Graph Neural Network based Service Function Chaining for Automatic Network Control

Software-defined networking (SDN) and the network function virtualization (NFV) led to great developments in software based control technology by decreasing expenditures. Service function chaining (SFC) is an important technology to find efficient paths in network servers to process all of the requested virtualized network functions (VNF). However, SFC is challenging since it has to maintain high Quality of Service (QoS) even for complicated situations. Although some works have been conducted for such tasks with high-level intelligent models like deep neural networks (DNNs), those approaches are not efficient in utilizing the topology information of networks and cannot be applied to networks with dynamically changing topology since their models assume that the topology is fixed. In this paper, we propose a new neural network architecture for SFC, which is based on graph neural network (GNN) considering the graph-structured properties of network topology. The proposed SFC model consists of an encoder and a decoder, where the encoder finds the representation of the network topology, and then the decoder estimates probabilities of neighborhood nodes and their probabilities to process a VNF. In the experiments, our proposed architecture outperformed previous performances of DNN based baseline model. Moreover, the GNN based model can be applied to a new network topology without re-designing and re-training.

I. Introduction

Reducing Capital Expenditure (CAPEX) and Operating Expenditure (OPEX) are consistently critical issues for telecommunication network service providers (NSPs). Before appearances of Software-Defined Network (SDN) and Network Function Virtualization (NFV), network functions were dependent on hardware middleboxes. The SDN technology [1] led to network traffic being controlled by a software-based control system. In addition, the NFV technology [2] led to network functions being virtualized and make them be separated from hardware middleboxes. With SDN and NFV technologies, NSPs are capable of deploying and processing Virtualized Network Functions (VNF) at a relatively low cost in terms of CAPEX and OPEX. These developments have led the software-based control system to receive much attention from NSPs. Also, high-level intelligent software-based control systems that operate networks automatically have become a central issue in the network field [3]. Fig. 1.

An example of an SFC task on network topology. The request list is updated by new or expired requests. The SFC model generates resulting paths for the active requests in the list. The bottom figure shows the resulting generated SFC paths of one request.