This course aims to provide overview of problems and applications of data science and machine learning techniques in the energy domain, particularly for the cities’ context. We will start with brief introduction to the domain area, highlighting current main trends and challenges. Afterwards we will explore the wide spectrum of already existing data-driven applications for energy-related problems. Finally, we will have a more detailed look on several cases of ongoing research projects in Stockholm playing with some sample data and discussing the potential and limitations for further expansion of data science into this field.
Urban energy, Data applications, Stockholm.
R, Tableau (full desktop version is preferred and it is free for students/trial, but free public version should also be enough).
Physics (thermodynamics, school level), base R, linear regression models.
PhD candidate at KTH Royal Institute of Technology, Sweden
Oleksii hold BSc in Applied Mathematics (2006) and MSc in Systems analysis (2008) from Kyiv Polytechnic Institute (Kyiv, Ukraine). His early post-graduate experience is fully connected to this university, where he worked as a researcher in the World Data Center for Geoinformatics and Sustainable development, as a teacher in the Faculty of Informatics and Computer Science, and also served as a head for Students Science Association working on various development projects for higher education. From 2013 he works in the Urban Analytics and Transitions Research Group, KTH Royal Institute of Technology (Stockholm, Sweden), focusing on smart sustainable cities. From 2015 he is doing a project-based PhD on data analysis for strategic planning of building energy retrofitting for the case of Stockholm.
Urban building energy modelling, data-driven strategic planning and urban governance, participatory modelling.