Invited talk at the second Smart Microgrids Meetup in Munich, hosted by Siemens.
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.
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.