User-Centered Nonintrusive Electricity Load Monitoring for Residential Buildings

Bergés, Mario; Goldman, Ethan; Matthews, H. Scott; Soibelman, Lúcio; Anderson, Ken

doi:10.1061/(asce)cp.1943-5487.0000108

Cited by 119 publications

(42 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An area of research called Non-Intrusive Load Monitoring (NILM) that starts with the total consumption for a home and separates out the switching on and off of individual appliances offers an elegant solution: with only one physical monitoring point yet giving individual appliance data (Farinaccio & Zmeureanu, 1999;Hart, 1992;Berges, Goldman, Matthews, Soibelman, & Anderson, 2011;Chahine, et al, 2011). A number of such devices that use NILM have become available to the consumer, primarily for the purpose of keeping track of electricity costs of appliances (smappee, 2015; Navetas energy management, 2015; The energy detective, 2015).…”

Section: íNdicementioning

confidence: 99%

Off-the-shelf Non-Intrusive Load Monitoring Devices Utilised in a Low Activity Detection Service

Hunt

Rajendran²,

Nikora³

et al. 2016

Ariadna

View full text Add to dashboard Cite

There is a growing awareness for the need to provide low cost solutions for the care of the elderly and in particular to allow them to keep living independent lives. In parallel to this, there have also been significant advances in a number of technical areas including 1) monitoring electricity consumption for the purpose of reducing power costs, 2) non-intrusive load monitoring (NILM), 3) using sensors to determine activities of daily living and 4) cloud computing. The purpose of this work was to demonstrate that it is possible to use a readily available consumer off the shelf electricity monitor to provide a low intrusive activity monitor for older persons. This work uses the Design Science Research Methodology and builds on the results of our previous work that used raw electricity usage data. In this work we are trailing the use of a meter that uses NILM to identify individual appliances in the home. The information on appliance use was analysed by a cloud base program and alerts were sent to the carer when lower than expected activity was detected. Participants both in this work and those reported in the literature have mentioned the annoyance of having multiple sensors in a home, especially if they emit either constant or flashing light. In contrast, NILM allows the use of multiple electrical appliances to be monitored without the need for a large number of sensors to be deployed -just one sensor at the meter or fuse board. The confluence of a number of technologies has enabled the creation of a low intrusive and low cost monitoring system to have become a reality. The initial trial of the system has been shown to be a most reliable alternative to a system built on multiple sensors. Based on previous work that involved the deployment of multiple sensors, the new system is expected to be more acceptable as it has the desired attribute of becoming invisible to the user.

show abstract

Section: íNdicementioning

confidence: 99%

Off-the-shelf Non-Intrusive Load Monitoring Devices Utilised in a Low Activity Detection Service

Hunt

Rajendran²,

Nikora³

et al. 2016

Ariadna

View full text Add to dashboard Cite

show abstract

“…Variations in steady state power metrics (differences between power metrics before and after an event), such as the real power, reactive power, power factor, RMS current, and RMS voltage, are among the most common steady state features used in the recent research studies (e.g., Marchiori et al 2011). Other features such as the harmonic content of the current waveform (Akbar and Khan 2007), and information contained in the transients between steady states (Berges et al 2011) were also integrated in a number of studies to improve the performance of the algorithms. In these studies, the efforts were mainly focused on the NILM event detection and pattern recognition with little attention paid to the challenges associated with training these algorithms.…”

Section: Nilm Research Backgroundmentioning

confidence: 99%

“…However, in recent years, the training process and its facilitation have been the subject of a number of studies. The introduction of a user-centric NILM system (Berges et al 2011) and use of non-electricity sensor assisted training (Rajagopal et al 2013;Schoofs et al 2010;Taysi et al 2010) are among these efforts. This study contributes to these efforts by improving upon the user-centric NILM systems.…”

Section: Nilm Research Backgroundmentioning

confidence: 99%

Unsupervised Clustering of Residential Electricity Consumption Measurements for Facilitated User-Centric Non-Intrusive Load Monitoring

Jazizadeh¹,

Becerik-Gerber²,

Bergés³

et al. 2014

Computing in Civil and Building Engineering (2014)

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM) is a low-cost alternative to appliance level sub-metering, that leverages signal processing and machine learning techniques to estimate the power consumption of individual appliances from whole-home measurements. However, the difficulty associated with obtaining training data sets for the commonly used supervised NILM classification algorithms is a major obstacle in wide commercial adoption of the technology. The diversity of electrical load signatures (patterns of appliances' power draw) demands in-situ training (labeling of the signatures), which often needs to be performed by ordinary users through usersystem interaction. To produce the example signatures required for training, continuous interaction with users might be required, which could reduce the success of the training process due to user fatigue. Pre-populating the training data set could help facilitate the process by reducing the number of user-system interactions needed for labeling. Taking into consideration all the issues described above, a study to test the feasibility of autonomous clustering of similar appliances' signatures based on hierarchical clustering was investigated. The information contained in the structure of the binary cluster tree was used for clustering without the need for a priori selection of the number of clusters. The assessment, carried out on data collected from a residential setting, showed promising results (with accuracy above 90%, calculated based on the ground truth labels) supporting the feasibility of the approach for unsupervised clustering.

show abstract

“…Azar and Menassa (2011) have studied the residents' impact on energy use in commercial buildings, while Berges et al (2008Berges et al ( , 2011 were focused on load monitoring of home's appliances mainly in residential buildings. Mardookhy et al (2014) studied energy efficiency in residential buildings in Knoxville, while Agüero-Rubio et al (2014) proposed a methodology for management of thermal loads with real-time prices.…”

Section: Introductionmentioning

confidence: 99%

Wind energy integration via residential appliances

Xydis

Mihet‐Popa

2016

Energy Efficiency

View full text Add to dashboard Cite

In this paper cold and thermal storage options via wind energy surplus are examined aiming to enable higher wind integration. A case study in Greece with an installed wind farm (WF) was investigated reviewing the possibilities for higher renewables integration using thermostatically controlled loads (TCLs), analysing thermal and cold storage possibilities according to the needs of the local municipalities. The basic aim is to describe the idea of an aggregated system with a number of residential freezers, in order the wind power to be stored in the residential cold stores aiming at maximizing the benefit to the grid, utility or cold store owner avoiding at the same time wind curtailment. In addition, for thermal storage, by calculating thermal losses of the building, ventilation losses and adding up internal thermal gains of the building the space heating needs can be calculated.

show abstract

User-Centered Nonintrusive Electricity Load Monitoring for Residential Buildings

Cited by 119 publications

References 14 publications

Off-the-shelf Non-Intrusive Load Monitoring Devices Utilised in a Low Activity Detection Service

Off-the-shelf Non-Intrusive Load Monitoring Devices Utilised in a Low Activity Detection Service

Unsupervised Clustering of Residential Electricity Consumption Measurements for Facilitated User-Centric Non-Intrusive Load Monitoring

Wind energy integration via residential appliances

Contact Info

Product

Resources

About