报告题目：Digital Twin-empowered Intelligent Management for 5G Network Slicing
活动时间：2023年8月17日（周四）15:30-16:30
活动地点：同济大学嘉定校区智信馆701室
腾讯会议号 940 390 846，密码 551070
报告人：埃克塞特大学 Dr. Haozhe Wang
报告内容：
Network slicing has emerged as a promising networking paradigm in 5G to support a variety of emerging applications with diverse performance and flexibility requirements, such as Industry 4.0, VR/AR, and remote healthcare. However, the unprecedented network complexity poses a significant challenge in network management due to the vast amount of generated data and stringent Quality-of-Service (QoS) requirements. Digital Twin (DT) technology paves the way for achieving cost-efficient and performance-optimal management by creating a virtual representation of slicing-enabled networks in a digital manner to simulate its behaviours and predict the performance after changes. We will introduce our recent research on DT-empowered intelligent management scheme for 5G Network Slicing, aiming to capture the rich interdependency among network slices, resource utilisation, and physical infrastructure and to monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT leverages the novel Graph Neural Network (GNN) model to gain insights directly from the network slices represented in a non-Euclidean graph structure. It also utilises an inductive framework to achieve generalisation across various network environments and make predictions for unseen scenarios.
报告人：
Haozhe Wang is a lecturer at the University of Exeter in the United Kingdom. He obtained his Ph.D. degree from the University of Exeter in 2017. His primary research areas include 5G network slicing resource management and optimisation, learning-based network optimisation algorithm design, content-centric network caching strategies, and network analysis modelling. He has published more than 18 academic journal and international conference papers, including IEEE TII, IEEE JSAC, IEEE TNSE, and has contributed to one English monograph. He has received the Best Paper Award twice and the Outstanding Contribution Service Award four times at international conferences. Additionally, he has chaired four international academic workshops and was invited to give academic talks (Invited Talk) at IEEE HPCC 2018 and ISPA 2020 conferences. Furthermore, Haozhe Wang has led and participated in two projects funded by the Engineering and Physical Sciences Research Council (EPSRC) of the United Kingdom, three European Union projects, and four industrial collaboration projects.