Automatic Virtual Network Embedding: A Deep Reinforcement Learning Approach With Graph Convolutional Networks

TLDR

Virtual network embedding maps virtual services onto substrate components, and its performance is critical for virtualized network efficiency, yet most algorithms cannot deliver automatic solutions quickly. The study seeks to automatically detect dynamic network states and provide optimal embedding solutions by integrating deep reinforcement learning with graph convolutional networks. It employs a deep reinforcement learning framework that uses graph convolutional networks, a parallel training scheme, and a multi‑objective reward function to efficiently embed virtual networks. Simulation results show the algorithm outperforms state‑of‑the‑art methods, improving acceptance ratio by up to 39.6% and average revenue by 70.6%, and demonstrating robust performance across scenarios.

Abstract

Virtual network embedding arranges virtual network services onto substrate network components. The performance of embedding algorithms determines the effectiveness and efficiency of a virtualized network, making it a critical part of the network virtualization technology. To achieve better performance, the algorithm needs to automatically detect the network status which is complicated and changes in a time-varying manner, and to dynamically provide solutions that can best fit the current network status. However, most existing algorithms fail to provide automatic embedding solutions in an acceptable running time. In this paper, we combine deep reinforcement learning with a novel neural network structure based on graph convolutional networks, and propose a new and efficient algorithm for automatic virtual network embedding. In addition, a parallel reinforcement learning framework is used in training along with a newly-designed multi-objective reward function, which has proven beneficial to the proposed algorithm for automatic embedding of virtual networks. Extensive simulation results under different scenarios show that our algorithm achieves best performance on most metrics compared with the existing state-of-the-art solutions, with upto 39.6% and 70.6% improvement on acceptance ratio and average revenue, respectively. Moreover, the results also demonstrate that the proposed solution possesses good robustness.