Smart Internet Lab Seminar: Multi-Objective Deep Reinforcement Learning Assisted Service Function Chains Placement
Zoom
Speaker: Teresa Bi
Talk Title: Multi-Objective Deep Reinforcement Learning Assisted Service Function Chains Placement
Abstract: The study of Service Function Chains (SFCs) placement problem is crucial to support services flexibly and use resources efficiently. Solutions should satisfy various Quality of Service requirements, avoid edge resource congestion, and improve service acceptance ratio (SAR). This work presents a novel approach to address these challenges by solving a multi-objective SFCs placement problem based on the Pointer Network in multi-layer edge and cloud networks. We design a Deep Reinforcement Learning algorithm, called Chebyshev-assisted Actor-Critic Algorithm, to overcome the limitations of traditional heuristic and evolutionary algorithms. Then, we run this algorithm iteratively with a set of weights to obtain approximated Pareto Fronts (PFs), which have much higher hypervolume values than those obtained from other state-of-the-art algorithms. Moreover, running our algorithm individually with selected weights from PFs can avoid edge resource congestion and achieve 98% SARs of low-latency services during high-workload periods. Finally, based on both simulation and real testbed experimental results, it is validated that the proposed algorithm fits for pragmatic service deployment while achieving 100% of SARs in the use cases deployed on the testbed.
Bio
Teresa Yu Bi is a research associate in High Performance Networks group. She received the B.Sc. degree of Optical Information Science and Technology from Beijing Jiaotong University and then the M.Sc. with distinction in Communication Networks and Signal Processing from the University of Bristol. She is currently pursuing the Ph.D. degree at the University of Bristol. Her research interests include Network Optimization, Deep Reinforcement Learning, Game Theory, Network Function Virtualization, and Optical Networks.
Contact information
Please contact Rebecca Layland, Smart Internet Lab Project Coordinator - smart-internet-lab@bristol.ac.uk for more information about this talk