Data-driven thermal model for smart thermostats
Predicting peak demand in Ontario demand response program
As part of the Energy Systems and Data Analytics MSc, students published online their ideas for applying data science and machine learning within the energy systems as part of their Energy Data Analysis (BENV0091) module. The students formed teams of four and worked for about 5 weeks to develop their own idea (link).
skills: R Shiny R Python Git
Industrial waste heat recovery potential in Ontario (geospatial map and dashboard)
As part of the Spatial Analysis of Energy Data (BENV0093) module during my MSc, I was tasked to communicate complex spatial dynamics around the energy systems with a map minimizing the use of text. The map I developed seeks to highlight potential industrial site clusters that can utilize waste heat in a district heating network to meet a portion of metropolitan area heating demand and abate Greenhouse Gases (GHG) emissions. My map was ranked within the top 5 of my cohort and showcased in an article (link).
skills: QGIS R (sf, raster) Tableau