Semisupervised Approach to Non Technical Losses Detection

Abstract

Non-technical electrical losses detection is a complex task, with high economic impact. Due to the diversity and large number of consumption records, it is very important to find an efficient automatic method to detect 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 a semisupervised method, that starting from a set of labeled data, extends this labels to unlabeled data, and then allows to detect new frauds at consumptions. Results show that the proposed framework, improves performance in terms of the Fmeasure against manual methods performed by experts and previous supervised methods, avoiding hours of experts/inspection labeling.

An Attention Guided Semi-Supervised Learning Mechanism to Detect Electricity Frauds in the Distribution Systems

“…This mechanism uses the concept of transfer learning. Another work done in [37] implements a semi-supervised support vector machine (SVM), named as transductive SVM (TSVM), for ETD by utilizing the labeled and unlabeled information. Likewise, authors in [38] design a deep generative model, termed as semi-supervised autoencoder (SSAE), which makes use of semi-supervised information for ETD.…”

“…It creates a boundary between classes for class separation. The authors in [37] design a semi-supervised SVM, named as TSVM, to make use of both labeled and unlabeled information. Therefore, we consider it as a baseline.…”

Knowledge Embedded Semi-Supervised Deep Learning for Detecting Non-Technical Losses in the Smart Grid

“…[23] uses Transductive SVM(TSVM) to build a NTL detecting system. Restricted to TSVM could not handle imbalance situation, [23] has not been demonstrated enough for detecting NTL. However, semi-supervised learning still is competitive and hopeful choice for detecting NTL when it meets deep learning.…”

“…However, we cannot use SVM to replace these 2 fully connected layers, because it is impossible to co-train SVM and autoencoder together. The separated training will lead to a decline in the learning efficiency, such as [23] could not get satisfactory performance of NTL detection.…”

Optimal and Linear F-Measure Classifiers Applied to Non-technical Losses Detection

“…Several pattern recognition approaches have addressed the detection of nontechnical losses, both supervised, unsupervised or recently semi-supervised as shown in [36]. Leon et al review the main research works found in the area between 1990 and 2008 [23].…”