End-to-End Delay Modeling via Leveraging Competitive Interaction Among Network Flows

End-to-end (E2E) delay modeling is crucial to network operation and optimization, which is the key enabler for Knowledge-Defined Networking (KDN) and network Digital Twins (DT). Neural network-based methods have been widely applied in this research area and have made significant progress. However, previous work modeled E2E delay with node/link states in the network topology graph, ignoring competitive interactions among E2E flows. To this end, we propose a flow interaction graph construction method. By introducing the flow interaction graph, our proposed method can mine the bandwidth contention information among E2E flows. Meanwhile, with the help of the network context-aware encoding method, we propose a flow interaction graph transformer (FI-Graphormer) model, which can effectively utilize the competitive relationships represented in the flow interaction graph. Experimental results on the publicly available datasets of TnCwD, NSFNET and Geant2 show that FI-Graphormer achieves competitive results, which is superior to the state-of-the-art methods.