RouteNet: Leveraging Graph Neural Networks for Network Modeling and Optimizat...

杨利霞

RouteNet: Leveraging Graph Neural Networks for

Network Modeling and Optimization in SDN

Network modeling is a key enabler to achieve
effificient network operation in future self-driving Software
Defifined Networks. However, we still lack functional network
$ o/ ~' C: t! K. Kmodels able to produce accurate predictions of Key Performance
. u6 [% R0 |/ F/ Y  m2 a  sIndicators (KPI) such as delay, jitter or loss at limited cost.
2 k) [* |. W4 D! @3 CIn 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
traffific to produce accurate estimates of the per-source/destination
per-packet delay distribution and loss. RouteNet leverages the
  q/ J  y4 f) s' f, l$ D6 Oability 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 traffific intensity. In our eval
+ E' d& m9 J" X! ]5 l. c* luation, we show that RouteNet is able to predict accurately
0 U3 _' q# m# H$ d9 othe delay distribution (mean delay and jitter) and loss even in
topologies, routing and traffific 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
6 w( P( I9 ~) d8 D1 a2 neffificient routing optimization and network planning.

- J& l4 W. G) d