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

5 `7 r/ o! ~' i! o% ]0 _0 G0 I% Y
3 ^5 y; i* [# e3 E1 A" sNetwork modeling is a key enabler to achieve
effificient network operation in future self-driving Software
' ]5 [3 W+ R- P$ o/ ^Defifined Networks. However, we still lack functional network
models able to produce accurate predictions of Key Performance
: V0 l. l5 k+ ?* Q+ {! KIndicators (KPI) such as delay, jitter or loss at limited cost.
In this paper we propose RouteNet, a novel network model based
5 [/ G/ B* I9 @( F4 D. don Graph Neural Network (GNN) that is able to understand
  e# A6 L/ t+ C) c/ dthe complex relationship between topology, routing, and input
1 s9 V  J4 a& u4 htraffific to produce accurate estimates of the per-source/destination
per-packet delay distribution and loss. RouteNet leverages the
: _4 A+ D. a; O$ K  gability 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
* s6 O, \9 g* Tthe 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
effificient routing optimization and network planning.
" m" Q; T# h2 J; t
" h9 Y3 `7 ]* P$ u: f# R* P9 v
9 k* q8 g0 I% m8 `1 Y, }; V