Friday 4 November 2016

Energy Futures Lab talk at Imperial College London

I gave a talk at the Energy Futures Lab at Imperial College London this afternoon, which covered some of the data products which my team at Connected Home is responsible for providing to the rest of the business. Below you can find a summary of my talk:

Smart meters will be installed in 26 million UK homes over the next few years in an effort to achieve the country’s carbon emission reduction targets. Such smart meters will conform to the SMETS2 specification, which allows customers to chose whether to upload daily or half-hourly data to their supplier over the cellular network for billing purposes.

At Centrica Connected Home, we developed the My Energy dashboard for British Gas. This dashboard aims to not only visualise energy consumption, but also to extract meaningful insight from the consumption data. The dashboard offers a comparison of the customer’s consumption against similar homes, and also a monthly breakdown of their consumption into six categories; heating, hot water, lighting, entertainment, cooking and other appliances.

For the similar homes comparison, we rephrased this problem as the following question: “can we predict daily consumption given only the customer’s location and answers to a short survey?” We then built an algorithm to answer this question, and optimised the accuracy of this prediction given the huge dataset of all our customers’ actual consumptions. However, we realised that it was also important to balance single-day accuracy against the day-to-day stability of a single customer’s predicted consumption.

For the energy breakdown, we consider the problem again as a prediction problem, in which individual blocks of energy are detected from half hourly data and assigned to one of the six categories based on a range of features, such as magnitude, duration and time of day. We then optimised the accuracy of the algorithm using data collected from the Household Electricity Survey, which measured the consumption of individual appliances in addition to the total household’s consumption.

In addition to My Energy, Connected Home is probably best known for developing the Hive ecosystem of products, including Active Heating, Lighting, Motion Sensors, Door & Window Sensors, Smart Plugs and Boiler IQ. I’ve chosen to focus on Hive Active Heating in the rest of this talk, given that it’s the product that I’ve spent most time working on.

Hive Active Heating is a connected thermostat that allows customers to control their heating from their phone. However, Hive doesn’t instrument the boiler directly, but instead sends control signals to the boiler based on the ambient temperature of the home and the customer’s desired temperature. We’ve recently been experimenting with the possibility of detecting boiler failure from this limited set of features. Such a failure might consist of Hive asking the boiler to heat the home, followed by a decrease in the ambient temperature (rather than the expected increase in temperature). While this algorithm is still in its early stages of development, it illustrates a clear possibility to turn a connected product into a truly smart device.

In conclusion, I believe that smart meters offer huge potential to give customers insight into their energy consumption. Furthermore, I see real potential in the Internet of Things market, not only in connecting everyday appliances to the Internet, but also by enabling the insight and automated control which transforms them into smart appliances.

Monday 31 October 2016

Machine learning & the connected home: useful data or meaningless noise?

Later this week I'll be giving a talk at the Energy Futures Lab on the recent work we've been doing around the data collected from smart meters and the Hive ecosystem. Here are the important details:

  • When? - Friday 4th November 2016 at 13:00
  • Where? - Room 116, South Kensington Campus, Imperial College London
  • Registration - Free, via EventBrite

Abstract


The ongoing national rollout aims to deploy one smart meter to every home in the country by the end of 2020. Furthermore, the market for connected household devices, such as automatic and remote controlled heating and lighting, continues to grow each year. As a result, more and more data is being collected about how we live our lives. This talk explores how machine learning can be used to extract value from this data improve our lives, but also highlights the importance of customer consent and keeping this data secure.

Venue


The seminar will be held in Room 116 of Electrical and Electronic Engineering (building 16 on the campus map). The room is known as the Energy Futures Lab teaching area (or The Bunker). If you are entering the building from Dalby Court/through the building's main entrance the room is down a flight of stairs, through the double doors on your left hand side, turn right at the end of the corridor and it is the second door on your right.

Thursday 20 October 2016

EPRI EU NILM 2016 review

"NILM is a challenging problem. But it’s not impossible." This was one of Prof Bin Yang's five concluding messages of his keynote talk at EU EPRI NILM 2016. I think this sums up pretty much every NILM researcher's feelings, but lets face it, there wouldn't be much much need to hold such a conference if NILM was an easy problem. In his talk, Bin started with the fundamentals of source separation, and went on to relate energy disaggregation to a number of other separation problems, including image segmentation and speaker diarisation. Our other keynote talk was given by Chris Holmes of EPRI, who described their motivation for co-organising the workshop, as well as their recent work in evaluating a large number of NILM vendors in both North America and Europe.


In addition to the two keynote talks, the workshop featured 25 other talks from NILM vendors, academics and utilities. The workshop was attended by roughly 100 people across the two days, from countries far beyond Europe, including Japan and Korea. While we did our best to live stream the event, bandwidth limitations affected the audio and video quality on the first day, but the stream made a miraculous recovery for the second day. A playlist of (most of the) individual presentations is available on YouTube:

https://www.youtube.com/playlist?list=PLJrF-gxa0ImrCOG4rn0b_cgYCTK5n7TLZ

I personally really enjoyed the event, and given the attendance numbers and feedback we've received so far, I think it confirms the demand for NILM-focused events on both sides on the Atlantic. Having said that, I hope to see you all next year, and don't forgot to bring your NILM bingo card ;)


Update 21.10.2016: replaced live stream videos with playlist of individual presentations.

Monday 17 October 2016

EPRI EU NILM 2016 livestream

The stream of day 1 of the EPRI EU NILM workshop is now live:

http://youtu.be/4RARHKiSg08

Update 21.10.2016: A playlist of individual presentations is now available on YouTube:

https://www.youtube.com/playlist?list=PLJrF-gxa0ImrCOG4rn0b_cgYCTK5n7TLZ

Unfortunately the lack of bandwidth at the venue meant only 19 of the 27 talks were of acceptable quality. Apologies to the speakers to the other 8 speakers!

Tuesday 27 September 2016

A competition for energy disaggregation algorithms

Cross-posted from Jack Kelly's blog:

Now that I've (finally!) submitted my PhD thesis, I can focus on designing and implementing a competition for energy disaggregation algorithms. EDF Energy have kindly given me post-doc funding from now until the end of December 2016 to work on the NILM competition.

The broad plan is to first consult with the NILM community and create a specification for the NILM competition which works for everyone. Then I plan to implement a web application which can run the NILM competition.

Right now, I'm writing a survey on the design of a competition for energy disaggregation algorithms. The aim of the survey is to systematically collect feedback about the design of the competition. I plan to launch the survey on the morning of Friday (30th September). Before Friday, I'm really eager to hear feedback on the survey itself. For example: is the survey missing any vital questions? Do some questions not provide sufficient options? Do some questions not make sense?!

Please note that, prior to Friday, the aim is to get feedback on the design of the survey itself. So please don't actually submit any answers yet! I'll write another blog post when the survey is ready to accept answers.

It's probably best to provide feedback about the survey in public on the relevant thread on the Energy Disaggregation Google Group. If you want your feedback to be private then, by all means, email me directly at jack.kelly@imperial.ac.uk!

And please do get in touch if you have feedback on any aspect of the proposed NILM competition.

Monday 19 September 2016

Last chance to register to EPRI EU NILM 2016

We've added a few more spaces to EventBrite and extended the registration deadline until the 3rd October. Register now for your free space: http://www.nilm.eu/

Thursday 15 September 2016

Online NILM Communities

A number of online NILM communities have sprung up over the past couple of years, so in this post I've tried to list all those that I can remember. Please leave a comment if there are any I've missed!

Energy Disaggregation Google Group


This Google Group was set up by Jack Kelly back in January 2015. The group is open to join immediately, and members can post new topics to the group or reply to existing topics. At the time of writing, the group contains 35 threads covering a wide range of topics, including data sets, conferences, job postings and appliance modelling.

NILM Workshop LinkedIn Group


This LinkedIn group was originally set up by our friends at Green Running in 2015 to facilitate networking between attendees of the 2015 EU NILM workshop. The group currently boasts 72 members, and we'll definitely be encouraging attendees of the upcoming 2016 workshop to join the community.

Conduit NILM Users Group


This Conduit Community was set up by PNNL in August 2015 as an online resource to support their open monthly calls aiming to produce a standardised NILM evaluation protocol. I've previously written posts about the outcomes of the first and second conference calls, their decision to develop a data-driven protocol, and also their recent vendor survey.

NILM Wiki


This wiki was set up by a collaboration between Jack Kelly and Green Running in an effort to build a community-driven collection of NILM knowledge. The wiki currently includes pages covering NILM data sets, common appliance power demands and existing NILM companies, although new contributions are encouraged!

Friday 19 August 2016

Announcing EPRI EU NILM 2016

We’re pleased to announce that the European Workshop on Non-intrusive Load Monitoring will be held on the 17-18th October 2016 in London, UK. This year’s workshop is a collaborative effort between the organisers of EU NILM 2014 and EU NILM 2015 and the Electric Power Research Institute (EPRI). 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. The aim of EPRI is to facilitate a collaborative dialogue between industry stakeholders – manufacturers, utilities and researchers, to create opportunities to enable technology maturation and market adoption of NILM devices in the European market. See www.nilm.eu/nilm-workshop-2016 for full details.

Important dates


  • Registration deadline: 17th September 2016
  • Presentation abstract submission: 17th September 2016
  • Workshop dates: 17-18 October 2016

Call for presentations


We invite attendees to submit presentation abstracts via this Google Form by 17th September 2016. We build a balanced agenda from a combination of invited speakers, submitted presentations, lightning talks and a poster/demo session. We strongly encourage new and relevant submissions in the field and also welcome submissions from companies with challenges, results or data which they’d like to share with the community. Possible topics include but are not limited to algorithms, evaluation of NILM algorithms, datasets and applications. Since the workshop will not feature published proceedings, a previous or future appearance at other venues will not be an issue.

Call for sponsors


We have a number of sponsorship options for the workshop available. Options include sponsoring a lunch or the evening reception, exposure on the website and slides, as well as a space for a small information stall at the event. Please contact us via form at the bottom of www.nilm.eu/nilm-workshop-2016 for further information.


We look forward to welcoming you in London!

Friday 29 July 2016

PNNL to use data-driven protocol for NILM vendor evaluation

PNNL recently held their fourth NILM Protocol Development Advisory Group conference call, in which it was decided that they would use a data driven protocol to evaluate the accuracy of NILM products. To give a bit of background to this decision, the choice was between the following two options:

Data driven - use (potentially existing) data collected from real homes to evaluate the accuracy of NILM products

Lab test - collect new data from an artificial lab home, in which the schedule of appliances is programmed rather than operated by humans

In my opinion, this is definitely the right decision given the diversity of loads and schedules of use in real homes. Although theoretically this is possible to simulate in an artificial lab home, in practice I would still be concerned that some reality gap might exist between the data collected from lab homes and real homes. However, monitoring real homes is more difficult than lab homes given the inherent intrusion into people's homes, and clearly a careful approach to data collection will be required to ensure the integrity and usefulness of the resulting data set.

A summary of the meeting is available via the advisory group's Conduit community.

Monday 4 July 2016

NILM Wiki

The much discussed NILM wiki has finally emerged thanks to a great effort from Jack Kelly and the folks at Green Running. So far, the wiki features pages covering the following topics:
If you have published your own data set or if you work for a NILM company, please check it's listed on the wiki. Also, if you have any other information you think would enrich the wiki please feel free to add new content!

Thursday 9 June 2016

Please help design a NILM competition!

Cross posted from Jack Kelly's blog:

Has disaggregation accuracy improved since the 1980s? Which algorithms are most accurate for a given use-case? Which (if any) use-cases are well served by NILM already?

It's pretty much impossible to answer any of these questions with confidence (unless you only consider the tiny number of algorithms for which you have access to executable code). We can't directly compare published results across papers because, when testing the disaggregation accuracy of NILM algorithms, each paper uses different datasets, different metrics, different pre-processing, etc.

This means that we can't measure progress over time. Nor can we decide which NILM algorithms are most promising and which might be dead-ends.

These are bad problems. Let's work towards fixing them.

Some other machine learning communities have had great success running yearly competitions. For example, the ImageNet "Large Scale Visual Recognition Challenge" has been running yearly since 2010. Some regard this competition as having played a crucial role in the recent dramatic increase in the accuracy of image classification algorithms.

The idea of running a NILM competition has been rumbling around for several years. But designing and implementing a NILM competition is hard. The community uses sample rates ranging from monthly to MHz. No single metric is informative for all use-cases. Collecting ground truth data (the power demand of individual appliances) is expensive and time-consuming.

Maybe we can pull this off. The first step is to decide on a design which will work for everyone.

To give us something concrete to debate, we'll outline one way this could work. This is not meant to be definitive! Think of this as the DNA for a clumsy, inefficient animal 500 million years ago. Together, we need to evolve this design into an elegant, efficient beast, well adapted to its environment.

Please shoot holes in this proposal! What won't work for you? What's impractical? What's unfair? What opens the competition up to cheating? How can we make the competition more attractive to researchers? How can we make the competition more informative for the community? How can we simplify the process?

The draft proposal is available on Google Docs. I've linked to a Google Doc rather than copying-and-pasting the proposal into this post so that we can update the proposal as the discussion develops. Please add your comments either to the mailing list discussion; or to the Google Doc (please sign your comment with your name; unless you deliberately want to be anonymous); or if you want to keep your comment private then email Jack directly.

Thanks, (in no particular order) Jack, Mario, Oli, Stephen, Grant, Marco, Peter

Thursday 2 June 2016

PNNL NILM vendor survey

Below is a message to NILM vendors I'm sharing on behalf of PNNL:

The Pacific Northwest National Laboratory (PNNL) continues its work to develop Non-Intrusive Load Monitoring (NILM) test protocols.  Activities to date have focused on the development of a technical working group (NILM vendors, users/potential users, and other stake holders), research and decisions on candidate performance metrics, and the development of performance protocols.  This last activity we are seeking input from the larger NILM vendor community.

Below is a short feedback form to assist in directing the protocol development.  We would appreciate your responses as soon as possible. Please send responses by this email to Joseph.Petersen@pnnl.gov.  We appreciate your time and participation.

NILM Performance Metrics Project:  Status and Feedback Request


Feedback Goal:  To better understand preferences and constraints of proposed metric implementation approaches.  Please consider the two approaches to evaluating NILM performance listed below, and then provide your feedback to the following questions.

Approach 1: Data Driven – NILM devices use a diverse set of previously collected interval data to test device performance.

Approach 2:  Laboratory Testing – NILM devices are connected to actual appliances and/or load simulation systems to test performance.

  1. Is your NILM platform/product capable of accepting 1-second to 1-minute interval data as inputs for disaggregation?
  2. At what sampling interval is your NILM platform/product designed to take measurements or data inputs, e.g., 1 minute, 5 minute, hourly, other?
  3. What specific inputs are necessary for your NILM platform or product, e.g., interval power data, energy data, voltage, current, reactive power, other?
  4. What appliances or end-uses does your NILM product target?
  5. What are the target use cases for your NILM product?
  6. Other comments or questions you’d like to share regarding the development of the Data Driven or Laboratory Testing protocols?

Saturday 21 May 2016

NILM 2016 presentation videos and slides now available

Stephen Makonin has just uploaded the last of the videos to the NILM 2016 Youtube playlist, meaning that you can now easily watch individual talks from the conference. In particular, I'd recommend George Hart's keynote talk: Life after NILM, covering what it was like to do energy disaggregation in the '80s, his passion for mathematics throughout his life, his more recent shift towards art and sculpture, and finally his educational workshops.

The full set of slides and papers relating to each talk are also available via the NILM 2016 program if you'd like to catch up on everything else from the conference too. Happy watching!


Wednesday 18 May 2016

5 things I learned from NILM 2016


The 3rd International Workshop on Non-Intrusive Load Monitoring was held on the 14-15 May 2016 at the beautiful mountaintop campus of Simon Fraser University, Vancouver, Canada. I thoroughly enjoyed the event, and just wanted to summarise a few of my thoughts having had the flight home to digest the weekend's activities.

1. NILM is not dead


Despite the jokes that were thrown around at the European workshop last year, the NILM community is very much as alive as it has ever been. The Vancouver workshop was the first 2-day energy disaggregation conference, the best attended, and in my opinion the most stimulating in terms of presentations and discussions. That being said, NILM is still far from a solved problem. Michael Baker from SBW Consulting presented a paper which evaluated the performance of three NILM vendors, and concluded that "further development of disaggregation algorithms is needed before they are sufficiently accurate to provide customers with accurate estimate of how much they spend on most end uses."

2. Different customers want energy breakdowns for different reasons


Most academic researchers (I'm including myself here) see NILM as a tool to encourage energy efficiency, but utilities also see it as a tool for customer engagement. For example, a perfect monthly energy breakdown might be useful for both, but the disaggregation methodology might be quite different. In the case of energy efficiency the aim might be to identify the rare cases where large energy savings are possible, while in the customer engagement case it might be preferable for the disaggregation result to be more conservative when identifying such edge cases, since false positives are likely to be much more costly in terms of reputation than correct identification.

3. The assumption that disaggregation leads to significant energy efficiency has never been concretely demonstrated


Jack Kelly gave an excellent presentation of his paper which summarised the literature regarding whether disaggregated feedback leads to energy savings. One of the most shocking messages was that "the four studies which directly compared aggregate feedback against disaggregated feedback found that aggregate feedback is at least as effective as disaggregated feedback" (see full paper for details). Jack was very careful to clarify that this does not mean that disaggregated data is useless, but rather that the community desperately needs a large, well-controlled, long-duration, randomised, international study to confidently quantify energy reductions as a result of disaggregated data.

4. An academic energy disaggregation competition is badly needed


The panel discussion following the two algorithm sessions brought a lively debate around what a NILM competition might look like. Phrases like "bring it on!" were thrown around, though it also became clear that defining a scenario (e.g. sample rate, scale) which encouraged broad participation is a real challenge. Furthermore, such a competition would need a strong investment in time from an impartial organiser as well as an expensive process of data collection.

5. NILM researchers love puzzles


George Hart gave an excellent keynote talk describing what it was like to perform energy disaggregation research in the 1980s. He then went on to talk to a transfixed audience about his more recent interests in mathematical sculpture and puzzle solving. However, nothing prepared me for the silence which dropped over dinner when he handed out a series of puzzles (mostly physical blocks which had to be separated or assembled) as every researcher forgot the topic of the conference and indulged in some more traditional problem solving.

Sunday 15 May 2016

Watch NILM 2016 Day 2 Livestream

The stream for day 2 of NILM 2016 is now live:

https://www.youtube.com/watch?v=KlqkP3EVXUY

I'll try to add links to the videos of each talk once they're available.

Friday 13 May 2016

NILM 2016 Livestream

Update 08:46 14.05.2016: new youtube link
Update 09:06 14.05.2016: new youtube link


The 3rd International Workshop on Non-Intrusive Load Monitoring will be held in Vancouver, Canada, from May 14 to 15 2016, at the beautiful mountaintop campus of Simon Fraser University. We are hoping to livestream the event on YouTube via the following link:

https://www.youtube.com/watch?v=3YHBC-xvm4c

This livestream will be a little experimental, so please keep an eye on NILM2016 on Twitter if we encounter any technical difficulties. For those of you who are not able to attend or watch the livestream, we are hoping to upload videos of the presentations to YouTube to be viewed at a later date.

Friday 6 May 2016

Data Management guest lecture

Yesterday I gave a guest lecture on Gopal Ramchurn's Data Management course at the University of Southampton. It was great fun exposing the first year Computer Science undergrads to technologies like Cassandra, Elastic Search and Kafka, while also contradicting a lot of what I was taught about database design on the same course 9 years ago. My favourite questions from the (surprisingly attentive) audience were:
  • Doesn't all that data replication negate the point of using a database in the first place?
  • Why wouldn't you pay for supported packages of open source technologies?


If you're interested in a similar guest lecture on your course please don't hesitate to get in touch!

Friday 29 April 2016

NILM 2016 proceedings available and last chance to register

The proceedings of the upcoming NILM 2016 conference are now available for download. Furthermore, the full schedule has been released, which includes:

  • Day 1 keynote by Lyn Bartram
  • Day 2 keynote by George Hart
  • 13 oral paper presentations
  • Lightning talks and poster session
  • 5 sponsor talks
  • Industry & power utilities discussion panel
The registration deadline has been extended until 1st May 2016, so please register now if you'd like to attend. I look forward to seeing you there!

Monday 18 April 2016

PNNL User Group 2nd Meeting

PNNL organised the second meeting of their NILM User Group on 5th April 2016. The meeting featured a reminder of the priority use cases resulting from the first meeting of the user group, a discussion of whether PNNL's NILM evaluation should use data from real homes or lab homes, and also a presentation of PNNL's investigation into the desirability of a wide range of accuracy metrics. Notes from the meeting have been uploaded to the Conduit community, and the next meeting is scheduled to take place in the next few weeks in order to finalise the metrics for PNNL's study, as well as present the plan for data collection.

Wednesday 13 April 2016

NILM 2016 – Workshop Program

Cross posted from Stephen Makonin's blog:

The program for NILM 2016 has now been posted at http://nilmworkshop.org/2016/NILM2016_Program.pdf. The TPC has accepted 13 papers for presentation and will also feature 12 additional papers presented as posters. George W. Hart (credited as being the founder of NILM research) and Lyn Bartram (world renowned eco-visualization researcher) will be our keynote speakers.

The 3rd International Workshop on Non-Intrusive Load Monitoring (NILM) will be held in Vancouver, Canada from May 14 to 15, 2016. This year’s venue will be the beautiful mountaintop campus of Simon Fraser University (SFU) which is located in the neighbouring municipality of Burnaby.

The mission of this workshop is to create a forum that can unite all the researchers, practitioners, and students that are working on the topic of energy disaggregation. The main objective of this event is to review the main types of approaches that have been explored to date to solve the problem of electricity disaggregation, and to then discuss possible paths forward knowing what has been tried and what has yet to be experimented. We also intend to have a group discussion about possible solutions to the growing need for standardized datasets and performance metrics that can allow the field to move forward, as well as possible areas of collaboration among different research groups.

Hope to see you there!

Stephen Makonin, Workshop General Chair, NILM 2016

Thursday 25 February 2016

Is deep learning the future of NILM?

Deep learning has recently revolutionised a number of well-studied machine learning and signal processing problems, such as image recognition and handwriting recognition. Furthermore, long short-term memory architectures have demonstrated the effectiveness of applying recurrent neural networks to time series problems, such as speech synthesis. In addition to the impressive performance of these models, the elegance of learning features from data rather than hand crafting intuitive features is a highly compelling advantage over traditional methods.

In the past year, deep learning methods have also started to be applied to energy disaggregation. For example, Jack Kelly demonstrated at BuildSys 2015 how such models outperform common disaggregation benchmarks and are able to generalise to previously unseen homes. In addition, Lukas Mauch presented a paper at GlobalSIP 2015 describing how sub-metered data can be used to train networks to disaggregate single appliances from a building's total load. Most recently, Pedro Paulo Marques do Nascimento's master's thesis compared a variety of convolutional and recurrent neural networks across a number of appliances present in the REDD data set. Each piece of research demonstrates that there's real potential to apply deep learning to the problem of energy disaggregation. 

However, two critical issues still remain. First, are the huge volumes of sub-metered data available which are required to train such models? Second, are the computational requirements of training these models practical? Fortunately, training can be performed offline if only general models of appliance types are to be learned. However, if learning is required for each individual household, surely this will need to take place on cloud infrastructure rather than embedded hardware. I hope we'll get closer to answering these questions at this year's international NILM conference in Vancouver!

Thursday 18 February 2016

NILM 2016 registration and paper submission now open



The 3rd International Workshop on Non-Intrusive Load Monitoring (NILM 2016) will be held in Vancouver, Canada from 14-15th May 2016, at the beautiful SFU Burnaby Mountain Campus. Registration for the conference is now open so make sure you book your place by 15th March (though please book early as space might be limited). The paper submission site is also now open until 24th April, along with an updated call for papers. We've also put together an excellent programme committee to ensure each paper receives feedback from experts in the field. For full details and updates, see the conference website:

Wednesday 27 January 2016

PNNL NILM User Group

The Pacific Northwest National Laboratory (PNNL) has set up on online NILM user group via the Conduit platform. The user group consists of a monthly call, followed by an online summary and discussion. The group aims include:
  • vetting NILM metrics and test protocols
  • exploring utility use cases –mapping NILM characteristics and performance levels to each use case
  • better understanding non-US products and use cases;
  • maintaining a list of NILM products, including overviews on new products
  • sharing field test results
  • informing future NILM projects, including surveys to provide feedback on projects
The first call was on 6th November 2015, and gave an overview of PNNL's recent analysis of the performance of a number of NILM vendors in the Northwest Energy Efficiency Alliance's NILM field study. Challenges with evaluating the performance were also highlighted along with planned next steps to overcome these challenges and potentially accelerate the development of NILM technologies. EPRI also gave an overview of the NILM segment of their EE Symposium. The full webinar is available to watch on demand.

The user group welcomes any researchers who wish to join and contribute to the discussion. See you on the next call!

Wednesday 20 January 2016

EPRI's 2015 NILM workshop

The Electric Power Research Institute (EPRI) has been a long term research player in the field of NILM since beginning development of NIALM systems in the 1980s. In conjunction with its efforts of laboratory and field trials, EPRI has been attempting to facilitate an industry effort to develop “consensus based” performance metrics, create protocols to test metric impacts and demonstrate the need for product labels. To this end, EPRI hosted a NILM workshop on 13 November 2015 in Orlando, FL, to follow on from the previous 2013 EPRI NILM workshop in Palo Alto, CA. The event was attended by disaggregation vendors, utilities, universities, a U.S. Department of Energy National Lab and research organisations and covered topics such as current EPRI research, use cases, utility and consultant experiences with NILM and product labelling (see full slide deck). One of the key outcomes of workshop was the recognition of gaps related to NILM metrics and how to address them as an industry through collaborative efforts. Specifically the need to define an analytical framework to understand metric characterisation, their impact on the representation of NILM device performance and ways to assess these impacts.

The meeting was conducted for the following two-fold objectives:
  • Facilitate a collaborative dialogue between product manufacturers, utilities and other stakeholders such as national labs and researchers for identifying gaps and new opportunities that enable adoption of NILM technologies.
  • Propose a set of “straw man” metrics to stimulate discussion and focus efforts to create working groups and follow-on activities to address identified gaps.

The discussions covered four key areas:
  • Value of end use load data to utilities and new use cases
  • Current research
  • Practitioner experiences
  • Quest for metrics and product labels

The collaborative industry group arrived at the following conclusions and expressed interest in the following activities for the future:
  • Non-intrusiveness is a significant attribute of the technology that makes it appealing for both utilities and customers.
  • Customer interfaces such as mobile apps and web dashboards play a decisive role in persuading customers to use the technology and benefit from the information reported
  • Metrics and product labels can improve the credibility, visibility and confidence for use of these products both in utility and customer applications.
  • Automatic load labelling is a must for high-value utility applications, and this characteristic may well be the “deal breaker” for some utilities.
  • Metrics need to be simple and articulate so that utility customers can derive tangible benefit. EPRI’s set of metrics is a good start and lays the ground work for future work to assess metric characteristics and impacts on performance representation
  • Other industry stakeholders such as PNNL’s NILM user group effort should coordinate their efforts to represent industry interest and requirements. (more on this soon!)

The following next steps are proposed:
  • Identify use cases that can lend themselves well to the use of AMI data and demonstrate customer integration case studies.
  • Start engaging with NILM vendors and interested utilities for pilots targeting the commercial sector by building type.
  • AMI meter manufacturers are interested to develop embedded NILM solutions which can be included as part of the meter hardware and software. Partner with AMI meter manufacturers to define requirements for such apps for various use cases.
  • Continue to track the NILM market space and understand product performance and features.
  • Engage utilities and vendors through laboratory trials and field assessments as newer technologies become available 
  • Continue to assess NILM metrics and test protocols. By virtue of the metrics proposed at the meeting, EPRI should work to create analytical frameworks to assess impact of metrics on performance representation.
  • Exploring utility use cases, map NILM characteristics and performance levels to each use case
  • Informing of future utility and research projects and release the data to vendors for algorithm development and refinement.

Many thanks to Chris Holmes and Krish Gomatom for contributing most of the material for this post!

Thursday 7 January 2016

REFIT analysis using NILMTK converter

I recently wrote a NILMTK converter for the REFIT data set, which allowed me to do a quick piece of analysis over the data set which I wanted to share. See my post on the release of the data set for further details about REFIT.

Below is a plot showing the duration of data recorded from each of the 20 houses. We can see that the installations took place between September 2013 and March 2014, and data continued to be collected until July 2015. The data set is pretty complete, apart from a gap of one or two months during early 2014, and a few small gaps mid 2015.



Below is a bar graph showing the number of instances of each appliance category across the data set. It can be seen that the television is monitored in all 20 houses (while the washing machine is monitored once in 18 houses, and twice in one house), while other common kitchen appliances, such as the microwave, dish washer and fridge freezer, were monitored in most houses. However, no lighting or oven/hobs were monitored in the data set, since only plug monitors were used.



Below is a histogram showing the proportion of the total electricity that was also sub-metered by the plug-level monitors. It can be seen that only 30-50% of the electricity was sub-metered in 16 out of the 20 houses, while no houses managed to sub-meter greater than 65% of the electricity consumption. This is likely due to a range of appliances which hardwired into the ring main consuming a large amount of energy, which could not be measured using plug-level monitors.



Below is a scatter plot showing the average daily energy consumption of each appliance instance in the data set. It can be seen that white goods often consume the most energy, with the dish washer, fridge freezer, tumble dryer and washing machine all consuming large amounts of energy. However, it should be noted that I've limited the y-axis to 2.5 kWh/day, despite one fridge freezer consuming nearly 6 kWh/day and one dishwasher consuming more than 3 kWh/day.

Wednesday 6 January 2016

From Southampton to London

This week I finally said goodbye to Southampton as I started my new full-time role as a Data Scientist at British Gas Connected Homes. I'm definitely a little sad to be leaving my academic life behind me, but I'm also excited about the new challenges that lie ahead. The Connected Homes team are a fantastic group of people, and are the ones responsible for products such as the Hive thermostat and the My Energy dashboard. I'm still hoping to continue writing this blog and to stay in contact with the NILM community, though I doubt I'll be writing as many papers. Fingers crossed I'll still make it to Vancouver though for NILM 2016!

Below is a photo I shared this time last year of the Connected Homes' London office, which is probably not what you might expect from the UK's largest gas and electricity supplier!