Machine Learning Assisted Network Slicing for Wireless Edge Computing System

5G and edge computing will serve various emerging use cases that have diverse requirements for multiple resources, e.g., radio, transportation, and computing. Network slicing is a promising technology for creating virtual networks that can be customized according to the requirements of different use cases. Provisioning network slices requires end-to-end resource orchestration which is challenging. This talk will discuss the challenges of end-to-end network slicing in wireless edge computing systems and present machine learning assisted network slicing solutions. First, the design of a new decentralized cross-domain resource orchestration solution will be presented. This solution optimizes the cross-domain resource orchestration while providing the performance and functional isolations among network slices. Second, a decentralized deep reinforcement learning algorithm will be designed to dynamically orchestrate resources for end-to-end network slicing. The system implementation and testbed design of the end-to-end network slicing system will also be discussed. Finally, future research directions in designing end-to-end network slicing solutions with machine learning will be shared.

Co-sponsored by: North Jersey Section, Signal Processing Chapter,

Speaker(s): Dr. Tao Han,

Agenda:
5G and edge computing will serve various emerging use cases that have diverse requirements for multiple resources, e.g., radio, transportation, and computing. Network slicing is a promising technology for creating virtual networks that can be customized according to the requirements of different use cases. Provisioning network slices requires end-to-end resource orchestration which is challenging. This talk will discuss the challenges of end-to-end network slicing in wireless edge computing systems and present machine learning assisted network slicing solutions. First, the design of a new decentralized cross-domain resource orchestration solution will be presented. This solution optimizes the cross-domain resource orchestration while providing the performance and functional isolations among network slices. Second, a decentralized deep reinforcement learning algorithm will be designed to dynamically orchestrate resources for end-to-end network slicing. The system implementation and testbed design of the end-to-end network slicing system will also be discussed. Finally, future research directions in designing end-to-end network slicing solutions with machine learning will be shared.

Room: M105, Bldg: Muscarelle Center, M105, , 1000 River Road , Teaneck , New Jersey, United States, 07666, Virtual: https://events.vtools.ieee.org/m/301143