The research objective of this award is to test the hypothesis that interactive, sensor monitoring and online control can significantly reduce the energy consumption of buildings (by 20 percent or more) while maintaining occupant comfort. Through simulations and experimentation, inputs from a wide range of modalities and platforms in a heterogeneous sensor system (including wired and wireless sensors; mobile and static sensors; automatic and human-input-based sensors) will be integrated and fused in order to measure and track indoor climate, energy usage, as well as occupant location, activities, and preferences with much higher accuracy and lower cost compared to homogeneous systems. The research will encompass mathematical and empirical analysis and evaluation of efficient online stochastic algorithms based on multi-armed bandit theory that take the integrated sensor measurements as input to learn over time how to automatically operate building controls, so as to minimize energy consumption while maintaining occupant comfort, and quantify the gains in energy consumption obtained in typical environments.

If successful, the research will establish a framework, where humans and building systems interact ubiquitously in real time through an integrated mobile sensor and control system for energy awareness and learning and energy efficiency in buildings. The results will be disseminated through and contribute to the civil and environmental engineering, electrical engineering and computer science curricula, multiple conference talks, and publications. A public outreach and energy education program is planned to raise public awareness on energy efficiency in buildings. Targeting K-12 classrooms, this program aims to attract minority students to the engineering profession in the greater Los Angeles area. An interactive game, focusing on teaching K-12 students how they can conserve energy in their daily life by modifying their behavior and habits will be prototyped and tested.

Project Report

In this project, we investigated the development and use of state-of-the-art mobile sensor technologies and heterogeneous sensor networks that are non-intrusive, economic, designed to be quickly and ubiquitously deployed and that gather, compute and fuse data from different modalities, such as wired and wireless ambient sensors, meters and mobile phone sensors. We developed data processing and analysis methods to enable energy-aware and adaptive building management. We explored whether real-time occupancy information (e.g., occupant locations, comfort levels) and long-term occupancy patterns (e.g., occupant schedules, thermal comfort profiles) acquired through algorithms that use fine-grained sensor information (e.g. temperature, lighting, CO2) could reduce energy consumption while increasing occupant comfort. We analyzed datasets of energy consumption, optimized building controls based on stochastic feedback and quantified the results through energy simulations, as well as field tests. We developed and evaluated novel algorithms for indoor localization that can enable a smart building to maintain awareness about the location of its occupants. We also developed and evaluated through simulations online learning algorithms that aim to learn how to operate the thermal controls of a building so as to try and maximize the satisfaction level of its identified occupants, if the occupants could provide feedback about their level of comfort through an interactive mobile application. These online learning algorithms are in principle able to incorporate noisy and uncertain feedback from occupants. We disseminated project outcomes in our scientific communities through several peer reviewed papers and talks, and to several K-12 students through presentations, aiming to increase scientific and public awareness about energy aware buildings and attract minority students to engineering in the greater Los Angeles area. In addition to Ph.D. students, two underrepresented undergraduate students participated in project-related research activities. In addition, as part of this project, we hosted three incoming underrepresented freshmen students for a summer project. We integrated research outcomes into our educational activities through case studies and lectures based on sensing and control-related outcomes, as well as additional content that covers state-of-the-art sensor technologies, embedded systems and computing into the existing engineering curriculum.

Project Start
Project End
Budget Start
2012-05-15
Budget End
2014-09-30
Support Year
Fiscal Year
2012
Total Cost
$383,256
Indirect Cost
Name
University of Southern California
Department
Type
DUNS #
City
Los Angeles
State
CA
Country
United States
Zip Code
90089