Comprehensive fault diagnosis for multiple coupled SFCs based on deep learning

Abstract

Service Function Chains (SFCs) are deployed and executed in a complex network environment, where multiple SFCs are coupled by sharing various types of network functions and transmission links. As a result, diagnosing the state of these SFCs and accurately locating network fault becomes a challenge and plays a fundamental role in SFC management. In this paper, we introduce a comprehensive fault diagnosis mechanism for multiple coupled SFCs by applying the deep learning technique. By formulating the involved network nodes and transmission links into a heterogeneous graph model, we propose the Rendered Service Path Heterogeneous Graph Attention Network (RSP-HAN) model to comprehensively estimate the state of every network node and link. Typically, RSP-HAN first applies Bi-directional Long Short-Term Memory (Bi-LSTM) to normalize features from different types of network entities, then obtains the embedding results through intra-RSP and inter-RSP attention mechanisms. Finally, Multi-Layer Perceptron (MLP) is utilized to estimate the state of these network entities. We also setup an experiment platform and obtain extensive datasets to evaluate our RSP-HAN model. Experimental results show that RSP-HAN performs better in fault diagnosis for various types of network entities than several traditional methods and two deep learning-based baselines, the Graph Convolutional Network (GCN) and the Graph Attention Network (GAT).