Coordinated Sketch-Based Traffic Monitoring in Dynamic Networks

As modern networks grow in scale and speed, sketch-based algorithms have become essential tools for accurate and low-overhead network monitoring. Existing solutions for sketch-based network monitoring assume that traffic rates in the network are fixed and known a priori. However, this assumption fails to reflect the real-world scenario of dynamic traffic rates, leading to degraded monitoring accuracy. In this paper, we introduce a novel approach for coordinated sketch placement on programmable network devices such as switches and SmartNICs without relying on the fixed traffic rate assumption. Instead, we consider scenarios with only statistical information about rates, such as their means and variances. To this end, we show that the problem can be formulated as a second-order optimization problem. Given the computational challenges of solving such optimization problems, we present an approximation technique to derive a linear formulation which can be solved efficiently even for large instances of the problem. Our evaluations using realistic workloads and network settings reveal that, by accounting for dynamic traffic rates, our approach can increase monitoring accuracy in the network by up to 2 x across different workloads compared to the existing solutions that do not explicitly consider these dynamics.