A reinforcement learning approach based on convolutional network for dynamic service function chain embedding in IoT

Network communication technologies are developing rapidly in various scenarios, such as 6G, SDN/NFV, and IoT. And the demand for dynamic service function chain orchestration is increasing day by day. Due to the dynamic complexity of IoT networks, the service function chain (SFC) embedding problem in IoT scenarios is more difficult. In this paper, a reinforcement learning algorithm based on convolutional neural network is first applied to SFC embedding, combined with DQN's experience pool reply and target network mechanism. The proposed scheme is verified in three typical complex networks: Random network, BA scale-free network, and small-world network. The experimental data suggest that the applicability of the approach proposed in IoT scenarios and, on the whole, the proposed algorithm can achieve lower latency and faster convergence performance than the mainstream algorithms with the increase of SFC number and node number.