My research focuses on efficient data analytics for cyber-physical human systems, which employs modeling, optimization, and control theories to design new algorithms and mechanisms for emerging technologies and human factors, in order to facilitate the transition into an energy-efficient and system-wide resilient urban ecosystem.
To this end, I developed learning algorithms under weak supervision, novel sensing paradigms for indoor environment monitoring and demand-based, occupancy-aware controls, deep Bayesian inverse reinforcement learning algorithm, as well as modeling and incentivization of humans to induce desirable behaviors via gamification.
I also explore the design and operation of community-based micro-grid in support of the mega-grid, which exploits the flexibility of demands, as well as the efficiency from both thermal and electricity energy provision and shared distributed energy resources (DERs) and storages, to address the grand challenge of distributed energy resource integration [see my publications].
Centerline has reported our IEQ Bot in its November issue: "CBE Panel Session Explores Innovative Methods for Monitoring Indoor Environments".Nov 2017
Paper on our new IEQ Bot "Automated mobile sensing: Towards high-granularity agile indoor environmental quality monitoring" accepted by Building and Environment (paper | slide | code).Oct 2017
INFORMS invited talk on "Robustness Analysis of Power Grid under False Data Attacks Against AC State Estimation" at Houston, Texas. Panelist in the Industrial Advisory Board meeting at the Center of the Built Environment, "IEQ Bot", Berkeley, California.Oct 2017
New paper on power system vulnerability analysis "Power Grid AC-based State Estimation: Vulnerability Analysis Against Cyber Attacks".Oct 2017
Berkeley Engineer magzine featured an article "Brains for buildings, packaged in a smart briefcase" on our Building-in-Briefcase sensor platform.