.png){kind=icon}
.png){kind=icon}
Return
Routing-Oblivious and Data-Efficient Network Tomography With Flow-Based Generative Model
.png){kind=icon}
PRE
AI
DOI：10.1109/TON.2026.3665293.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Given the high cost associated with directly measuring the Traffic Matrix (TM), researchers have devoted efforts to devising methods for estimating the complete TM from low-cost link loads by solving a set of heavily ill-posed linear equations. Today’s increasingly intricate networks present an even greater challenge: as adaptive and dynamically changing routing strategies are gradually replacing traditional fixed routing schemes, the routing matrix within these equations can no longer be deemed reliable. In our previous work, we pioneered a flow-based generative model, FlowTM, which estimated the TM by establishing an invertible correlation between the TM and link loads without relying on the routing matrix. We demonstrated that the missing information in the ill-posed equations can be decoupled from the TM and learned jointly with the invertible mapping. Considering that acquiring a complete training set for FlowTM is often impractical in many real-world networks, we further propose an enhanced model, FlowTM+, in this extended work. It incorporates an Inspector module to mine deeper latent structures from the partially observed TM data and link load measurements. This new technique effectively compensates for unobservable information in the training data. Extensive experiments demonstrate that FlowTM improves the performance of the best baseline by 38%–58% when the actual routing matrix is absent. Remarkably, with only 2% of the training data, FlowTM+ achieves an estimation accuracy comparable to that of state-of-the-art baselines trained with full routing knowledge and complete training data.
Keywords:
Traffic matrix estimation
network tomography
flow-based generative model
Journal
I
IF:
0
Papers:
543
Citations:
0
View more organizations