Distinguished Lecturers

To request a Distinguished Lecturer (DL) for your next event, complete the DL Application Form. For more information or to see the full list, go to the Distinguished Lecturers page.

Qing-Shan (Samuel) Jia portrait
Qing-Shan (Samuel) Jia
Smart Buildings
Tsinghua University
Beijing, China
RAS Geographic Region 3

(Samuel) Qing-Shan Jia received his B.E. and Ph.D. degrees in automation and control science and engineering from Tsinghua University, Beijing, China in 2002 and 2006, respectively. He is a tenured Associate Professor in the Center for Intelligent and Networked Systems, Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University. He was a visiting scholar at Harvard, HKUST, and MIT in 2006, 2010, and 2013, respectively. His research interest is to develop an integrated data-driven, statistical, and computational optimization approach for cyber physical systems with applications to smart buildings and energy Internet. He is an associate editor (AE) of IEEE Transactions on Automatic Control, and was an AE of IEEE Transactions on Automation Science and Engineering and J. of Discrete Event Dynamic Systems. He chairs the Control for Smart Cities Technical Committee in IFAC and the Beijing Chapter Chair of IEEE Control Systems Society, and co-chairs the Smart Buildings Technical Committee in IEEE Robotics and Automation Society. He chaired the Discrete Event Systems Technical Committee in IEEE Control Systems Society. He is a member of the Technical Committee on Control Theory and the Technical Committee on Information Security of Industrial Systems in the Chinese Automation Association.

Talk # 1

Artificial Intelligence in Cyber Physical Energy Systems - Event-Based Learning and Optimization

Cyber physical energy system (CPES) is where information and energy merges together to improve the overall system performance including economic, comfort, and safety aspects. Artificial intelligence which are enabled by internet of things, big data, and cloud computing, has a big role in the optimization of CPES. In this talk, we focus on a real problem in smart buildings, in which multiple buildings are connected into a micro grid. The renewable energy such as solar power and wind power are generated locally in the building, stored in the building, and consumed in the building by plug-in loads and electric vehicles. There are models to predict the power generation and consumption in minutes, hours, and days. And there are models to predict the power generation and consumption in individual buildings or a group of buildings. We developed a multi-scale event-based reinforcement learning method which makes decisions only when certain events occur, and uses policy projection and state and action aggregation to connect the models in multiple scales. The performance of this method is demonstrated by numerical examples. We will also discuss extensions of this method to distributed optimization. We hope this work sheds light to the optimization of CPES.

Talk # 2

Title: Event-Based Learning for Smart Buildings – from Energy Saving to Fast Evacuation

Building is responsible for nearly 40% of energy consumption in many developed and developing countries around the globe. Recent technology advances have enabled the deployment of small sensors and actuators within the building, the wearable devices for the occupants, and the human machine interface for convenient interaction between the occupants and the buildings. It is of great practical interest to develop scalable methods to handle the large amount of data from these sensors and to provide real-time decision making for energy saving and fast evacuation in smart buildings. We focus on this important problem in this talk and show two examples. The first example considers energy saving in buildings. After reviewing the state of the art in this field, we will show a distributed event-based learning method for estimating the distribution of occupants within the building. This method uses multi-sensor fusion and uses stay-time to reduce the accumulative estimation error. The second example considers fast evacuation in buildings. Exploring the structural property of the problem, we will show approaches for fast modeling, indoor localization, and navigation and evacuation guidance for fire fighters. We hope these examples may attract more researchers to join the field of smart buildings.

Show More