RouteNet: Leveraging Graph Neural Networks for Network Modeling and Optimization in SDN

By Krzysztof Rusek, José Suárez-Varela, Paul Almasan, Pere Barlet-Ros, Albert Cabellos-Aparicio. IEEE Journal on Selected Areas in Communications, 2019

338 citations recorded by the source corpus.

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 paper 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 predict accurately the delay distribution (mean delay and jitter) and loss even in topologies, routing and traffic unseen in the training (worst case MRE = 15.4%). Also, we present several use cases where we leverage the KPI predictions of our GNN model to achieve efficient routing optimization and network planning.

Subfields: Artificial Intelligence, Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/880dddc15a7e1ac0523e40d4b265512984af0535

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. H. Vincent Poor

In Computer Networks and Communications

1. H. Vincent Poor
2. Yonghui Li
3. Branka Vucetic
4. Changyang She
5. Chengjian Sun
6. Zhouyou Gu
7. Chenyang Yang

In Electrical and Electronic Engineering

1. Yonghui Li
2. Chenyang Yang
3. H. Vincent Poor
4. Branka Vucetic
5. Zhiguo Ding
6. Yuanwei Liu
7. Robert Schober
8. Merouane Debbah

Citations in the corpus

• A Tutorial on Ultrareliable and Low-Latency Communications in 6G: Integrating Domain Knowledge Into Deep Learning (2021, methodology): “As summarized in Table 8, DRL algorithms have been applied in wireless networks for mobile networking [247]–[249], scheduler design [250]–[254], resource allocation [255], [256], [258], [260]–[262], and routing [263], [264].”
• Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence (2023, methodology): “[47] proposed RouteNet, which uses GNN to accurately evaluate the end-to-end delay and packet loss of network paths.”