Skip to main content
Workshops & seminars, Conferences & lectures

Seminar by Dr. Qiang Ye (Minnesota State University)


Date & time
Thursday, March 11, 2021
10 a.m. – 12 p.m.
Speaker(s)

Dr. Qiang Ye

Cost

This event is free

Where

Online

Title: Radio Resource Slicing and Computing Task Offloading for 5G Wireless Networks

Abstract: The fifth generation (5G) wireless networks are expected to provide diversified and customized service deliveries with fine-grained quality-of-service (QoS) guarantee. Software-defined networking (SDN) and network function virtualization (NFV) are two promising networking and computing technologies that facilitate cost-effective and flexible service customization. With SDN and NFV, both the network resources and computing resources can be sliced in a more fine-grained manner to maximize the overall resource utilization with better QoS provisioning. In this talk, I will introduce two pieces of our recent research works on radio resource slicing and computing task offloading for 5G wireless networks. For the first research work, a dynamic radio resource slicing framework is presented, which facilitates spectrum bandwidth sharing among heterogeneous wireless base stations (BSs) to achieve differentiated QoS guarantee for both mobile data and machine-to-machine services. Specifically, a network utility maximization problem is formulated, with the consideration of different traffic/service characteristics and network load conditions, to determine a set of optimal radio bandwidth slicing ratios. For the second research work, a computing task offloading problem is investigated in a 5G-assisted autonomous vehicular network, from the perspective of balancing the long-term network-wide computation load with minimum number of offloading decision switching times. To deal with the unknown state transition probability and large state-action spaces, a multi-agent deep Q-learning (MA-DQL) module is designed, in which all the agents cooperatively learn a joint optimal task offloading policy based on local observations. Some future research directions will also be pointed out at the end of the talk.


Bio: Dr. Qiang Ye received the Ph.D. degree in electrical and computer engineering from the University of Waterloo, Canada, in Sept. 2016. He was a Post-Doctoral Fellow and then a Research Associate with the same department at the University of Waterloo, from Dec. 2016 to Sept. 2019. Since Sept. 2019, he has been an Assistant Professor with the Department of Electrical and Computer Engineering and Technology, Minnesota State University, USA. His research interests include network slicing for 5G, software-defined networking and network function virtualization, AI-enabled resource management for next-generation wireless networks, channel access protocol design and performance analysis for Internet of Things.

Back to top

© Concordia University