Literature review on the applications of data mining in power systems

Kazerooni, Maryam; Zhu, Hao; Overbye, Thomas J.

doi:10.1109/peci.2014.6804567

Cited by 22 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also plan to study in more detail the feature correlation in order to understand better customers' behaviour. 6 Details omitted for double-blind reviewing.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Distilling provider-independent data for general detection of non-technical losses

Meira

Glauner

State

et al. 2017

2017 IEEE Power and Energy Conference at Illinois (PECI)

View full text Add to dashboard Cite

Abstract-Non-technical losses (NTL) in electricity distribution are caused by different reasons, such as poor equipment maintenance, broken meters or electricity theft. NTL occurs especially but not exclusively in emerging countries. Developed countries, even though usually in smaller amounts, have to deal with NTL issues as well. In these countries the estimated annual losses are up to six billion USD. These facts have directed the focus of our work to the NTL detection. Our approach is composed of two steps: 1) We compute several features and combine them in sets characterized by four criteria: temporal, locality, similarity and infrastructure. 2) We then use the sets of features to train three machine learning classifiers: random forest, logistic regression and support vector vachine. Our hypothesis is that features derived only from provider-independent data are adequate for an accurate detection of non-technical losses. We used Area Under the Receiver-operating Curve (AUC) to assess the results.

show abstract

“…We also plan to study in more detail the feature correlation in order to understand better customers' behaviour. 6 Details omitted for double-blind reviewing.…”

Section: Discussionmentioning

confidence: 99%

“…This task is called feature engineering. [4], [5] and [6]. Surveys of how an advanced metering infrastructure can be manipulated, are provided in [7] and [8].…”

Section: A Backgroundmentioning

confidence: 99%

Distilling provider-independent data for general detection of non-technical losses

Meira

Glauner

State

et al. 2017

2017 IEEE Power and Energy Conference at Illinois (PECI)

View full text Add to dashboard Cite

show abstract

“…These 10 algorithms cover classification, clustering, statistical learning, association analysis, and link mining, which are all among the most important topics in data mining research and development. In [18] a review on the applications of data mining in power systems is given. The approach described here combines several segments of classification and clustering and statistical learning in one algorithm.…”

Section: Proposed Algorithm Designmentioning

confidence: 99%

Wind Power Monitoring and Control Based on Synchrophasor Measurement Data Mining

Klarić¹,

Kuzle

Holjevac

2018

Energies

View full text Add to dashboard Cite

More and more countries and utilities are trying to develop smart grid projects to make transformation of their power infrastructure towards future grids with increased share of renewable energy production and near zero emissions. The intermittent nature of solar and wind power can in general cause large problems for power system control. Parallel to this process, the aging of existing infrastructure also imposes requirements to utility budgets in the form of a need for large capital investments in reconstruction or maintenance of key equipment. Synchrophasor and other synchronized measurement technologies are setting themselves as one of the solutions for larger wind power integration. With that aim, in this paper one possible solution for wind power control through data mining algorithms used on a large quantity of data gathered from phasor measurement units (PMU) is described. Developed model and algorithm are tested on an IEEE 14 bus test system as well as on real measurements made on wind power plants currently in operation. One such wind power plant is connected to the distribution grid and the other one to the transmission grid. Results are analyzed and compared.

show abstract

“…NTL detection can be treated as an anomaly or fraud detection problem. Comprehensive surveys of the field of NTL detection are provided in [7], [12] and [16]. Surveys of how an advanced metering infrastructure can be manipulated, are provided in [15] and [17].…”

Section: Related Workmentioning

confidence: 99%

Neighborhood features help detecting non-technical losses in big data sets

Glauner

Meira

Dolberg³

et al. 2016

Proceedings of the 3rd IEEE/ACM International Conference on Big Data Computing, Applications and Technologies

View full text Add to dashboard Cite

Electricity theft occurs around the world in both developed and developing countries and may range up to 40% of the total electricity distributed. More generally, electricity theft belongs to non-technical losses (NTL), which occur during the distribution of electricity in power grids. In this paper, we build features from the neighborhood of customers. We first split the area in which the customers are located into grids of different sizes. For each grid cell we then compute the proportion of inspected customers and the proportion of NTL found among the inspected customers. We then analyze the distributions of features generated and show why they are useful to predict NTL. In addition, we compute features from the consumption time series of customers. We also use master data features of customers, such as their customer class and voltage of their connection. We compute these features for a Big Data base of 31M meter readings, 700K customers and 400K inspection results. We then use these features to train four machine learning algorithms that are particularly suitable for Big Data sets because of their parallelizable structure: logistic regression, k-nearest neighbors, linear support vector machine and random forest. Using the neighborhood features instead of only analyzing the time series has resulted in appreciable results for Big Data sets for varying NTL proportions of 1%-90%. This work can therefore be deployed to a wide range of different regions.

show abstract

Literature review on the applications of data mining in power systems

Cited by 22 publications

References 24 publications

Distilling provider-independent data for general detection of non-technical losses

Distilling provider-independent data for general detection of non-technical losses

Wind Power Monitoring and Control Based on Synchrophasor Measurement Data Mining

Neighborhood features help detecting non-technical losses in big data sets

Contact Info

Product

Resources

About