VNE solution for network differentiated QoS and security requirements: from the perspective of deep reinforcement learning

The rapid development and deployment of network services has brought a series challenges to researchers. On the one hand, needs Internet end users/applications reflect characteristics travel alienation, they pursue different perspectives service quality. other with explosive growth information in era big data, lot private is stored network. End naturally start pay attention security. In order solve requirements differentiated quality (QoS) security, this paper proposes virtual embedding (VNE) algorithm based on deep reinforcement learning (DRL), aiming at CPU, bandwidth, delay security attributes substrate DRL agent trained environment constructed by above attributes. purpose deduce mapping probability each node map according probability. Finally, breadth first strategy (BFS) used links. experimental stage, compared representative algorithms three aspects: long term average revenue, revenue consumption ratio acceptance rate. results show that proposed achieved good results, which proves can be effectively applied user/application QoS requirements.