NORMA@NCI Library

Electricity Consumption Anomaly Detection Model Using Deep Learning

Banad Ramesh, Chetan (2019) Electricity Consumption Anomaly Detection Model Using Deep Learning. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (727kB) | Preview

Abstract

Electricity loss minimization is one of the major issues the service providers are facing, which needs to be addressed as soon as possible. Loss may be because of the technical or non-technical factor. The non-technical losses (NTLs) are the losses which are caused by human in form of illegal use of electricity, electricity theft and billing fraud etc. These losses should be minimized for the providers to be profitable. Smart meter plays a prominent role in monitoring energy theft and optimizing the usage of the electricity among the consumer. The smart meter records the consumption data of the consumer and when analysed give the usage pattern of the consumer which can be used to detect the anomaly in the usage pattern of the consumer. By detecting the anomaly, the provider can take necessary steps and minimize the loss. Many researchers have attempted to tackle this problem of detecting the anomaly in the consumption data using different time series model like ARIMA, ARMA etc to forecast the future consumption and thus detect anomaly. The researcher has also used deep learning models like LSTM, RNN etc. to predict the future consumption and detect anomaly. In this research we propose a novel computational effective anomaly detection model using the various version of GRU model.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software

T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electricity Supply
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 11 Oct 2019 14:04
Last Modified: 11 Oct 2019 14:04
URI: http://trap.ncirl.ie/id/eprint/3848

Actions (login required)

View Item View Item