Friday 25 May 2012

NIALM in industry

Since the Pittsburgh workshop I've learnt a lot about industry's perspective of NIALM. Academic work is often criticised for solving simplified problems, and I believe it's important to understand what our friends in industry believe to be the real-world problems. This post is meant to list the companies I'm aware of that are working in this field, and summarise their approach to energy disaggregation. As always, please leave a comment or drop me an email if you know of any inaccuracies or omissions.

AlertMe (now part of Centrica Hive), Cambridge, UK

AlertMe is a company focusing on household monitoring for energy reduction and security purposes. Their Analytics package is able to use second by second measurements to disaggregate the whole-home data to identify individual appliances, analyse their performance and provide personalised feedback and recommendations.

Bidgely (formerly MyEnerSave), CA, USA

Bidgely is a meter-agnostic cloud-based electricity disaggregation company focused generating actionable appliance-level feedback from second to minute level aggregate power data. Their web interface allows users to either connect third party meters (TED, WattVision etc.). In addition, customers are able to upload data collected from smart meters to Bidgely's platform for analysis.

EEme (now part of Uplight), NC, USA

EEme are a spin-out from Carnegie Mellon University, who apply energy disaggregation to 15-minute smart meter data to provide demand side management analytics. EEme released a report describing the accuracy of disaggregation product as calculated by Pecan Street’s 3rd party evaluation tool. The evaluation tool which provided EEme with 15-minute aggregate smart meter data and weather data from hundreds of homes, and required EEme to return monthly totals for four of the largest energy consuming appliances.

Fludia, Paris, France

Fludia is a French company specialising in energy management, and aim to provide their customers with energy efficiency technology. They have developed a device to retrofit non-smart meters, called Fludiameter, such that 1 minute resolution energy data can be collected without installing a whole new meter. Fludia also provide a tool to break down electricity consumption into its end uses, called Beluso, which makes use of household aggregate data and also information entered from a household survey.

Homepulse (formerly WattGo), Aix-en-Provence, France

Homepulse is a French company whose technology disaggregates electricity and gas consumption in-near real-time into categories, such as standby, cold appliances, hot water, home appliances and heating. The company also released a whitepaper detailing the aggregate monitoring of thousands of households along with the collection of a range of metadata, which forms the training data for their algorithms.

Informetis, Japan

Informetis are a spin out of Sony R&D, whose technology offers both historic appliance-specific energy breakdowns and real-time disaggregation. Furthermore, their product aims to detect abnormal power consumption of individual appliances. The product currently works with either a custom plug-in sensor, or a smart meter running custom firmware. In July 2015, Informetis expanded the company by opening a second office in Europe, operating out of Cambridge in the UK.


LoadIQ are a company focusing on electricity disaggregation within commercial and industrial domains. The company offers solutions aimed at reducing business' costs as a result of inefficient electricity consumption.

Navetas, Oxford, UK

Navetas is a spin-out company from the University of Oxford who have partnered with a meter manufacturer to focus upon disaggregating appliance energy consumption given the high-resolution aggregate data.

Neurio (from Energy Aware), Vancouver, BC, Canada

Neurio recently raised Kickstarter funding to develop their electricity disaggregation technology, which consists of a hardware sensor featuring two CT clamps, capable of reporting voltage, current, real power and power factor at 1 second intervals. The company also offer a cloud-based service which breakdown your household electricity usage into individual appliances.

Onzo, London, UK

Onzo is a London-based energy analytics company, who recently sold their energy display business to SSE Labs, allowing them to concentrate solely on data analytics. Their website boasts a proprietary energy knowledgebase containing tens of thousands of household's energy data at a range of resolutions, as well as thousands of energy signatures from individual appliances from a range of manufacturers. Furthermore, their disaggregation algorithms not only infer the energy consumption of appliances, but also determine household occupancy schedules and appliance diagnostic information.

PlotWatt, NC, USA

PlotWatt are a meter-agnostic cloud-based electricity disaggregation company focused on disaggregating second to minute level aggregate power data. Their web interface allows users to either connect third party meters (TED, WattVision etc.) or upload files of their consumption data.

Powersavvy, Castlebar, Ireland

Powersavvy is a company looking to highlight energy savings to both households and businesses. They offer their own meter, which can be installed for either 6 days or indefinitely, and is used to provide disaggregated advice based on the data they collect. Their website quotes that savings of 30% can be easily achieved using their products.

Sense, MA, USA

Sense are a consumer-oriented startup based in Cambridge, Massachusetts, doing sub-second level monitoring of current and voltage through 2 current sensors attached to the service mains in the electric panel. On 01.09.16 Sense received $14M in series A funding to grow the business.

SmartB (from Yetu), Berlin, Germany

SmartB are the energy disaggregation arm of Yetu, who offer a smart home platform which connects household appliances, micro-generators, micro-storage and smart meters via a home gateway. Their home energy management system allows household occupants to view their live or historic household aggregate power demand. Furthermore, they offer a software-based disaggregated breakdown of this 1 second smart meter data. The system also notifies the household occupants if an appliance has consumed significantly more energy than the national average, and offers personalised suggestions for saving energy.

Verdigris, CA, USA

Verdigris is a silicon valley start-up offering Building.AI, a platform for building intelligence. The product consists of a number of circuit panel CT clamps and a disaggregation software package. As a result, they're able to provide appliance-level energy breakdowns, real-time fault detection and persistent building commissioning.

Verlitics, (formerly Emme), OR, USA

Verlitics is a cloud-based company which use bespoke high sample rate meters to provide electricity disaggregation results to domestic customers. They offer web and smartphone interfaces to their home-owners or businesses allowing them to view their disaggregation electricity usage.

Watt-IS, Torres Vedras, Portugal

Watt-IS are an analytics company which aim to disaggregate smart meter data collected by utilities to produce appliance-level energy consumption data and actionable feedback which could be provided to customers. Such feedback includes the potential savings from replacing a refrigerator, reducing the whole-home standby power, and also shifting demand to off-peak times.

Wattics, (formerly Veutility), Dublin, Ireland

Wattics is a software company, partnered with EpiSensor, who have previously provided disaggregated appliance level data from a single point of measurement. Their on-line dashboard identified unneeded or deteriorating appliances and suggested energy saving measures. However, Wattics not longer offer disaggregation functionality.

Wattseeker (from Qualisteo), Nice, France

Wattseeker offer a datalogger, which includes a number of current clamps and options to upload data via 3G, Ethernet or Wi-Fi. These current clamps must sample the current and voltage at a kHz rate since real and reactive power are reported, along with harmonics etc. However, the installation does require a short shutdown of the building's power. Their disaggregation system, LYNX, then disaggregates the electricity consumption to provide actionable energy saving suggestions. Their website indicates that each current clamp can disaggregate up to 12 appliances, with an accuracy of +/- 2%.

Watty, Stockholm, Sweden

Watty is a startup company closely linked with the KTH Royal Institute of Technology. Rather than focusing specifically on energy disaggregation, Watty is an energy analytics company that focuses on producing the insight required to save energy and money for specific buildings.


  1. Really useful and interesting post, thank you. Over the past few months, I've made a few notes about commercial systems which I've just thrown together into a PDF:

    I wonder if we should start a NILM wiki?!

  2. And this page lists a few more:

  3. Hi Jack, thanks so much for the links.

    I wasn't aware AlertMe were working on NIALM, and hadn't even heard of Sentec or Veutility! However, I can't find any information on their public facing websites. Is there any chance you can point me at the information you found so I can update my list?

  4. Hi Oli,

    Sure thing. The AlertMe website has a few details here:

    Unfortunately the Veutility website has been inaccessible for a while. They appear to have allowed their domain name to expire, so I suspect they are no longer trading (perhaps they discovered disaggregation on real data is a tough challenge?!).

    Bizarrely enough, both Onzo and Sentec don't mention "Coracle" on their websites (perhaps it didn't perform well?). But here's a press release dating back to 2008:

    By the way, I'd really like to ask your opinion on something... prior to reading you blog this morning, I wasn't aware of either PlotWatt or Bidgely. Looking at their websites, it's easy to get the impression that "disaggregation is solved". Given that I'm 8 months into a PhD on disaggregation, this is somewhat disheartening news! So I was wondering what your thoughts are about pursuing a disaggregation PhD given that several companies claim to have "solved" it (at least that's the impression their public websites give)?

    Here's my own attempt to comfort myself that there's still plenty of work to be done: Digging deeper into their websites, it seems that both services can only disaggregate a handful of loads (fridge, furnace, dryer) so I guess there's still plenty of work to be done to disaggregate more appliances per home. And Bidgely give the impression that they're hand-building disaggregation algorithms on an appliance-by-appliance basis rather than constructing a general-purpose NILM system (I could be wrong about that). And of course the presentations PlotWatt and Bidgely gave at the NILM workshop earlier this month make it clear that they haven't completely nailed disaggregation. And, even if PlotWatt and Bidgely had nailed the problem, it'd still be very useful to add to the public-domain knowledge about NILM.

    Does that sound about right?!

  5. This comment has been removed by the author.

  6. Hi Oli,

    Sure thing. Alert Me have some details here:

    Unfortunately Veutility's website has been down for a while. A whois search reveals that both domain names were due to be renewed in April 2012. Neither domains were renewed. It's not clear if Veutility is still trading. A search on the Irish companies registration office gives their status is “normal” but their “next accounts receivable” date was July 2011.

    Onzo and Sentec appear to have removed all mention of Coracle from their website. I think I got my info from here: and here:

    By the way, I'd really like to ask your opinion on something. Before reading your blog this morning, I hadn't heard of either PlotWatt or Bidgely. A quick glance at their websites gives the impression that "disaggregation is solved". This is somewhat disheartening news given that I'm 8 months into a PhD on disaggregation! I was wondering what your thoughts might be on doing a PhD in disaggregation given that several companies seem to already be doing it?

    My own attempt to comfort myself that there's still work to be done goes something like this:

    Closer inspection of Bidgely's service suggests that it can be improved upon. The “consumption by appliances” pie chart at shows five categories: pool pump 21%, dryer 11%, furnace 9%, fridge 11% and others 47%. So the largest single category, by some margin, is “others” (i.e. appliances uncategorised by the system). So there is still plenty of work to be done to disaggregate more appliances. It's a similar situation for PlotWatt's website. PlotWatt also, of course, listed a bunch of challenges in their workshop presentation.

    There is clearly a lot of commercial interest in disaggregation (which is great) but unfortunately there seems to be almost no information regarding the performance of these systems or the design of the algorithms. There are hints that commercial disaggregation systems are, at present, only able to disaggregate a few loads, with a focus on large two-state loads (which are the easiest to disaggregate). So it appears that the commercial sector is some distance from providing a full solution to the problems we academics are working on, namely disaggregating as many appliances as possible using standard, low-sample-rate meters. Even if a commercial company had completely solved the disaggregation problem, there would still be value in creating public-domain disaggregation algorithms.

    Does that sound about right?!

  7. Also, add Wattics to that list.

  8. Big companies like Bosch and Samsung are working on this too (both were present at the NILM conference)

  9. Hi Suman,

    Thanks for the comment. I'm aware of the work that Bosch and Samsung are doing within the energy disaggregation field, but I'd only included companies in this post who have a public facing webpage describing their product. If you've seen such pages please send them my way!

    Sorry for the slow reply,

  10. One more to add to the list:

  11. Another NIALM compagny in France :

  12. Another company in Belgium!

    1. There's always more!

    2. Thanks loads for this list. I've just checked through this list and I think the SiteSage product by Powerhouse Dynamics does not do NILM: instead I think they use intrusive monitoring of individual circuits (and possibly taking data from the building management system too; but I'm not sure about this!)

    3. I've just received confirmation from Powerhouse Dynamics that SiteSage does not do NILM.

  13. Hi Oli,

    Thanks for your post. And do you know any publication using occupancy schedule as a feature for disaggregation algorithm? This feature was also mentioned in other papers but there's no any reference.

    1. This one springs to mind:
      which uses a conditional hidden Markov model to capture dependencies on time of day and day of week. You can see these variables represented as c1 and c2 in fig 9 on page 7. I'm sure many other papers have done something similar though!

    2. Actually, that paper is exact one that mentioned the daily schedule (but have no reference).

      I expected to find out more about factors that may impact on such schedule (e.g. personal jobs, plan, etc) rather than a general time of day, week. Such details may give more information about usage patterns of appliances.

  14. Another company for the list:

  15. And another company (!):

  16. Another company: - they claim to do appliance health monitoring: "Appliance Health Monitoring tracks and analyzes the energy patterns of appliances in the home to promptly alert users of problems and provide actionable tips, solutions, and incentives to address them." although it's possible that powerley don't do disaggregation, instead they collect data from smart appliances.

  17. Hi Oliver,
    Another company to add to your list: Sense We are a consumer-oriented startup based in Cambridge, Massachusetts doing sub-second level monitoring of current and voltage through 2 current sensors attached to the service mains in the electric panel. We'd appreciate being added to your list as we are currently expanding our team and looking for data scientists to assist in analysis of the substantial data flow we are getting from live installations. We're looking forward to attending the May workshop!

    1. I've just added you to the list. Looking forward to meeting you at the Vancouver workshop!

  18. Another company:

  19. another small update for the list: the post says of Bidgely that "Their website indicates that USA Smart Meters will also be able to upload data to their website, although this functionality is not available yet.". That functionality is definitely available now. e.g.: and

    1. Thanks Jack, I've uploaded the post accordingly :)

  20. I checked with them and Wattics no longer do disaggregation

  21. Neurio's API docs: Looks nice! Appears to include full disag timeseries for appliances. Supported appliances: air_conditioner, dryer, electric_kettle, heater, microwave, other, oven, refrigerator, stove, toaster, unidentified

  22. Two more quick updates (don't worry about updating the blog post if you don't have time - I think it's sufficient to just use the comments to accumulate new knowledge... until we have a wiki...):

    Verdigris emailed me to let me know that their product *was* called '' but is now just called 'Verdigris'.

    And Stephen Makonin told me about this NILM company:

  23. Great Blog you got here. Getting a good insight about NIALM and its research potential. Keep up the good work. Thank you for sharing.

  24. Oliver - A few more products to be added -, Ecotagious, Ecoisme ( - all based out of the USA.

    1. Thanks Krish! I already have Sense on my list, but I'll add the others when I get a moment :)

  25. Kindly anyone explain me what's meant by semisupervised approach for energy disaggregation? If I apply clustering for on-off grouping of events and then training data set for classification, can I say that I've used semi supervised approach?
    Pls guide me the energy disaggregation researchers.

    1. Semi-supervised learning algorithms typically combine (a small amount of) labelled data with (a large amount of) unlabelled data for training. Since you use unlabelled data in the clustering phase followed by labelled data in the classification phase, it sounds like semi-supervised learning in my opinion. However, 'labelled data' is not particularly well-defined in the NILM field. Sometimes 'labelled data' refers to sub-metered appliance power data, while in other cases it's used to refer to the state of an appliance at a point in time (e.g. on or off).


Note: only a member of this blog may post a comment.