Reference : Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
Computational Sciences
http://hdl.handle.net/10993/28594
Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets
English
Glauner, Patrick mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Meira, Jorge Augusto mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Dolberg, Lautaro [CHOICE Technologies Holding Sàrl]
State, Radu mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Bettinger, Franck [CHOICE Technologies Holding Sàrl]
Rangoni, Yves [CHOICE Technologies Holding Sàrl]
Duarte, Diogo [CHOICE Technologies Holding Sàrl]
2016
Proceedings of the 3rd IEEE/ACM International Conference on Big Data Computing Applications and Technologies (BDCAT 2016)
Yes
International
3rd IEEE/ACM International Conference on Big Data Computing Applications and Technologies (BDCAT 2016)
from 06-12-2016 to 09-12-2016
Shanghai
China
[en] Data mining ; Electricity theft detection ; Feature engineering ; Feature selection ; Machine learning ; Non-technical losses ; Time series classification
[en] 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.
http://hdl.handle.net/10993/28594

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets.pdfPublisher postprint770.23 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.