NILM2022
On behalf of the organizing committee, we would like to invite you to participate in the 6th International Workshop on Non-Intrusive Load Monitoring (NILM). The workshop will be held on November 2022, in conjunction with the ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys).
NILM (or disaggregation) is a growing research field which began in 1985 with a report written by George W. Hart (MIT) for Electric Power Research Institute (EPRI). NILM is used to discern what electrical loads (e.g., appliances) are running within a home/building using only the aggregate power meter. Why? To help occupants understand how they and their appliance use energy so that they could conserve to either save money, the environment, or both.
The mission of this workshop is to serve as a forum for bringing together all the researchers, practitioners, and students that are working on the topic of energy disaggregation around the world. To this end, NILM 2022 will be held in hybrid format.
We are looking forward to welcoming you at this next gathering of our community!
COMMITTEE
-
General Co-Chairs
Lucas Pereira, ITI/LARSyS, Instituto Superior Técnico
Stephen Makonin, Simon Fraser University
Wenpeng Luan, Tianjin University
-
Organizing Committee
David Irwin, University of Massachusetts, Amherst
Lina Stankovic, University of Strathclyde
Lucas Pereira, ITI/LARSyS, Instituto Superior Técnico
Stephen Makonin, Simon Fraser University
Wenpeng Luan, Tianjin University
-
Program Committee Chairs
Lina Stankovic, University of Strathclyde
-
Technical Program Committee
Andreas Reinhardt, TU Clausthal
Anthony Faustine, ITI/LARSyS, Instituto Superior Técnico
Bochao Zhao, Tianjin University
Bo Liu, Tianjin University
Christoforos Nalmpantis, Aristotle University of Thessaloniki
Christoph Klemenjak, University of Klagenfurt
David Irwin, University of Massachusetts, Amherst
Dimitrios Doukas, NET2GRID
Dimitris Vrakas, Aristotle University of Thessaloniki
Emanuele Principi, Università Politecnica delle Marche
Haiwang Zhong, Tsinghua University
Iosif Mporas, University of Hertfordshire
Lina Stankovic, University of Strathclyde
Lucas Pereira, ITI/LARSyS, Instituto Superior Técnico
Maria Kaselimi, National Technical University of Athens
Mario Bergés, Carnegie Mellon University
Mingjun Zhong, University of Aberdeen
Nipun Batra, IIT Gandhinagar
Oliver Parson
Peter Davies, Austin Consultants
Shiming Tian, China Electric Power Research Institute
Wenpeng Luan, Tianjin University
IMPORTANT DATES
- Paper Submission Due:
August 2131September 11, 2022 AoE - Notification of Acceptance:
September182330, 2022 AoE - Final Paper Due:
October27, 2022 AoE - Presentation Video Submission:
October 28, 2022 AoE - Workshop Date: November 11, 2022 08:30 to 17:00 ET
KEYNOTE
REGISTRATION
Reduced fees for online participation are now available.
Registrations are made via SenSys/BuildSys 2022. Follow the links below for details and to proceed with your registration.
Note that an accepted workshop contribution needs at least one registration for the workshop day. Only contributions that have at least one registered author, and are presented at the worskshop will be made available in the final proceedings.
Registration Details Register Here
PROGRAM & PROCEEDINGS
| Time (ET) | Topic | Presentation Details |
|---|---|---|
| 08:30 | Doors Open / Stream Begins | |
| 09:00 | Welcome Address | |
| 09:30 | Keynote | Five Predictions for the NILM Industry Oliver Parson |
| 10:30 | Morning Break | |
| 10:45 | Technical Session 1 (Chair: Sean Barker) | Identifying Impactful Devices on Disaggregation Performance Sean Barker, Anna Leitner, Andy Stoneman (Bowdoin College) |
| A Case Study on Obstacles to Feasible NILM Solutions for Energy Disaggregation in Quebec Residences Sayed Saeed Hosseini (University of Quebec at Trois-Rivieres); Benoit Delcroix (Hydro-Quebec Research Institute); Nilson Henao, Kodjo Agbossou, Sousso Kelouwani (University of Quebec at Trois-Rivieres) | ||
| Using Explainability Tools to Inform NILM Algorithm Performance: A Decision Tree Approach Rachel Stephen Mollel, Lina Stankovic, Vladimir Stankovic (University of Strathclyde) | ||
| 12:00 | Noon Break | |
| 13:00 | Technical Session 2 (Chair: Burak Gunay) | Unsupervised Energy Disaggregation Using Time Series Decomposition for Commercial Buildings Narges Zaeri Esfahani, Burak Gunay (Carleton University); Araz Ashouri (National Research Council Canada) |
| An Unsupervised Load Disaggregation Approach based on Graph Signal Processing Featuring Power Sequences Xuhao Li, Bochao Zhao, Wenpeng Luan, Bo Liu (Tianjin University, China) | ||
| LightNILM: Lightweight neural network methods for non-intrusive load monitoring Zhenyu Lu, Yurong Cheng (Beijing Institute of Technology); Mingjun Zhong (University of Aberdeen); Wenpeng Luan (Tianjin University); Ye Yuan, Guoren Wang (Beijing Institute of Technology) | ||
| 14:15 | Technical Session 3 (Chair: Lucas Pereira) | Appliance Recognition with Combined Single- and Multi-label Approaches Marco Manolo Manca (University of Cagliari); Anthony Faustine, Lucas Pereira (ITI, LARSyS, Técnico Lisboa) |
| Benefits of Three-Phase Metering for Load Disaggregation Apostolos Vavouris, Lina Stankovic, Vladimir Stankovic (University of Strathclyde); Jiufeng Shi (Discovergy GmbH) | ||
| What’s Up for the Weekend? Exploiting Day Type Information in Non-Intrusive Load Monitoring Mazen Bouchur, Daniel Szafranski, Andreas Reinhardt (TU Clausthal) | ||
| 15:30 | Afternoon Break | |
| 15:45 | Tutorial | Unlocking the Full Potential of Neural NILM: On Automation, Hyperparameters & Modular Pipelines Hafsa Bousbiat (University of Klagenfurt) |
| 16:45 | Closing Session | |
| 17:00 | Stream Ends | |
KEYNOTE
Five Predictions for the NILM Industry
Oliver Parson
In this talk, Oliver will speculate on the future of the NILM field through five key predictions. These will cover the dominant applications of NILM, the relationship between NILM and energy tariffs, NILM's application beyond electricity data and the potential to fuse disaggregated data with other data sources. The talk will also cover the effect of various elements of the energy transition on NILM, such as the increasing prevalence of electric vehicles, the move away from gas boilers, and our increasing dependence on renewable electricity generation over fossil fuel-fired power stations.
Oliver Parson Oliver has over a decade of experience in the field of energy analytics, including roles in both academia and industry. His PhD and subsequent research fellowship focused on the application of NILM to smart meter data, during which time he also contributed to the release of NILMTK. In 2016, Oliver joined Hive, the smart home sister company of British Gas, as a Data Scientist where he was part of the team who built the My Energy disaggregation tool. In 2019, he moved to Bulb, then the fastest growing energy company in the UK, where he contributed to Bulb's electric vehicle and smart tariff products. As an enthusiastic member of the community, Oliver hasn't missed a NILM conference since the series began in 2012, and has also co-organised a number of workshops along the way. He is currently taking a career break to travel the world, which has given him plenty of time to reflect on the direction of the energy industry.
TUTORIAL
Unlocking the Full Potential of Neural NILM: On Automation, Hyperparameters & Modular Pipelines
Hafsa Bousbiat (University of Klagenfurt)
This hands-on tutorial aims at introducing the NILM community to the new NILM toolkits, titled Deep-NILMtk. The toolkit implements the most recent machine learning best practices for efficient, reproducible and transparent research. The tutorial session will first briefly introduce basic concepts of the toolkit followed by an interactive coding session to demonstrate these best practices and how they can be used.
Hafsa Bousbiat is PhD student at the univeristy of Klagenfurt. She received a degree in Computer Science Engineering and Master degree in computer science from the Ecole Nationale Superieure d’Informatique (ESI ex.INI), Algiers. She is currently pursuing a PhD in Information and Communications Engineering at the University of Klagenfurt, Austria. She worked for three years as senior researcher within the Digital Age Research Center (D!ARC). Now, she is a research assistant at the univeristy fo Applied Sicences Wiener Neustadt The main focus of her work is the evaluation of ICT systems based on NILM to influence decision making in smart homes through improving the performance of load disaggregation and its applications to support ambient and assisted living..