Routenet: Using Graph Neural Networks for SDN Network Modeling and Optimizations

Abstract

This paper presents a simple and novel architecture for high-speed and low-cost processors based upon Software-Defined Networking  (SDN), strictly  neural networks, to solve combinatorial optimization problems within  time. Software-Defined Networking (SDN) simplifies network management by separating the control plane from the data forwarding plane. However, the plane separation technology introduces many new loopholes in the SDN data plane. In order to facilitate taking proactive measures to reduce the damage degree of network security events, this paper proposes a security situation prediction method based on particle swarm optimization algorithm and long-short-term memory neural network for network security events on the SDN data plane. Network modeling is a key enabler to achieve efficient network operation in future self-driving Software-Defined Networks. However, we still lack functional network models able to produce accurate predictions of Key Performance Indicators (KPI) such as delay, jitter or loss at limited cost. In this report, we propose RouteNet, a novel network model based on Graph Neural Network (GNN) that is able to understand the complex relationship between topology, routing, and input traffic to produce accurate estimates of the per-source/destination per packet delay distribution and loss. RouteNet leverages the ability of GNNs to learn and model graph-structured information and as a result, our model is able to generalize over arbitrary topologies, routing schemes and traffic intensity. In our evaluation, we show that RouteNet is able  to accurately predict the delay distribution (mean delay and jitter) and loss even in topologies, routing and traffic unseen in the training. Also, we present several use cases where we leverage the KPI predictions of our GNN model to achieve efficient routing optimization and network planning.