Abstract:
SDN and NFV make cloud Service Function Chain (SFC) deployment efficient and flexible. However, without knowledge of underlying network configurations, overlay networks cannot efficiently chain Virtualized Network Functions (VNFs). Many deterministic VNF placement and chaining methods are complex and require substrate network state information.
Luckily, Reinforcement Learning (RL) can learn to make good decisions without prior knowledge. Thus, we propose an RL approach for efficient SFC provision in overlay networks where VNFs from multiple vendors have different performance.
For benchmarking, we first form an Integer Linear Programming (ILP) model. Next, we model online SFC path selection as a Markov Decision Process (MDP) and propose a policy-gradient-based solution.
Finally, we simulate randomly generated SFC requests and a real-world video streaming dataset with an emulation system to verify feasibility. Our method performs similarly to ILP-based and better than deep Q-learning, random, and load-least-greedy methods.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
