PhD Seminar • Systems and Networking • Model-driven Slice Resource Optimization in 5G and Beyond Networks

Please note: This PhD seminar will take place in DC 1304.

Muhammad Sulaiman, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Raouf Boutaba

A pivotal attribute of 5G networks is their capability to cater to diverse application requirements. This is achieved by creating logically isolated virtual networks, or slices, tailored to the requirements of different use cases. However, efficiently allocating resources to slices to maintain their quality of service (QoS) is challenging due to time varying traffic, and the complex relationship between resource allocation and the QoS. Existing approaches in this domain use mathematical slice models (e.g., queueing models) or simulations, and various optimization methods but struggle with optimality, tractability, and generalizability.

In this talk, I will present MicroOpt, a novel framework that leverages a differentiable neural network-based slice model with gradient descent for resource optimization and Lagrangian decomposition for QoS constraint satisfaction. MicroOpt was evaluated against two state-of-the-art approaches using an open-source 5G testbed with real-world traffic traces. Our results demonstrate up to 22% improvement in resource allocation compared to these approaches across various scenarios, including different QoS thresholds and dynamic slice traffic.