III: Small: Cyber Physical Mappings - Empower Building Analytics at Scale

University Of Virginia Main Campus, Charlottesville VA

Investigators

Abstract

Buildings have profound impact on human health, productivity, comfort, and energy consumption. For example, building operation is the single largest energy consumer in the US, accounting for 70% of electricity consumption and 40% of total energy consumption. Allergens, noise levels, and the availability of sunlight affect health and well-being, especially given that on average Americans spend 90% of their time in buildings. Indoor conditions such as thermal comfort and CO2 and pollutant concentrations have been shown to affect human productivity by 8-11%, which has an important effect on the national economy. The performance of the nation's buildings can be significantly improved with analytics engines that collect and analyze data from the thousands of sensing and control points that already exist within a typical building. However, data alone does not inherently have any meaning, and so a person must manually provide the context (also called metadata) about every sensor and controller so that the analytics engine can interpret the data. This costly manual process can take days or weeks for a single building and is a major obstacle for applying building analytics to a large number of buildings. This project creates tools to automatically infer the metadata of data streams, such as the type of sensor or controller that produced the data and its relation to other sensors, equipment, or rooms in the building. The approach is based on the hypothesis that the data in buildings is structured due to weather patterns, equipment operation patterns, and common design patterns that are observed in many buildings around the world. Metadata inference exploits this structure to quickly and easily create new metadata values for a large number of sensing and control points based on known metadata of other points or other buildings. It develops new learning-based techniques along three main research thrusts: 1) value inference of individual points, 2) relationship inference between sensors, and 3) latent metadata inference from building managers' interactive access behaviors with a building management system. This research enables industry and institutions to more easily apply building analytics to new buildings with minimal or even no manual mapping required. It generates impact on average US building performance along multiple metrics, including human health, productivity, comfort, and energy consumption. In addition, the proposed research includes the development of fundamentally new methods and techniques in the fields of data mining and cyber-physical systems, and they will be released as open-sourced code. The research activities will be incorporated into teaching materials for student training and education. Both graduate and undergraduate researchers will be involved in all phases of this research, and we will engage and recruit students from underrepresented groups to participate in this research. If successful, these techniques will generalize to other types of C activities such as human health monitoring, infrastructure monitoring, or smart transportation systems where structure can similarly be used to help infer the physical context of a sensor or controller.