Marc Wenninger, Andreas Maier & Jochen Schmidt have recently released DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany. The data set contains recordings from 15 homes over a period of up to 3.5 years, in which 50 appliances have been recorded at a frequency of 1 Hz. The data set focuses on appliances of significance for load-shifting purposes, such as dishwashers, washing machines and refrigerators. One home also includes three-phase mains readings that can be used for disaggregation tasks. Additionally, DEDDIAG contains manual ground truth event annotations for 14 appliances, that provide precise start and stop timestamps. The authors have also released source code of the data collection system, as well as a python command line tool for loading the data.
Disaggregated Homes
My name is Oliver Parson, and I'm currently employed as a Senior Data Scientist at Bulb. I'm interested in investigating the ways in which machine learning can be used to break down household energy consumption data into individual appliances, also known as Non-intrusive Appliance Load Monitoring (NILM) or energy disaggregation.
Tuesday, 20 July 2021
Sunday, 7 February 2021
NILM 2020 presentation videos available on Youtube
The NILM 2020 conference was held online in November last year, and featured 26 presentations on recent progress in the field. The individual talks are now available on Youtube:
https://www.youtube.com/playlist?list=PLhs3Zf0KIDKnzUNwf8sXeN7QjsLTmlvnP
An introduction to the conference can be found in the following video:
Wednesday, 18 November 2020
Thursday, 30 July 2020
NILM 2020 to be held online in November
The NILM 2020 Workshop will be a one day online conference held during the week commencing 16 November 2020. The workshop will be jointly organised by the International and European NILM Workshop teams, and will be free to attend. For the first time, the event will appear as a workshop of the larger ACM BuildSys conference, and accepted papers will be published in the ACM digital library. The paper submission deadline is 21 August, although abstracts should be registered by 14 August. Further details (including the conference date, registration and paper submission) will appear on the NILM 2020 Workshop website as they are finalised.
Monday, 29 June 2020
DEBS 2020 NILM Grand Challenge
The DEBS Grand Challenge is a series of competitions in which both academics and professionals compete with the goal of building faster and more accurate distributed and event-based system. This year, the DEBS Grand Challenge focuses on NILM, with the goal of detecting when appliances contributing to an aggregated stream of voltage and current readings from a smart meter are switched on or off. The track has already closed to submissions, but the submissions will be presented at the DEBS 2020 conference, which will be held on Thursday 16th July. The whole conference is virtual and registration is free for participants. Registrants have access to the 5 day online program, including tutorials, keynotes, and main conference presentations, as well as access to the Slack discussion channel. The papers can also be downloaded via the online programme.
Thursday, 4 June 2020
IDEAL Household Energy Dataset released
The IDEAL Household Energy Dataset was recently announced by researchers at the University of Edinburgh. The data set description reads:
The IDEAL Household Energy Dataset comprises data from 255 UK homes. Alongside electric and gas data from each home the corpus contains individual room temperature and humidity readings and temperature readings from the boiler. For 39 of the 255 homes more detailed data is available, including individual electrical appliance use data, and data on individual radiators. Sensor data is augmented by anonymised survey data and metadata including occupant demographics, self-reported energy awareness and attitudes, and building, room and appliance characteristics.
The IDEAL Household Energy Dataset comprises data from 255 UK homes. Alongside electric and gas data from each home the corpus contains individual room temperature and humidity readings and temperature readings from the boiler. For 39 of the 255 homes more detailed data is available, including individual electrical appliance use data, and data on individual radiators. Sensor data is augmented by anonymised survey data and metadata including occupant demographics, self-reported energy awareness and attitudes, and building, room and appliance characteristics.
Monday, 23 March 2020
George Hart's 1984 progress report: "Nonintrusive Appliance Load Data Acquisition Method"
Stephen Makonin recently made George Hart's 1984 progress report available, titled "Nonintrusive Appliance Load Data Acquisition Method". This is one of the earliest reports describing a NILM system, and shortly proceeds Hart's 1985 second progress report and 1992 summary report. Happy reading!
On another note, George Hart also gave the keynote presentation at the 2016 International NILM Workshop in Vancouver, where he talked about NILM in the 1980s, and his more recent interests in sculpture and education.
On another note, George Hart also gave the keynote presentation at the 2016 International NILM Workshop in Vancouver, where he talked about NILM in the 1980s, and his more recent interests in sculpture and education.
Subscribe to:
Posts (Atom)