Machine learning Techniques for Energy Theft Detection in AMI

Maamar, Assia; Benahmed, Khelifa

doi:10.1145/3178461.3178484

Cited by 26 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, electricity theft datasets contain an imbalanced class, whereby anomalous (thieves) are smaller than normal consumers [35]. e problem with an imbalanced dataset is known in the literature.…”

Section: Related Workmentioning

confidence: 99%

“…To analyze the classification results, accuracy, precision, recall, area under the ROC curve (AUC) [35], and F1-score [36] are calculated to determine the performance of ML models. Besides, to obtain more meaningful performance measures, certain performance criteria, such as the numbers of true positives (TPs), true negatives (TNs), false positives (FPs), and false negatives (FNs), are commonly used in previous studies [29,[37][38][39][40][41][42][43].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Analysis of Supervised Learning Techniques for Electricity Theft Detection

Bohani¹,

Suliman²,

Saripuddin³

et al. 2021

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

There are many methods or algorithms applicable for detecting electricity theft. However, comparative studies on supervised learning methods for electricity theft detection are still insufficient. In this paper, comparisons based on predictive accuracy, recall, precision, AUC, and F1-score of several supervised learning methods such as decision tree (DT), artificial neural network (ANN), deep artificial neural network (DANN), and AdaBoost are presented and their performances are analyzed. A public dataset from the State Grid Corporation of China (SGCC) was used for this study. The dataset consisted of power consumption in kWh unit. Based on the analysis results, the DANN outperforms compared to other supervised learning classifiers such as ANN, AdaBoost, and DT in recall, F1-Score, and AUC. A future research direction is the experiments can be performed on other supervised learning algorithms with different types of datasets and suitable preprocessing methods can be applied to produce better performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Comprehensive Analysis of Supervised Learning Techniques for Electricity Theft Detection

Bohani¹,

Suliman²,

Saripuddin³

et al. 2021

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…Maamar and Benahmed [140] explored energy theft detection in AMI using machine learning techniques, performing a general comparison of machine learning models for detecting energy theft based on extracted information, such as: environment types, metrics and data sets. The most used methods found in this study were, neural networks and support vector machines.…”

Section: H Cybersecuritymentioning

confidence: 99%

Control Networks and Smart Grid Teleprotection: Key Aspects, Technologies, Protocols, and Case-Studies

et al. 2020

View full text Add to dashboard Cite

The appeal for more reliable, efficient and resilient power grids has become indispensable with the recent technological development and ever-increasing demand for electrical energy. These goals might be achieved by introducing sensors and actuators in the power grid, with the purpose of enabling a smart control of the power network. All power devices must be connected using a reliable communication network, which should be able to operate even when the power grid fails. Currently, several communication technologies have been applied for supporting this new application scenario. This paper aims for reviewing both academic and market use cases for technologies applied to the mission-critical, control networks and Smart Grid applications, such as teleprotection, self-healing, communication with control centers and field devices, among others. More specifically, the key aspects, potential technologies, main protocols and use cases of operating data networks in energy transmission, power distribution and smart grid environments, including circuit and packet switching technologies, are discussed into details. Furthermore, resilience and the main telecommunications technologies used in power grids, as well, the correlation among them, are exploited in practical point of view. The article provides a broad discussion on the best telecommunication options to build the emerging intelligent energy distribution systems, covering control networks, teleprotection, and smart grid applications.

show abstract

“…The authors point out how challenges in energy theft detection have not adequately been addressed yet. Such challenges can be data imbalance (normal samples in the same range), Big Data's 3V (volume, velocity, and variety), feature description and selection, and non-malicious factors (change of residents or appliances, or seasonality) [52].…”

Section: Big Data and Data Analytics For Amimentioning

confidence: 99%

The Power of Big Data and Data Analytics for AMI Data: A Case Study

Guerrero-Prado

Alfonso-Morales

Caicedo-Bravo

et al. 2020

Sensors

View full text Add to dashboard Cite

In recent years, there has been a transformation in the value chain of different industrial sectors, like the electricity networks, with the appearance of smart grids. Currently, the underlying knowledge in raw data coming from numerous devices can mark a significant competitive advantage for utilities. It is the case of the Advanced Metering Infrastructure (AMI). Such technology gets user consumption characteristics at levels of detail that were previously not possible. In this context, the terms big data and data analytics become relevant, which are tools that allow using large volumes of information and the generation of valuable knowledge from raw data that can support data-driven decisions for operating on the grid. This paper presents the results of the big data implementation and data analytics techniques in a case study with smart metering data from the city of London. Implemented big data and data analytic techniques to show how to understand user consumption patterns on a broader horizon, the relationships with seasonal variables identify behaviors related to specific events and atypical consumptions. This knowledge helps support decision making about improving demand response programs and, in general, the planning and operation of the Smart Grid.

show abstract

Machine learning Techniques for Energy Theft Detection in AMI

Cited by 26 publications

References 17 publications

A Comprehensive Analysis of Supervised Learning Techniques for Electricity Theft Detection

A Comprehensive Analysis of Supervised Learning Techniques for Electricity Theft Detection

Control Networks and Smart Grid Teleprotection: Key Aspects, Technologies, Protocols, and Case-Studies

The Power of Big Data and Data Analytics for AMI Data: A Case Study

Contact Info

Product

Resources

About