A Little Data Is Enough: Criticality-Aware Range Routing for Wide Area Networks

Abstract

The rapid development of Wide Area Networks (WANs) in recent years has imposed new requirements on Traffic Engineering (TE) solutions in terms of robust to frequent and dynamic traffic fluctuations, scalable to maintain computational efficiency, and working well with limited historical traffic data. However, existing TE solutions generally struggle to achieve all three requirements simultaneously. Model-based solutions often fall short in realizing both good scalability and robustness against traffic fluctuations. Although recent deep learning-based solutions achieve strong scalability and robustness for public datasets, their effectiveness heavily relies on large numbers of Traffic Matrices (TMs). In this paper, we propose Criticality-Aware Range Routing (CARR) to achieve the three requirements using two techniques. First, we propose data and model hybrid-driven approach to alleviate dependence on large-scale datasets by integrating deep reinforcement learning with existing well-established routing models. Second, we develop hierarchical collaborative multi-model optimization to achieve both robustness and scalability by properly distributing routing tasks of TE to different routing models based on their specific features. Evaluations on public datasets with real traffic traces demonstrate that CARR achieves good performance using only 96 TMs, improving the worst-case performance by 79% at the cost of 2% median-case performance, and reduces computational overhead by more than $10\times $ .