Methodology to Identify Non-Technical Losses in Rural Grids Using Artificial Neural Networks and Deep Learning

Vieira, Vanessa Gindri; Bernardon, Daniel Pinheiro; Heink, M.; Figueiredo, Rodrigo Marques de; Evaldt, Maicon Coelho; Uberti, Vinícius André; Abaide, Alzenira da Rosa; Chiara, L. de; Silva, J. A.

doi:10.1049/icp.2021.1472

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the discrete "true" or "false" values, it utilizes a "degree of truth" that can assume any value between zero and one, with the extreme values representing truth and falsehood, respectively. Instances of employing this nuanced logic are illustrated in [25,26].…”

Section: Methods Of Identification and Assessment Of Nontechnical Los...mentioning

confidence: 99%

“…Thanks to these hidden layers, input signals undergo preliminary processing before reaching the adder. Studies employing this type of neural networks can be found in [25,27,[40][41][42][43][44][45][46][47][48].…”

Section: Methods Of Identification and Assessment Of Nontechnical Los...mentioning

confidence: 99%

“…From this, it can be concluded that if a newly connected consumer immediately, after their connection, starts to use electrical energy and is not detected, while maintaining certain patterns of their behavior, it is unlikely to be detected further by existing algorithms. Only 9% of publications describe how to detect theft of electrical energy online, and in such cases, it is necessary to fulfill certain requirements [25,43,102].…”

Section: Source Data Metric Depth Of Retrospective and Sampling Ratementioning

confidence: 99%

See 2 more Smart Citations

Data-Driven Machine Learning Methods for Nontechnical Losses of Electrical Energy Detection: A State-of-the-Art Review

Pazderin,

Kamalov,

Gubin

et al. 2023

Energies

View full text Add to dashboard Cite

Nontechnical losses of electrical energy (NTLEE) have been a persistent issue in both the Russian and global electric power industries since the end of the 20th century. Every year, these losses result in tens of billions of dollars in damages. Promptly identifying unscrupulous consumers can prevent the onset of NTLEE sources, substantially reduce the amount of NTLEE and economic damages to network grids, and generally improve the economic climate. The contemporary advancements in machine learning and artificial intelligence facilitate the identification of NTLEE sources through anomaly detection in energy consumption data. This article aims to analyze the current efficacy of computational methods in locating, detecting, and identifying nontechnical losses and their origins, highlighting the application of neural network technologies. Our research indicates that nearly half of the recent studies on identifying NTLEE sources (41%) employ neural networks. The most utilized tools are convolutional networks and autoencoders, the latter being recognized for their high-speed performance. This paper discusses the main metrics and criteria for assessing the effectiveness of NTLEE identification utilized in training and testing phases. Additionally, it explores the sources of initial data, their composition, and their impact on the outcomes of various algorithms.

show abstract

Section: Methods Of Identification and Assessment Of Nontechnical Los...mentioning

confidence: 99%

Section: Methods Of Identification and Assessment Of Nontechnical Los...mentioning

confidence: 99%

Section: Source Data Metric Depth Of Retrospective and Sampling Ratementioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Machine Learning Methods for Nontechnical Losses of Electrical Energy Detection: A State-of-the-Art Review

Pazderin,

Kamalov,

Gubin

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

Assignment of AI Detected Buildings from Satellite Images to Registered Meters for Energy Theft Detection

Kaminski,

Carloto,

Barriquello

et al. 2024

2024 IEEE Power &Amp; Energy Society Innovative Smart Grid Technologies Conference (ISGT)

View full text Add to dashboard Cite

Tolerance-Based Demand-Side Management for Load Shifting in Rural Areas of Southern Brazil

et al. 2023

View full text Add to dashboard Cite

In the rural regions of southern Brazil, electricity is largely directed to irrigation activities on rice crops at restricted periods of the year. Typically, customers in these regions are called “irrigators”, and have some characteristics different from loads in urban centers, such as high demand levels and sharp load variations. These characteristics can result in problems of excessive loading on distribution grids at certain times of the day, generating concerns for the power utilities in relation to the security of the electrical system, energy supply to customers, and the integrity of electrical equipment. An alternative to avoid or mitigate these possible problems may be the application of a demand management model to irrigator customers. In this context, a load shifting strategy can be inserted to reduce demand in more critical periods and move it to intervals with lower load on the power grid. In this context, this article presents a demand-side management methodology in distribution systems located in rural areas, employing the load shifting strategy for irrigator customers. The methodology proposed in this paper is not an entirely novel approach, but one specifically developed for the context of irrigator customers, a subject little studied in the literature. The load management model proposed by this study is segmented into three hierarchical levels. The first level is the identification of the electrical characteristics of the distribution systems, the second level is the power flow analysis of the distribution networks, and the third and last level consists in the application of load shifting to the irrigator customers of these electrical systems. The load shifting strategy is modeled by a linear programming algorithm and is only applied to irrigator customers in situations of excessive loading on power grid. The case studies were conducted on three distribution systems of a power utility, with more than 150 irrigator customers. The DSM model based on the load shifting strategy reduced the maximum demand and daily load variations on the three rural feeders evaluated. The proposed changes in load patterns can ensure the continuity of electric power supply service in future even with the high concentration of load on distribution networks, benefiting customers and power utilities.

show abstract

Methodology to Identify Non-Technical Losses in Rural Grids Using Artificial Neural Networks and Deep Learning

Cited by 3 publications

References 0 publications

Data-Driven Machine Learning Methods for Nontechnical Losses of Electrical Energy Detection: A State-of-the-Art Review

Data-Driven Machine Learning Methods for Nontechnical Losses of Electrical Energy Detection: A State-of-the-Art Review

Assignment of AI Detected Buildings from Satellite Images to Registered Meters for Energy Theft Detection

Tolerance-Based Demand-Side Management for Load Shifting in Rural Areas of Southern Brazil

Contact Info

Product

Resources

About