The IEEE Toronto Vehicular Technology Chapter is hosting two talks as part of their Rising Star Series! Haixia Peng and Huaqing Wu are at their final stages of their PhD studies at the University of Waterloo. They will share their research on mobile edge computing/caching/ communication, network slicing, Artificial Intelligence (AI) enabled IoV networks, and integrated space-air-ground vehicular networks during their PhD studies.
Location: All events are held with Zoom Meeting
Meeting ID: 968 0829 0854
Contact: Please contact Lian Zhao at email@example.com for any questions
The details of each talk are below.
Intelligent Multi-Dimensional Resource Slicing in MEC-Assisted Vehicular Networks
Date & Time: Tuesday, March 16, 2021
7:00 p.m. – 8:00 p.m.
Speaker: Haixia Peng, University of Waterloo
Abstract: Benefiting from advances in the automobile industry and wireless communication technologies, the vehicular network has been emerged as a key enabler of intelligent transportation services. However, with more and more services and applications, mobile data traffic generated by vehicles has been increasing and the issue of the overloaded computing task has been getting worse. Because of the limitation of spectrum resources and vehicles’ onboard computing/caching resources, it is challenging to promote vehicular networking technologies to support the emerged services and applications, especially those requiring sensitive delay and diverse resources. To effectively address the above challenges, two potential technologies, multi access edge computing (MEC) and unmanned aerial vehicle (UAV), can be exploited in vehicular networks. In this presentation, I will introduce how to adopt optimization and AI technologies for efficient resource slicing, and therefore supporting various applications with satisfied quality of service (QoS) requirements in MEC- and/or UAV-assisted vehicular networks. For a relatively simple vehicular network scenario with only terrestrial MEC servers, a model-based method is applied for dynamic spectrum management, including spectrum slicing, spectrum allocating, and transmit power controlling. For a vehicular network supported by both terrestrial and aerial MEC servers, an AI-based method is applied to effectively manage the spectrum, computing, and caching resources while satisfying the QoS requirements of different applications.
Haixia Peng received her M.S. and Ph.D. degrees in Electronics and Communication Engineering and Computer Science from Northeastern University, Shenyang, China, in 2013 and 2017, respectively. She is currently a Ph.D. student in the Department of Electrical and Computer Engineering at the University of Waterloo, Canada. Her current research focuses on Internet of vehicles, resource management, multi-access edge computing, and reinforcement learning. She has authored or co-authored more than 30 technical papers. She serves/served as a reviewer for IEEE Journals on Selected Areas in Communications (JSAC), IEEE Transactions on Communications, IEEE Transactions on Vehicular Technologies, etc. more than 20 prestigious journals, and as a TPC member in IEEE ICC, Globecom, VTC, etc. conferences.
Content Caching and Delivery in Heterogeneous Vehicular Networks
Date & Time: Tuesday, March 30, 2021
7:00 p.m. – 8:00 p.m.
Speaker: Huaqing Wu, University of Waterloo
Abstract: Connected and automated vehicles (CAVs), which enable information exchange and content delivery in real time, are expected to revolutionize current transportation systems. However, the emerging CAV applications such as content delivery pose stringent requirements on latency, throughput, and global connectivity. To empower multifarious CAV content delivery, heterogeneous vehicular networks (HetVNets), which integrate the terrestrial networks with aerial networks and space networks, can guarantee reliable, flexible, and globally seamless service provisioning. In addition, edge caching can facilitate content delivery by caching popular files in the HetVNet access points (APs) to relieve the backhaul traffic with a lower delivery delay. In this talk, we investigate the content caching and delivery schemes in the caching-enabled HetVNet. First, we study the content caching in terrestrial HetVNets with intermittent network connections. A coding-based caching scheme is designed and a matching-based content placement algorithm is proposed to minimize the content delivery delay. Second, UAV-aided caching is considered to assist vehicular content delivery in aerial-ground vehicular networks (AGVN) and a joint caching and trajectory optimization (JCTO) problem is investigated to jointly optimize content caching, content delivery, and UAV trajectory. To enable real-time decision-making in highly dynamic vehicular networks, we propose a deep supervised learning scheme to solve the JCTO problem. Third, we investigate caching-assisted cooperative content delivery in space-air-ground integrated vehicular networks (SAGVNs), where the vehicle-to-AP association, bandwidth allocation, and content delivery ratio are jointly optimized. To address the tightly coupled optimization variables, we propose a load- and mobility-aware cooperative delivery scheme to solve the joint optimization problem with the consideration of user fairness, load balancing, and vehicle mobility.
Huaqing Wu received the B.E. and M.E. degrees in Electrical Engineering from Beijing University of Posts and Telecommunications, Beijing, China, in 2014 and 2017, respectively. She is currently working toward the Ph.D. degree at the Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada. Her current research interests include vehicular networks with emphasis on edge caching, wireless resource management, space-air-ground integrated networks, and application of artificial intelligence (AI) for wireless networks. She has authored/co-authored more than 30 technical papers which are published in prestigious refereed journals (IEEE JSAC, TWC, WCM, etc.) and conferences (IEEE ICC, Globecom, VTC, etc.).