Multi-Task Deep Learning Based Dynamic Service Function Chains Routing in SDN/NFV-Enabled Networks

摘要

With the development of Software-Defined Networks (SDNs) and Network Function Virtualization (NFV), Service Function Chains (SFCs), that steer the traffic through a series of specified Virtual Network Functions (VNFs) with predefined orders, has become a popular network service paradigm. Compared with the rule-based routing algorithms, deep-learning technology has great potential to achieve efficient path computation for SFC Requests (SFCRs) in an intelligent way. However, traditional intelligent models have trouble in the speed of convergence, which incurs long training time and high computation consumptions. In this paper, we propose a novel Multi-Task Deep Learning (MTDL) based architecture, which improve generalization by sharing related information of tasks, to assure fast convergence in training process, and an MTDL-based Routing Algorithm (MTDL-RA) to efficiently compute routing paths with the minimum end-to-end delay for SFCRs. Performance evaluation results demonstrate that our proposed MTDL-based architechture and routing algorithm can achieve significantly reduction in the training time and obtain high performance in terms of SFCR acceptance rate and the delay of paths, respectively.