Lei Lei

Headshot of Lei Lei
Associate Professor
School of Engineering
Phone number: 
(519) 824-4120 ext. 53922
THRN 2407
Seeking academic or industry partnerships in the area(s) of: 
Intelligent control, computation, and communications through machine learning, especially deep reinforcement learning.
Available positions for grads/undergrads/postdoctoral fellows: 

Education and Employment Background

Prof. Lei Lei received her PhD in Electrical Engineering from Beijing University of Posts and Telecommunications (BUPT) in Beijing, China. She has rich academic and industry experiences including working at China Mobile Research Institute (CMRI), Beijing Jiaotong University (BJTU) in China and James Cook University  (JCU) in Australia.  She is also an Adjunct Research Professor at Western University.  Lei joined the University of Guelph in 2020. 

Research Themes

Lei’s research is focused on applying artificial intelligence and machine learning methodologies to the optimal control of Internet-of-Things (IoT) and mobile cloud/edge computing for applications such as smart grid, autonomous driving, and cloud robotics. Cloud/Edge computing is a new paradigm of computing, while IoT is a vision for the next-generation Internet. The increased capacity of the fifth generation (5G) mobile networks means that the computing tasks of mobile devices can run at either the remote cloud or close edge servers. 5G provides a good opportunity to connect the IoT devices (e.g., sensors and wearable devices) to each other and the Internet under a unified framework. Key research themes include:

  1. Reinforcement learning and optimal control of 3C functions. Traditional resource control methods in computer and communications systems and networks rely on methodology that is highly dependent on human intelligence (e.g. heuristic algorithms). Reinforcement learning enables the systems to learn the optimal control on their own based on the past experiences in a model-free style. Lei is interested in exploring how to optimize 3C functions—communications, computing, and control. Specifically, she is interested in applying reinforcement learning methods to enable energy management for smart grid, vehicle control for autonomous cars, and networked robots and the cloud to optimize control decisions.
  2. Artificial neural networks (ANN) and IoT optimal control problems. ANN is another important branch of artificial intelligence and machine learning belonging to the supervised learning. The IoT network connects many devices to the Internet, and thus generates a huge amount of sensory data from the physical world. However, there are challenges when it comes to designing efficient machine learning algorithms to learn optimal policies directly from the massive amount of sensory input data for IoT applications.  This data is processed to provide feedback to IoT devices and to optimize their control over the physical world. Lei is exploring how ANN can be integrated with the reinforcement learning to deal with the high-dimensional sensory input data from the massive number of IoT devices.


  • Senior member of the Institute of Electrical and Electronics Engineers (IEEE), 2016.
  • Associate Editor for Transactions on Emerging Telecommunications Technologies (ETT) and Peer-to-Peer Networking and Applications (PPNA).
  • Secretary for IEEE Communications Society Asia-Pacific Region Chapters Coordination Committee, 2015–2017.
  • Best Paper Award, IEEE/CIC ICCC, 2015.
  • Top 10 patent applicants at China Mobile Research Institute, 2009.