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

3 L7 `) K4 z5 Y% `  C
5 r1 ^1 z. A) W$ e" j' L
  k2 A% L( B3 C- o5 `! X4 N9 T8 oNetwork modeling is a key enabler to achieve
( c: Q. m" N3 ^  _1 j) a5 ?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.
! O7 j. [; k; r1 a, tIn 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' ]3 D8 J# P% m1 S' s& E* X7 }traffific to produce accurate estimates of the per-source/destination
" c( Z, n% l$ K/ a+ a4 sper-packet delay distribution and loss. RouteNet leverages the
4 Q6 C9 Q; E8 x  D: I& W0 N( gability of GNNs to learn and model graph-structured information
) s9 l' X1 h  mand as a result, our model is able to generalize over arbitrary
topologies, routing schemes and traffific intensity. In our eval
2 e# Q; S* i' Q* j. v/ Fuation, we show that RouteNet is able to predict accurately
the 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
5 X5 s2 u3 n9 i2 ]+ T3 T, eleverage the KPI predictions of our GNN model to achieve
effificient routing optimization and network planning.
  [, M( g+ w" X7 v  V

' z$ x4 }3 Y9 X, f2 `! ]$ o