Non-Intrusive Load Monitoring (NILM)
Use a smart meter for a house, building, microgrid, etc., to infer and track the performance of appliances and loads; thus, helping to create a smart energy efficient environment.
Our goal is to work with our SFU departments and external partners to help understand what computation tools are available and how computation can be used to solve difficult suitability problems. We apply and invent new machine learning and statistical signal processing algorithms to the many different aspects of computational sustainability. Here are some of our current projects.
Use a smart meter for a house, building, microgrid, etc., to infer and track the performance of appliances and loads; thus, helping to create a smart energy efficient environment.
Collect data and publish publicly available datasets that are used to test machine learning systems that attempt to solve sustainability problems.
Investigating how communities can become self-reliant by generating and sharing power using new information and communication technologies (ICT).
Create a ubiquitous computing platform that communities can use to track their carbon output and collectively reduce their carbon footprint.