Variability and Trend-Based Generalized Rule Induction Model to NTL Detection in Power Companies

León, Carlos; Biscarri, Félix; Monedero, Íñigo; Guerrero, Juan Ignacio; Biscarri, Jesús; Millán, Rocío

doi:10.1109/tpwrs.2011.2121350

Cited by 60 publications

(37 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies with a Pattern Recognition approach have addressed the detection of non-technical losses, both supervised or unsupervised. Leon et al review the main research works found in the area between 1990 and 2008 (Leon et al, 2011). Here we present a brief review that builds on this work and wide it with new contributions published between 2008 and 2013.…”

Section: Introductionmentioning

confidence: 85%

Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage

Rodríguez

Lecumberry

Fernández

2014

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

Non-technical losses detection is a complex task, with high economic impact. The diversity and big number of consumption records, makes it very important to find an efficient automatic method for detection the largest number of frauds with the least amount of experts' hours involved in preprocessing and inspections. This article analyzes the performance of a strategy based on learning from expert labeling: suspect/no-suspect, with one using inspection labels: fraud/no-fraud. Results show that the proposed framework, suitable for imbalance problems, improves performance in terms of the F measure with inspection labels, avoiding hours of experts labeling.

show abstract

Section: Introductionmentioning

confidence: 85%

Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage

Rodríguez

Lecumberry

Fernández

2014

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

show abstract

“…These deviations are commonly referred to as non-technical losses (NTLs) [55], and different techniques have been successfully applied to detect them. For instance, León et al [56] proposed a comprehensive framework to detect NTLs and recover electrical energy (lost by abnormalities or fraud). Their predictive analysis tool, supplemented by a binary quest tree classification method, was used to discovered association rules in the data.…”

Section: Energy Fraud Detectionmentioning

confidence: 99%

Data science for building energy management: A review

Molina-Solana

Ros

Ruiz

et al. 2017

Renewable and Sustainable Energy Reviews

222

108

View full text Add to dashboard Cite

The energy consumption of residential and commercial buildings has risen steadily in recent years, an increase largely due to their HVAC systems. Expected energy loads, transportation, and storage as well as user behavior influence the quantity and quality of the energy consumed daily in buildings. However, technology is now available that can accurately monitor, collect, and store the huge amount of data involved in this process. Furthermore, this technology is capable of analyzing and exploiting such data in meaningful ways. Not surprisingly, the use of data science techniques to increase energy efficiency is currently attracting a great deal of attention and interest. This paper reviews how Data Science has been applied to address the most difficult problems faced by practitioners in the field of Energy Management, especially in the building sector. The work also discusses the challenges and opportunities that will arise with the advent of fully connected devices and new computational technologies.

show abstract

“…Recently in [1], a state estimation based approach to the load estimation of distribution transformers was exploited to detect meter tampering and provide quantitative evidence of NTLs. In the literature, several techniques in the area of intelligent systems, or soft computing, have been employed, some of which are: multiple classifiers and wavelet coefficients [3]; fuzzy logic [4], [5]; text mining [6]; Bayesian networks [7]; the pattern recognition technique via optimum path forest [8], data mining [9]; data mining using support vector machines [10], using extreme leaning machines [11], using generalized rule induction [12], and fuzzy inference systems [13].…”

Section: Introductionmentioning

confidence: 99%

Spatial-Temporal Estimation for Nontechnical Losses

Faria

Melo

Padilha‐Feltrin

2016

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

This paper presents a novel method for estimating the spatial distribution in geographical space of the nontechnical losses over time. The method progresses in two stages: in the first stage, a generalized additive model is used to generate a map of current loss probabilities. The second stage employs the Markov chain to generate a map that indicates possible future changes in loss probabilities. The method yields an assessment of the location of the non-technical losses now and in the future at the city subarea level, even indicating the variables that have greater statistical correlation with the non-technical losses. We apply the method to a city with approximately 81,000 consumers and the results are compared with those obtained through inspections carried out by a Brazilian power utility. The detection rate surpasses 78% in inspected subareas. The method we propose offers improved estimation of distribution of the non-technical losses in urban regions. Index Terms -Electricity theft, generalized additive models, non-technical losses, spatial point pattern analysis.0885-8977 (c) . His main fields of insterest are analysis and control of electrical power systems.

show abstract

Variability and Trend-Based Generalized Rule Induction Model to NTL Detection in Power Companies

Cited by 60 publications

References 25 publications

Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage

Non Technical Loses Detection - Experts Labels vs. Inspection Labels in the Learning Stage

Data science for building energy management: A review

Spatial-Temporal Estimation for Nontechnical Losses

Contact Info

Product

Resources

About