• Corpus ID: 49582353

Leveraging data from environmental sensors to enhance electrical load disaggregation algorithms

@inproceedings{Bergs2010LeveragingDF,
  title={Leveraging data from environmental sensors to enhance electrical load disaggregation algorithms},
  author={Mario Berg{\'e}s and Lucio Soibelman and H. Scott Matthews},
  year={2010}
}
The idea of sustainable or green buildings generally stops after the design and construction phases. Little effort is made to continuously monitor and control the energy profile throughout the life-cycle of these facilities. To effectively identify opportunities for consumption reduction, measurement and feedback of current energy use is necessary. Monthly utility bills are inadequate for planning conservation programs, or even for assessing their effectiveness once implemented. Extensive… 

Figures from this paper

Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey
TLDR
This paper provides a comprehensive overview of NILM system and its associated methods and techniques used for disaggregated energy sensing, review the state-of-the art load signatures and disaggregation algorithms used for appliance recognition and highlight challenges and future research directions.
A fast multiple appliance detection algorithm for non-intrusive load monitoring
TLDR
A Bayesian solution is considered which efficiently computes the Log-Likelihood Ratio of an appliance's on/off state, then combines it with historical estimates to yield a new estimate for improved accuracy, and results show promising disaggregation performance.
Improving performance of non-intrusive load monitoring with low-cost sensor networks
TLDR
This thesis proposes to use an external information to improve the performance of the existing NILM algorithms by using another external feature that is the operating probability of each device provided by an additional Wireless Sensor Network (WSN).
On the Modelling, Monitoring, and Detection of Electrical Appliances
To analyse user behaviour and energy consumption data in contemporary and future households, we need to monitor electrical appliance features as well as ambient appliance features. For this purpose,
A Test Bench to Collect Electrical Appliance Load Signatures and Ambient Conditions
TLDR
This work presents a data collection setup to investigate the analysis of dependencies between electrical and ambient sensor data, and shows that the data acquisition test bench is capable of creating a time-synchronized data set, comprised of ambient data and energy measurements at high sampling rates.
Non-intrusive load monitoring: A review and outlook
TLDR
The fundamental building-blocks of NILM are discussed, first giving a taxonomy of appliance models and device signatures and then explaining common supervised and unsupervised learning methods, and a fundamental algorithm that tackles the task of NilM is outlined.
Augmenting an Assisted Living Lab with Non-Intrusive Load Monitoring
TLDR
This work aims to depict an architecture supporting non-intrusive measurement with a smart electricity meter and the handling of these data using an open-source platform that allows to visualize and process real-time data about the total energy consumed.
The Impact of Ambient Sensing on the Recognition of Electrical Appliances
TLDR
This work investigates how additional sensing modalities, i.e., data beyond electrical signals, can be leveraged to improve the appliance detection accuracy and shows that electrical power measurements already yield a high appliance recognition accuracy, yet further accuracy improvements are possible when considering ambient parameters as well.
Low Cost Framework for Non-intrusive Home Energy Monitoring and Research
TLDR
This paper presents a low-cost framework for non-intrusive home energy monitoring and research built on top of Non-Intrusive Load Monitoring (NILM) concepts and techniques using a mini netbook as a packaged solution.
Using Wavelet Transform to Disaggregate Electrical Power Consumption into the Major End-Uses
TLDR
An innovative method based on wavelet transform (WT) to decompose the global power consumption in elemental loads corresponding to each appliance is proposed to identify the main entities that are responsible of total electricity consumption.
...
...

References

SHOWING 1-10 OF 19 REFERENCES
ViridiScope: design and implementation of a fine grained power monitoring system for homes
TLDR
ViridiScope is a fine-grained power monitoring system that furnishes users with an economical, self-calibrating tool that provides power consumption of virtually every appliance in the home and can estimate the end-point power consumption within 10% error.
Challenges in resource monitoring for residential spaces
TLDR
Challenges emerging from fine grained resource monitoring systems are discussed through an empirical study of long-term monitoring data of a residential space, and interesting privacy implications while monitoring a household's resource consumption at high time resolution are revealed.
Power signature analysis
Nonintrusive load monitoring (NILM) can determine operating schedule of electrical loads in a target system from measurements made at a centralized location, such as the electric utility service
Improving shipboard applications of non-intrusive load monitoring
Abstract : The Non-Intrusive Load Monitor (NILM) measures equipment performance by measuring and analyzing the source power to the equipment at a single point in the electrical system. Previous
Minimally intrusive strategies for fault detection and energy monitoring
TLDR
This thesis addresses the need for automated monitoring systems that rely on minimally intrusive sensor arrays and describes the development and application of several modelbased methods that make it possible to use electrical data to detect faults in certain mechanical systems.
Residential energy monitoring and computerized surveillance via utility power flows
  • G. Hart
  • Art
    IEEE Technology and Society Magazine
  • 1989
The author notes that all novel technologies have the potential to affect society in a complex manner, with both beneficial and detrimental consequences. He considers an illustrative case study: a
Feedback on household electricity consumption: a tool for saving energy?
TLDR
A psychological model is presented that illustrates how and why feedback works, and some indication that the most successful feedback combines the following features: it is given frequently and over a long time, provides an appliance-specific breakdown, is presented in a clear and appealing way, and uses computerized and interactive tools.
Development and Validation of a Transient Event Detector
The nonintrusive load monitor (NILM) determines the operating schedule of the major electrical loads in a building from measurements made at the utility service entry. This paper describes techniques
Demo abstract: The Sensor Andrew infrastructure for large-scale campus-wide sensing and actuation
TLDR
This demonstration will showcase already active sensor systems on campus using Sensor Andrew through a web interface as well as the ability to locally configure sensor and actuator interactions as an example of how larger-scale applications could be built.
...
...