Posted by anderc8 on Friday, May 25, 2018 in Data Science Methods for Smart City Applications, News.

This spring, the University Course Data Sciences Methods for Smart City Applications was offered to Vanderbilt University undergraduate and graduate students for the first time. The course was designed to examine and address issues facing cities and metropolitan areas by bringing together concepts and methodologies from systems engineering, data sciences and machine learning, modeling and simulation, optimization and social sciences. Students reviewed these topics and focused on machine learning, Python programming and script generation, qualitative methods for data collection, and ethics issues related to data collection and privacy.

A significant portion of the semester was devoted to team projects with students working together. The projects covered four separate themes: transportation, energy, gentrification and transportation, and emergency response. Each team worked with a faculty mentor and a graduate student advisor to research their projects, implement qualitative and quantitative methods for data collection, and analyze the data to answer research questions. The students presented their findings at the end of the semester and submitted reports.

This is the second in a series of four student-written blogs describing the projects.

Energy Management with Vanderbilt Buildings
Written by Kelsea Best, Sebastian Lim, Anya Tarascina and Kevin Yang

Worldwide energy demand continues to increase, fueled by rising populations, expanding economies and increasing consumption rates. For this reason, reducing energy consumption and improving energy efficiency is an urgent goal for scientists and policy-makers alike. A promising area of research is the heating, ventilation and air conditioning (HVAC) of buildings, which comprise about 20 percent of global energy usage. HVAC systems also have a direct impact on building occupant comfort by controlling space temperature and humidity, therefore impacting occupant productivity and building profitability. These competing objectives for HVAC systems present a challenge when designing, analyzing and implementing optimal systems. To that end, our project focused on improving Alumni Hall, a multipurpose building that houses the graduate student office, dining hall, gym, classroom and event spaces.

Our team of graduate and undergraduate students with backgrounds in chemical and environmental engineering, computer engineering, economics, mathematics and biological sciences explored how to make Alumni Hall more energy efficient and comfortable. We learned how to conduct focus groups with students, workers and university leaders to understand how the HVAC system in Alumni Hall works, what people loved about it, and what they’d like to see improved. We learned the theory behind machine learning techniques and how to use them to optimize and predict energy usage. We even got to explore the inner workings and measurements of the HVAC system, encountering plenty of puzzling surprises along the way. Our efforts on this project revealed discrepancies between what the system was measuring and the concerns stakeholders brought up. We faced many challenges along the way while working with administration, building occupants, engineers and architects. At the end of the semester, we had tangible results and feasible recommendations to better Alumni Hall. Who knew how long a door stays open could play such a huge role in a building’s energy consumption? We are excited to see how our findings can contribute to Vanderbilt’s plans as we work toward a campus with a minimal carbon footprint.