- We present a refined algorithm disaggregating appliance-level electricity consumption data from smart meters
- Consumption data with a resolution of 1 Hz allows recognizing several appliances with good accuracy
Information about a household’s electricity consumption at the level of individual appliances is valuable for energy efficiency services and for marketing purposes alike. Installing sensors at each outlet to retrieve such appliance-level data, however, comes at high cost and is rather impractical. An alternative is to measure the household’s overall consumption at a central point (e.g. via a smart electricity meter) and to infer appliance-level information by means of machine learning. This, however, is a challenging task, partly due to the large number of appliances per household and the high variability of the load patterns per device.
We implemented a prominent non-intrusive load monitoring (NILM) algorithm first published by Hart in 1992, improved its filtering technique and adapted it to electricity consumption data available at sampling frequencies of 1 Hz. These steps make it applicable to many smart electricity meters. Moreover, to support the learning phase in individual households, we developed a smartphone app that̶ based an automatic event detection ̶ enables users to label on-off events of appliances.
The algorithm performs well for devices that have only one or two distinct consumption modes such as lights and fridges. The smartphone app enables the user to comfortably label on-off events of appliances and thereby enables a training phase in individual households. The latter helps to bridge the gap between applications in the lab carried that are carried out by engineers, and in real homes by providing an easy-to-use tool that ordinary people without particular training and technical expertise can set up and use.
Weiss, Helfenstein, Mattern, Staake (2012) Leveraging smart meter data to recognize home appliances,2012 IEEE International Conference on Pervasive Computing and Communications, Lugano, 2012, pp. 190-197.
This project has been funded in parts by Landis+Gyr.
Date: 2010 - 2012
Markus Weiss, Adrian Helfenstein, Friedemann Mattern, Thorsten Staake
Non-Intrusive Load Monitoring: Do NILM-Researchers Promise too much?
Non-Intrusive Load Monitoring: An Updated Version of Hart's Algorithm
Base Load Estimation with Smart Meter Data
Occupancy Detection with Smart Meter Data
For further information or if you have any questions please do not hesitate to contact us.
Strictly necessary cookies guarantee functions without which this website would not function as intended. As a result these cookies cannot be deactivated. These cookies are used exclusively by this website and are therefore first party cookies. This means that all information stored in the cookies will be returned to this website.
Functional cookies enable this website to provide you with certain functions and to store information already provided (such as registered name or language selection) in order to offer you improved and more personalized functions.
Performance cookies gather information on how a web page is used. We use them to better understand how our web pages are used in order to improve their appeal, content and functionality.
Marketing / Third Party Cookies originate from external advertising companies (among others) and are used to gather information about the websites visited by you, in order to e.g. create targeted advertising for you.