Simone Silvestri Wins NSF CAREER Award

Simone Silvestri, assistant professor in the University of Kentucky Department of Computer Science, has received a National Science Foundation Faculty Early Career Development (CAREER) Award. The award is given in support of early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization.  

Silvestri's project is titled "Energy Management for Smart Residential Environments through Human-in-the-loop Algorithm Design." 

"This proposal seeks to overcome current limitations associated with state-of-the-art energy management for SREs by explicitly including humans in the design loop through novel algorithmic, machine learning and optimization solutions that specifically take into account user behaviors, perceptions and psychological processes," said Silvestri. "The proposed research has the potential to transform the way in which energy management systems for SREs are designed, implemented and used by people."  

The residential sector is responsible for more than 20% of the total energy consumption of the United States, and this amount has been constantly increasing for several decades. Smart residential environments (SREs) are a new paradigm that envisions homes equipped with smart appliances based on the paradigm of the Internet of Things. SREs offer tremendous potential to reduce the energy consumption of the residential sector; however, previous work in this context has largely overlooked the complexity of human behaviors and perceptions when interacting with such systems. This lack may actually generate negative user attitudes, potentially resulting in an increase of the energy consumption and even abandonment and avoidance of such systems.

The CAREER award contributes to Silvestri's long term research goal of laying the foundations for a new field of study at the intersection of computer science and social sciences, where social-behavioral theories and models are integrated into new algorithmic, machine learning and optimization solutions for cyber-physical systems to specifically consider user behaviors, perceptions and psychological processes in the design and operation of these systems.