Supported by
Monitoring of energy consumption at equipment level is essential to predict the energy needs and the equipment health in a household, a building or an industrial system. Energy disaggregation regards the use of data analytics and signal processing, in order to identify specific patterns and distinguish between individual electric device consumption. This is usually done in a non-intrusive manner by monitoring the utility connection meter, and has been a field of significant research work for several years. The project aims to develop novel tools for energy disaggregation and monitoring of device health status, based on realtime pattern recognition/matchmaking of complex energy load data time-series, and hardware accelerated algorithms. This requires the design, development and implementation of complex algorithms on a Field Programable Gate Array (FPGA), to create a network of distributed agents that performs the majority of the data analysis in real-time, and transmits events, instead of raw data, to a main server.
The developed algorithms for events’ analysis will be integrated in a cloud platform to share knowledge between agents.
