Reliability-Aware Placement of Virtual Network Functions via Multi-Agent Deep Reinforcement Learning

Network Function Virtualization (NFV) often suffers from unexpected failures in some mission-critical applications due to the reliability-agnostic deployment of Virtual Network Functions (VNFs), thus achieving suboptimal service performance. To cope with this issue, we propose a Reliability-aware VNF service Provisioning (RVFP) approach for NFV-based networks via Multi-Agent Deep Reinforcement Learning (MADRL), where each VNF is hosted and backed up in appropriate hardware with reliability guarantees. Specifically, a novel MADRL-based framework for VNF placement is designed with two alternating optimization objectives, namely maximizing reliability and minimizing VNF instance failure probability, to incorporate diverse objective landscapes and encourage broader exploration within the solution space. Furthermore, two agent allocation strategies are developed to alternately arrange the tasks of collaborative agents for reliability-aware placement of VNFs in a parallel and cooperative manner. Besides, the newly-designed prioritized experience sampling, built on reward and sampling frequency, is used to better exploit valuable experiences for faster model training. Extensive simulation results obtained from various scenarios show that RVFP can significantly improve placement reliability and service acceptance ratios for VNF deployment compared with the state-of-the-art approaches.