Network virtualization involves transforming traditional hardware-based network components into software-based alternatives for benefits such as scalability, flexibility, and cost savings. Along with the proliferation of IoT devices and edge-native data, network virtualization is expanding to edge clouds and the proximity of IoT devices for pervasive connectivity, on-demand protection, and utmost privacy, which are necessities of the upcoming 6G communication. Nevertheless, heterogeneous and unpredictable edge environments present new challenges to implementing network virtualization effectively.

During this presentation, I will share my research on reliable and intelligent network virtualization in edge-cloud systems. I will first introduce a novel framework that enhances the reliability of virtual network functions (VNFs) in or close to the proximity of IoT and end users. This framework ensures the end-to-end reliability of interconnected VNFs under limited budgets and non-stationary failures via online approximation algorithms. Additionally, the framework includes a self-adaptive VNF backup architecture to handle more constrained scenarios, such as VNFs located near IoT devices with few resources to support basic redundancy. Besides reliability improvement designs, I will further present a new edge computing system that practically supports on-demand and high-quality virtual services to IoT and mobile users using a Function-as-a-Service (FaaS) pattern. Finally, I will cover my ongoing and future research focused on integrating AI and edge-cloud networks through advanced virtualization architectures, paving the way to pervasive network intelligence for 6G communication.

Xiaojun Shang is a Ph.D. candidate at SUNY Stony Brook, advised by Professor Yuanyuan Yang. His research interests lie in network virtualization, edge-cloud computing, online optimization, and AI/network integration. Xiaojun's current research aims to guarantee reliability and efficiency of network virtualization in heterogeneous edge-cloud systems. He is also working on integrating AI and serverless paradigm to edge-cloud networks for upcoming 6G communication. During his Ph.D. studies, he authored 19 publications, including a paper that was awarded the Best Paper Award at the IEEE International Conference on Computer Communications (INFOCOM).