Tuesday, 5 September 2017

Dates for the 2017 EU NILM Workshop announced!

We’re pleased to announce that the fourth European Workshop on Non-intrusive Load Monitoring will be held on the 6-7th November 2017 in London, UK. The aim of the European NILM conference series is to bring together all of the European researchers that are working on the topic of energy disaggregation in both industry and academia. See http://www.nilm.eu/nilm-workshop-2017 for full details and to register your place.

Important dates

Early registration deadline: 20 September 2017 (free)
Final registration deadline: 20 October 2017 (£50)
Presentation abstract submission: 20th September 2017
Workshop dates: 6-7 November 2017

Call for presentations

We invite attendees to submit presentation abstracts via this Google Form by 20 September 2017. We will aim to build a balanced agenda from a combination of invited talks and submitted abstracts, while the remaining submissions will be invited to present a lightning talk and a poster. Since the workshop will not feature published proceedings, we encourage relevant submissions which have previously appeared at other venues. We also welcome submissions from companies with results or data which they are willing to share with the community.

Call for sponsors

We have a number of sponsorship options for the workshop, including opportunities to give a full presentation, present a demo, and exposure on the website and slides. We need sponsorship in order to provide lunch, refreshments and an evening reception, so please contact us if you’re interested!

We look forward to welcoming you in London!

Tuesday, 4 July 2017

SustainIT 2017 final call for papers

The SustainIT 2017 conference will be held December 6-7, in Funchal, Portugal, and the organisers have specifically encouraged submissions from the field of NILM. While the deadline for registering abstracts is the 7th July (!), full papers aren't required to be submitted until the 21st July.

An interesting point of this conference is that proceedings will be uploaded to IEEE Xplore and IFIP DL, but copyrights will remain with the authors. The organisers believe that keeping the copyrights with the authors is quite important, not only because of respecting the most recent EU policies on Open Access publications, but also because this allows the authors to submit extended versions of their papers to journals of their choice.

The full call for participation can be found at the link below:

Saturday, 27 May 2017

GridCarbon app updated to include solar

One of the benefits of appliance-level disaggregation is the potential to provide deferral suggestions, e.g. consider running the dishwasher later in the day. Such deferral suggestions are typically motivated by either cost (in the form of time-of-use tariffs) or carbon emissions (different power stations are active at different times of day). To help visualise the latter, Alex Rogers (my PhD supervisor) and I released the GridCarbon app, which tracks the carbon intensity of the UK electricity grid in real time.

Over the years, the generation mix of UK electricity has changed substantially, with a large amount of un-metered wind and solar generation appearing on the distribution network. We recently updated both the iOS and Android apps to reflect these changes, using generation estimates of wind and solar provided by ELEXON. Yesterday saw a solar generation record, with 8.7 GW of UK electricity provided by solar at its peak, although we can see from the app that this peak was short-lived:

GridCarbon primarily functions as an educational tool, and aims to visualise and communicate the current status of the UK electricity grid. Our goal is to make this information easily accessible so that it becomes common knowledge, and encourages informed debate about the future of our electricity infrastructure.

Monday, 10 April 2017

Jack's NILM Competition Survey

Jack Kelly recently published the results of a survey which he designed to assess the appetite for a NILM competition. The survey covers a range of topics, from technical questions regarding the sample rate and required features, to practicalities such as where algorithms should run and how often the competition should take place. However, the survey highlights two key issues that make the design of such a competition quite tricky:

Data - As Jack explained in a recent blog post, the collection of a large enough data set is expensive and there is no clear business case for a single organisation to pick up the cost. This is due to the sheer number of sensors per house, duration of data collection and number of houses required. Furthermore, the data set cannot be reused once the data set has been released or even once the accuracy of successive runs of an algorithm have been made available.

Requirements - Almost by definition, every disaggregation company and researcher is tackling the problem from a slightly different angle. Some use a unique sensor, while others require a unique training procedure. Even beyond the differences in disaggregation solutions, there's no clear consensus on issues such as where the competition should run or what training data should be provided.

However, all hope is not lost, given Pecan Street's demonstration that collecting sub-metered data at scale is possible, and also the precedent set by Belkin's competition back in 2013. Furthermore, most participants agreed on a few issues, such as 1 Hz active power being a reasonable place to start.

Jack's post-doc has now come to an end, which means he won't continue working towards running such a competition. If you fancy picking up the challenge, I'd encourage you to put a post on the google group and get involved!

Tuesday, 3 January 2017

COOLL dataset released

The COOLL dataset was recently released by researchers at the PRISME laboratory at the University of Orléans, which contains high-frequency from 12 different types of appliances. Similar to the tracebase and PLAID datasets, multiple instances of the each type were measured, and each instance was measured throughout 20 operations. During each controlled operation, current and voltage data was collected at a sample rate of 100 kHz. The dataset is summarised in an academic paper, and can be downloaded from github after filling in a registration form.