Smart metering data analytics for non-intrusive load monitoring

Non-intrusive load monitoring (NILM) can provide a large amount of information users, power utilities for demand response and user-side management. This dissertation surveys NILM methodology, and outlines its basic principle framework and the applications in the first four chapters. In Chapter 5, an...

Full description

Saved in:
Bibliographic Details
Main Author: Ding, Hongyuan
Other Authors: Xu Yan
Format: Theses and Dissertations
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/77297
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-77297
record_format dspace
spelling sg-ntu-dr.10356-772972023-07-04T16:18:39Z Smart metering data analytics for non-intrusive load monitoring Ding, Hongyuan Xu Yan School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electric power::Auxiliaries, applications and electric industries Non-intrusive load monitoring (NILM) can provide a large amount of information users, power utilities for demand response and user-side management. This dissertation surveys NILM methodology, and outlines its basic principle framework and the applications in the first four chapters. In Chapter 5, an ARIMA-Neural Network model is proposed to solve load disaggregation problem of CleanTech Building One’s HVAC system. In Chapter 6, a new method is proposed to evaluate the accuracy of non-intrusive monitoring. Master of Science (Computer Control and Automation) 2019-05-24T04:15:21Z 2019-05-24T04:15:21Z 2019 Thesis http://hdl.handle.net/10356/77297 en 68 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering::Electric power::Auxiliaries, applications and electric industries
spellingShingle DRNTU::Engineering::Electrical and electronic engineering::Electric power::Auxiliaries, applications and electric industries
Ding, Hongyuan
Smart metering data analytics for non-intrusive load monitoring
description Non-intrusive load monitoring (NILM) can provide a large amount of information users, power utilities for demand response and user-side management. This dissertation surveys NILM methodology, and outlines its basic principle framework and the applications in the first four chapters. In Chapter 5, an ARIMA-Neural Network model is proposed to solve load disaggregation problem of CleanTech Building One’s HVAC system. In Chapter 6, a new method is proposed to evaluate the accuracy of non-intrusive monitoring.
author2 Xu Yan
author_facet Xu Yan
Ding, Hongyuan
format Theses and Dissertations
author Ding, Hongyuan
author_sort Ding, Hongyuan
title Smart metering data analytics for non-intrusive load monitoring
title_short Smart metering data analytics for non-intrusive load monitoring
title_full Smart metering data analytics for non-intrusive load monitoring
title_fullStr Smart metering data analytics for non-intrusive load monitoring
title_full_unstemmed Smart metering data analytics for non-intrusive load monitoring
title_sort smart metering data analytics for non-intrusive load monitoring
publishDate 2019
url http://hdl.handle.net/10356/77297
_version_ 1772828092275884032