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

杨利霞

RouteNet: Leveraging Graph Neural Networks for

0 s, I8 e2 D% a/ b% A; h

Network Modeling and Optimization in SDN

: k% J# a* G+ L3 [) T
+ \  }  ?2 f$ X" F* S- j
Network modeling is a key enabler to achieve
effificient network operation in future self-driving Software
Defifined 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
( E) I0 |$ O1 Vtraffific 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 traffific intensity. In our eval
uation, we show that RouteNet is able to predict accurately
1 [  r. E3 F* D. N: f2 }  ^the delay distribution (mean delay and jitter) and loss even in
topologies, routing and traffific unseen in the training (worst case
# q) j, I; P# B9 D3 `, F. Y; HMRE = 15.4%). Also, we present several use cases where we
leverage the KPI predictions of our GNN model to achieve
effificient routing optimization and network planning.

6 T0 ]1 \+ s  {3 t
+ {  z& m$ w2 c' o4 [$ Q0 _5 R1 f