Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN

@article{Rusek2019UnveilingTP,
  title={Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN},
  author={Krzysztof Rusek and J. Su{\'a}rez-Varela and Albert Mestres and P. Barlet-Ros and A. Cabellos-Aparicio},
  journal={Proceedings of the 2019 ACM Symposium on SDN Research},
  year={2019}
}
Network modeling is a critical component for building self-driving Software-Defined Networks, particularly to find optimal routing schemes that meet the goals set by administrators. [...] Key Method GNN are tailored to learn and model information structured as graphs and as a result, our model is able to generalize over arbitrary topologies, routing schemes and variable traffic intensity. In the paper we show that our model provides accurate estimates of delay and jitter (worst case R2 = 0.86) when testing…Expand
A benchmark for graph neural networks for computer network modeling
Path-Link Graph Neural Network for IP Network Performance Prediction
GDDR: GNN-based Data-Driven Routing
A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding
End-to-end Delay Prediction Based on Traffic Matrix Sampling
...
1
2
3
4
5
...

References

SHOWING 1-3 OF 3 REFERENCES
The Graph Neural Network Model
Performance evaluation of integrated OTN/DWDM networks with single-stage multiplexing of optical channel data units