Virtual Cross-Flow Detouring in the Deterministic Network Calculus Analysis

Deterministic Network Calculus (DNC) is commonly used to compute bounds on the worst-case communication delay in data networks. It provides various analyses to derive these bounds from a model, giving different tradeoffs between accuracy and analysis efficiency. Improving the tradeoff led to increasingly complex algorithms. We set out to design a novel DNC algorithm that is of low complexity while still providing competitive delay bounds. To achieve this goal, we make use of the insight that added pessimism in the model can alleviate more severe limitations of the DNC analysis. To that end, we introduce the concept of virtual cross-flow detouring where data flows are assumed to cross additional servers. Ultimately, we provide a heuristic that is simple, fast and high-quality. We show in numerical evaluations that our detouring not only provides a competitive alternative, it also outperforms current algebraic algorithms' delay bounds for >50% of analyzed flows.