Project – Nonintrusive loading monitoring for energy aware smart facilities
Project Description: this project aims to study nonintrusive load monitoring for event detection and classification. This project is supported by a subcontract from Carnegie Mellon University funded by the National Science Foundation (NSF)’s GOLIA Cyber-physical system (CPS) program.
About electric load monitoring
Load monitoring normally consists of a sequence of signal processing and analysis steps in order to achieve the goal of event detection, appliance event classification, appliance activity tracking, and energy consumption estimation. Event detection, also called load detection in this paper, refers to the detection of the change of On and Off status of the loads in buildings or shipboard electro-mechanical systems. The goal of event detection is to raise an alarm after the onset of an event (i.e., On or Off status of an appliance or the appliance state transitions), which would enable identification of the time-instant when the On or Off event occurs. We should note that many appliances contain several individual loads as building blocks. For example, an electric clothes dryer may contain a 120 V motor and 240 V thermostatically switched heating element, controlled so that the motor may be on while the heating element if off, but not vice versa. Hence, load detection may result in detecting multiple loads’ On and Off status of a single appliance. These detected load activities will be classified into corresponding appliances in the event classification stage. Furthermore conventional event detector often time requires periodic training to adjust the detection threshold due to the dynamics of electrical loads in order to achieve a high detection probability and a low false alarm rate. This condition imposes severe limits on the achievable accuracy of the event detector, thus reducing the practical usage of a NILM system.
Selected Publications:
- Y. Jin, E. Telebakemi, M. Berges, and L. Soibelman, “Robust adaptive event detection for non-intrusive load monitoring”, Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011), Prague, Czech Republic, May 22-27, 2011, pp. 4340-4343, IEEE
- Y. Jin, E. Telebakemi, M. Berges, L. Soibelman, “A time-frequency approach for event detection in non-intrusive load monitoring”, Proceedings of the SPIE Defense, Security and Sensing, Orlando, FL, April 25-29, 2011
