vanilla Recurrent Neural NetworkThe diagram above demonstrates how an RNN can be unrolled according to time steps or the quantity of sequences. For instance, the RNN can be unrolled into a 10-layer neural network if there are 10 sequences[16].…”

mentioning

confidence: 99%

Smart Metering System Using Ai Techniques

Goswami¹

2022

IJSREM

View full text Add to dashboard Cite

The economy of energy suppliers and countries may be significantly impacted by non-technical losses (NTLs) in the electrical distribution system, which mostly involve electrical theft. Non-technical losses include consumer dishonesty, unethical transmission line tapping, and hacking or tampering with energy meters. The smart meter, a crucial component of the smart grid, is anticipated to benefit several stakeholders on the economic, social, and environmental levels. Smart meter data analytics, which deals with data gathering, transmission, processing, and interpretation that benefits all stakeholders, is one of the crucial elements that will define the success of smart meters. An artificial neural network can be created in order to find and identify meter manipulation or energy theft. The outcomes can also be applied to larger real-world systems. Additionally, a communication network that satisfies the security requirements for smart grid communication must be properly chosen and implemented in order to deploy smart meters. This article discusses different problems and difficulties related to the development, implementation, use, and upkeep of the smart metering system. Catchphrases- NTL, losses detection, Smart meter, Advanced Metering Infrastructure, Automatic Meter Reading, Neural Networks, Communication Systems, Energy Consumption Profiles.

show abstract

Detection of non-technical losses using advanced metering infrastructure and deep recurrent neural networks

Cited by 14 publications

References 12 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

Performance analysis of machine learning classifiers for non-technical loss detection

Smart Metering System Using Ai Techniques

Contact Info

Product

Resources

About