Tuesday 1st – Wednesday 2nd October 2019, Thessaloniki, Greece
The NILM Workshop has now ended. We’ll be back again in 2020! Stay tuned for updates.
About the NILM Workshop
The EU NILM Workshop is now in its sixth year! The aim of this workshop is to bring together researchers that are working on the topic of energy disaggregation in both academia and industry. The workshop will feature two full days of conference-style material, following a similar format to the EU NILM 2018 conference. We hope to live stream the presentations via youtube, and also make videos of presentations available afterwards.
If you’re interested in sponsoring a part of the event, simply contact us using the form at the bottom of this page.
Who should attend?
If you are an individual or an organisation interested in energy disaggregation then this is the workshop for you. The workshop is an open forum to encourage collaboration within the field and we welcome all levels of knowledge in this area, even if you are relatively new to NILM.
What is NILM?
NILM stands for Non-Intrusive Load Monitoring. This is the process which disaggregates your total energy consumption into the energy readings of individual loads over a period of time, allowing users to see how much power a particular appliance has used during that time.
Early free ticket registration deadline: 31st May 2019
General ticket sales begin: 1st June 2019 (€100 + VAT)
Presentation abstract submission deadline: 1st August 2019
Final registration deadline: 25th September 2019
Tuesday 1 October 2019
0930 Registration & coffee
1030 Welcome and introduction
– Oliver Parson (Centrica Hive Limited) & Dimitrios Doukas (NET2GRID)
1100 Opening keynote
– Peter Schulten (Innogy) & Bert Lutje Berenbroek (NET2GRID) – IONA: NILM in a commercial rollout
1200 Lunch break
1320 Session 1: Evaluation and collaboration
– Shamim Ahmed & Marc Bons (Fludia) – Light weight deep learning model trained on combined available datasets
– Josh Honda (IEC TC85WG20) – Progress report of NILM International Standard activity
– Oliver Parson (Centrica Hive) – Towards reproducible state-of-the-art energy disaggregation
– Daniel von Gaertner (Fresh Energy GmbH) – A comparison between NILM providers
1510 Session 2: High frequency NILM I
– Peter Davies (Verv) – The super-smart plug
– Douglas P. B. Renaux (UTFPR) – A multi-agent architecture to detect and identify loads
– Bruna M. Mulinari (UTFPR) – A Comparison of Different Approaches of the Prony’s Method for Power Signature Analysis
1610 Session 3: High frequency NILM II
– Despoina Kothona (University of Thessaly) – Utilizing Harmonic Currents in Sequential and Parallel Disaggregation Schemes
– Anthony Faustine (Ghent University) – Exploring Recurrence plots for Appliance Classification in Non-intrusive Load Monitoring
– Bruna M. Mulinari (UTFPR) – A New Set of Steady-State and Transient Features for Power Signature Analysis Based on V-I Trajectory
1710 Lightning talks
1720 Poster and demo session
1830 Workshop group picture
1930 Social event: Kitchen Bar– Food and drink at your own expense
Wednesday 2 October 2019
0900 Coffee & networking
0940 Session 4: Deep Learning
– Patrick Huber (University of Applied Sciences and Arts Lucern) – Deep Neural Networks for NILM on low Frequency Data – An up to Date Review
– Jiufeng Shi (Discovergy GmbH) – Supervised approaches with user feedback mechanism
– Ankita Srivastava (Discovergy GmbH) – Deep Learning models for disaggregation of household load data
– Maria Kaselimi (National Technical University of Athens) – Applying Deep Learning Methods for NILM
1140 Session 5: Vendors & innovative applications
– Josh Honda (Informetis Co., Ltd.) – Informetis business development update
– Ioannis J. Pourakis (EcoMechanica / powerPerfector) – powerPerfector technology – Increased energy savings and security of power supply
1200 Lunch break
1320 Session 6: Real-world deployments
– Mukesh Kumar (CSIR-CSIO) – Energy Management using Non-Intrusive Load Monitoring Technique
– Kaustav Basu (Quby) – A scalable and data driven NILM solution for low resolution smart meter data
1430 Session 7: Data sets
– Douglas P. B. Renaux (Federal University of Technology – Parana) – A Dataset of Voltage and Current traces on a variety of single and multiple loads with precise load event time indications
– Simon Henriet (Télécom Paris / Smart Impulse) – NILM for commercial buildings
– Benjamin Völker (University of Freiburg) – Semi-Automatic Generation and Labeling of Training Data for NILM
– Dimitrios Doukas (NET2GRID) – NILM datasets, benchmarking and evaluation
1550 Discussion session
– Open discussion
– Plans for next year
1630 Workshop close
Register your place
Tuesday 1st – Wednesday 2nd October 2019
9.30am – 5pm
Ticket sales have now ended.
Bus: You need to have a bus ticket in advance or use coins on the bus to buy one. Credit cards are not accepted on the bus. You can find info about the buses here: http://oasth.gr/
Taxi: Before entering a taxi (or before calling for one) ask if they accept credit cards.
Bars/cafes: Most places will accept credit cards, however, a few may not accept Amex.
Airport to city centre:
Bus: The public bus is the cheapest option (€2). There is a daytime bus (01X) and a nighttime bus (01N) which run 24/7. The journey takes approx 70 minutes, including a 40 minute waiting time.
Taxi: A Thessaloniki Airport taxi is the fastest mode of transport (35 minutes). The journey will cost around €20.
The train station is located in the city centre. Taxis and buses also leave from here. The journey from the train station to the venue is approximately 20 minutes.
City centre to venue:
By local bus:
Lines 2, 8, 14, 78 (bus stop “University of Macedonia”).
Lines 17,37 (bus stop “Kaftatzoglio Stadium”).
This is the fastest way and the journey will cost approximately €5. You can order a taxi at this number: +302310525000. Please note, Uber is not functional in Greece.
Call for Sponsors
We have a number of sponsorship options for the workshop, including opportunities to give a full presentation, present a demo, exposure on the website and slides, and also to sponsor an evening reception. Please contact us for further information.
We would like to thank our sponsors for their support and enabling us to continue running the NILM Workshops.
Control. Comfort, convenience and cost savings. This is what smart energy products and services in a connected home can give our customers.
Verv is a smart home hub using AI to provide advanced insights into individual appliance usage and condition so users can save money on their energy bills, reduce their carbon footprint and keep their home safe.
NET2GRID delivers value-added services for energy suppliers based on energy data. It allows them to grow an engaged and loyal customer base and grow new revenues based on these new services.
Quby assists energy companies in the migration from commodity supplier to service provider by making smart use of data science, insights and business propositions.