Physics Constrained Flow Neural Network for Short-Timescale Predictions in Data Communications Networks
This work addresses the challenge of accurate short-timescale predictions in data communications networks, which is crucial for network management and optimization, though it appears incremental by adding physics constraints to existing neural network approaches.
The paper tackles the problem of predicting short-timescale information flows in data communications networks by introducing Flow Neural Network (FlowNN), which incorporates physics constraints to improve feature representation. The result is a 17% to 71% loss decrease compared to state-of-the-art baselines on synthetic and real-world datasets.
Machine learning is gaining growing momentum in various recent models for the dynamic analysis of information flows in data communications networks. These preliminary models often rely on off-the-shelf learning models to predict from historical statistics while disregarding the physics governing the generating behaviors of these flows. This paper instead introduces Flow Neural Network (FlowNN) to improve the feature representation with learned physical bias. This is implemented by an induction layer, working upon the embedding layer, to impose the physics connected data correlations, and a self-supervised learning strategy with stop-gradient to make the learned physics universal. For the short-timescale network prediction tasks, FlowNN achieves 17% - 71% of loss decrease than the state-of-the-art baselines on both synthetic and real-world networking datasets, which shows the strength of this new approach.