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!

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.

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

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!

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:

http://nilmworkshop.org/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!

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!