A Deep Reinforcement Learning-Based Approach for Adaptive SFC Deployment in Multi-Domain Networks

The emergence of virtualization technologies such as Software Defined Networking (SDN) and Network Function Virtualization (NFV) has enabled efficient service delivery by Service Function Chains (SFCs) deployment. SFCs deployment involves the optimal placement of Virtual Network Functions (VNFs) to satisfy service requirements and minimize deployment cost. Deep Reinforcement Learning (DRL) method could learn optimal decision-making policies in dynamic and uncertain environments. Therefore, we propose a DRL approach to solve the adaptive SFC deployment problem (DRL-SFCD) in multi-domain networks. First, the adaptive SFC deployment problem in multi-domain networks is formulated as a multi-objective optimization model with the aim of maximizing Service Deployment Successful Ratio (SDSR) and minimizing SFC Deployment Rescource Cost (SDRC). Then, a DRL algorithm is constructed based on Markov Decision Process (MDP) model to select the optimal servers and map virtual links cost-efficiently. Finally, we evaluate our approach and the results demonstrate that our approach out-performs comparison algorithms in terms of SDSR and SDRC.