CAREER: Model-based Energy Management for Sustainable Buildings

University Of Massachusetts Amherst, Amherst MA

Investigators

Abstract

Modern society depends on a massive amount of, largely ?dirty,? energy to sustain itself. Collectively, buildings consume more energy than the other broad sectors of consumption. A significant barrier to improving building energy efficiency is that fine-grained monitoring of electrical loads at large scales remains impractical: it is expensive, invasive, and unreliable. Our hypothesis is that a comprehensive repository of detailed models that describe how loads use power provides a foundation for programmatically managing building energy consumption. The project?s goal is to advance research and education using the model-based paradigm to design automated load discovery, monitoring, and scheduling techniques that are low in cost, highly transparent, and privacy preserving. To achieve this goal, the project will bootstrap and seed an online data repository to enable new techniques for modeling loads based on their energy usage. Since many types of loads exist, our goal is to develop a library of load modeling techniques. The project will then leverage these models to automatically discover the set of loads a building operates, and monitor their electricity usage using only aggregate electricity recorded by a building smart meter. To benefit students, the project will develop new courses on building energy management, and make the materials publicly available to benefit educators. Importantly, the courses will enable students to gain hands-on experience by ?programming? real buildings. This learning-by-doing approach is highly effective---simply turning devices on and off via computer is eye-opening---and will serve as a catalyst for including undergraduates in research.