Placement of Parallelized Service Function Chain by Reusing Virtual Network Functions in Fog-Cloud Computing-based Networks

Network function virtualization technology transforms hardware middleboxes into sets of software-based Virtual Network Function (VNF ) that can host the growing demand for latency-sensitive services at the fog-cloud computing-based networks. Dynamic placement of service functions chain by reusing (VNF) instances can improve resource utilization and save time. To address this problem, we propose a parallelized service function chain placement method by reusing (VNF)  in fog-cloud computing-based networks. Here, the placement problem is configured using deep reinforcement learning approaches with the aim of maximizing long-term cumulative reward. By sharing (VNF) s in parallel, this method can achieve computational acceleration in providing online services. In addition, the proposed method increases the ability to accept future requests by extracting the distribution of the initialized (VNF) s. The simulation results show the superiority of the proposed method, where considering the monetary cost criterion of more than 7%, it performs better than the best existing methods.