It is part of a project to build a Human-in-the-loop Sensing and Control System for Commercial Building Energy Efficiency and Occupant Comfort maintenance. The main goal of the project is to sense, analyze and estimate room occupancy and occupant's thermal comfort and use this information to change the environment conditions automatically to maximize occupant comfort and minimize energy consumption. My contribution involves occupancy sensing in these buildings using depth images captured by Kinect and to configure and oversee the installation of 12 prototype sensing units, manage the data collection, and begin the data analysis.
The report does a study on the climate and environment and recommends sustainable practices for dorm buildings in the area of Pittsburgh, PA. This report proposes seven sustainable features identified as feasible and impactful for a new undergraduate dormitory on the campus of Carnegie Mellon University in Pittsburgh, PA. Specifically, the Residence on Fifth Avenue(“The Res”), a first-year undergraduate, apartment-style dormitory, was used as reference for the proposed new building. The seven features include: green roofs, efficient showerheads, building orientation and windows, effective insulation, intelligent HVAC, LED lighting, and effective landscaping. All seven have been assessed for technical and financial feasibility, in addition to their contribution to a reduced environmental footprint for the building.
Understanding occupant-building interactions helps in personalized energy and comfort management. However, occupant identification using affordable infrastructure, remains unresolved. Our analysis of existing solutions revealed that for a building to have real-time view of occupancy state and use it intelligently, there needs to be a smart fusion of affordable, not-necessarily-smart, yet accurate enough sensors. Such a sensor fusion should aim for minimalistic user intervention while providing accurate building occupancy data. We describe an occupant detection system that accurately monitors the occupants’ count and identities in a shared office space, which can be scaled up for a building. Incorporating aspects from data analytics and sensor fusion with intuition, we have built a Smart-Door using inexpensive sensors to tackle this problem. It is a scalable, plug-and-play software architecture for flexibly realizing smart-doors using different sensors to monitor buildings with varied occupancy profiles. Further, we show various smart-energy applications of this occupancy information: detecting anomalous device behaviour and load forecasting of plug-level loads.
The use of smart-meters is proliferating, they are now being deployed without asking the obvious question: Do we really need each of them? Beyond the cost of smart-meters, there are overheads related to installation, wiring, etc. To formally tackle this question, we first define the notion of observability that one or more pieces of information (including that from smart-meters) enable. This notion allows us to compare two different deployments of sensors with respect to their information content and their usefulness. We then examine some commonly available information from which one can infer power consumption of devices in a given space. We show how we have applied this approach to systematically decide the optimal number and location of smart-meters to ensure observability of consumption by different parts of a building.