Load Disaggregation and Building Energy Management Systems

https://secure.meetupstatic.com/photos/event/5/4/6/0/600_466821600.jpeg

*** ATTENTION!!! ***
REGISTRATION ON EVENTBRITE, READ THE END OF THIS MESSAGE TO SIGN-UP

The Smart Microgrids München Meetup wants to invite you to another exciting evening, this time meeting at the Siemens AI Lab for discussing on the topic of Building Energy Management and Load Disaggregation, an key-enabling technique allowing for the identification of individual operating devices from an overall power measurement. This is a key technology for future energy management systems, as this offers a solution for monitoring legacy devices for which attaching a dedicated monitoring element would be costly or infeasible. The event will purposefully have a 50/50 academic and industrial flavour to showcase both uses and limits of this technique, as well as provide an overview of possible solutions being currently investigated.

• 18:30 - 18:40 Entry/Registration

• 18:40 - 18:45 A. Monacchi et Al. Welcome from the Smart Microgrids Munich organizers

• 18:45 - 19:00 B. Blumoser The Siemens AI Lab in a Nutshell

Abstract: The Siemens AI Lab has opened its doors in October 2017 as a room for exploration and open innovation on industrial AI. It is intended to foster an environment where people can separate the hype from the trend – by getting connected with R&D partners inside and outside Siemens that complement their perspective, and by jointly validating their hypothesis through early prototypes. In this short talk, we will get an impression on the rationale behind the AI Lab, its principles of work and an overview of past, running and planned activities

Bio: Bernd „Benno“ Blumoser is the Innovation Head of the Siemens AI Lab. He holds a diploma in international cultural and business studies from the university of Passau, and started his career at Siemens Management Consulting. In 2009, he transferred to Corporate Technology to drive the implementation of the Siemens Open Innovation Program, piloting and implementing new innovation methodologies like crowdsourcing and technology scouting. Based on this experience, he initiated in 2013 a Siemens-wide Trend Scouting approach to identify, analyze and disseminate emerging digitalization trends, narrowing it down more and more on strategic aspects related to Artificial Intelligence. In his private life, Benno is passionate about hiking in the Alps, playing music, and trying to better understand Latin America. He’s married and has three kids.

• 19:05 - 19:20 DI. C. Klemenjak Load Disaggregation: Introduction & State of the art

Abstract: With the roll-out of smart meters the importance of effective non-intrusive load monitoring (NILM) techniques has risen rapidly. NILM estimates the power consumption of individual devices given their aggregate consumption. In this way, the combined consumption must only be monitored at a single, central point in the household, providing various advantages such as reduced cost for metering equipment. We discuss the fundamental building-blocks of NILM, first giving a taxonomy of appliance models and device signatures and then explaining common supervised and unsupervised learning methods. Furthermore, we outline a fundamental algorithm that tackles the task of NILM. We review recent research that has brought novel insight to the field and more effective techniques. Finally, we formulate future challenges in the domain of NILM and smart meters.

Bio: Christoph Klemenjak (http://wwwu.aau.at/chklemen) is a PhD student and research assistant at the Institute of Networked and Embedded Systems, at the University of Klagenfurt. Christoph attended the Higher-Technical-School for Electrical Engineering with the focus on telecommunications and computer engineering in Klagenfurt where graduated in 2010. At the beginning of 2017, he concluded with distinction his master's degree study on Informations and Communications Engineering with focus on Smart Grid. His research focuses on intelligent energy applications in smart buildings and smart microgrids. This includes the design and analysis of intelligent techniques and algorithms to identify appliances in aggregated household power draws, the design of architectural requirements for next-generation energy management systems, and the conception and assessment of smart metering techniques. He is a student member of ACM / IEEE and actively publishing in those communities.

• 19:25 - 19:40 Prof. A. Reinhardt Accelerating Energy Analytics Research through Synthetic Consumption Trace Modeling

Abstract: Well annotated power consumption traces are a crucial prerequisite for the development and analysis of energy analytics algorithms. Due to the high efforts required to collect such traces in the real world, only a few such data sets have been published worldwide. Instead, their synthetic generation has emerged as a viable alternative. I will be talking about AMBAL, our Automated Model Builder for Appliance Loads, which allows to derive models from real device power consumption data and synthesize them into realistic-looking aggregate consumption traces that help us accelerate energy analytics research.

Bio: Andreas Reinhardt works at TU Clausthal as an interim professor for embedded systems. He has been looking into energy analytics research for close to ten years, starting at TU Darmstadt where he was heading the distributed sensing systems group that researched on energy data collection and processing techniques. He subsequently held a Vice-Chancellor's Postdoctoral Research Fellowship at the University of New South Wales in Sydney, Australia, to investigate smart energy management systems. In his current role at TU Clausthal, he is looking into the holistic and interdisciplinary approaches for energy analytics. Well, and he's the guy who released the Tracebase data set (www.tracebase.org (http://www.tracebase.org/)).

• 19:45 - 20:00 N. Starzacher Load Disaggregation - A Practitioner's View: Learnings and Challenges from Running Disaggregation for Thousands of Users

Abstract: In this talk Nikolaous Starzacher will be sharing his experiences as CEO of one of the top startups selling energy analytics.

Bio: Nikolaous Starzacher is the CEO of Discovergy, a company selling energy analytics based on the load disaggregation technique.

• 20:05 - 21:00 Networking

**********

ATTENTION!! Due to the limited number of seats available (40) we decided to reserve 10 seats on invitation only (for further participants from industry and academia strictly involved in the field) and let the other 30 to be reserved by the meetup attendees on a first-come first-served (FCFS) fashion. This should ensure both a very diverse audience as well as the participation of actual experts operating in the field. We therefore invite you to cancel your ticket shall you not make it so as to let others participate. We also might reduce the number of reserved tickets so as to reassign them to the meetup attendees shall they not be taken.

The link for the registration is provided here (https://www.eventbrite.com/e/load-disaggregation-and-building-energy-management-systems-tickets-41012103305).
Select the "Meetup Attendee" ticket only.
The access to the "Invited Attendee" ticket variant is strictly on invite only.

P.S. Organizers and Speakers are automatically signed up.

**********