This paper addresses a fundamental problem in resource management for flow-based hybrid switching systems. Such systems aim at efficient transport of layer-3 connectionless IP traffic over layer-2 connection-oriented ATM switching fabrics. One idea behind flow-based hybrid switching is to decompose individual IP packet streams into flows and then to classify them into short-lived and long-lived flows. While the short-lived flows are good for forwarding by the embedded software through permanent virtual connections (PVCs), the long-lived flows are more effectively transmitted by hardware through switched virtual connections (SVCs). Clearly the flow identification/classification mechanism will have great impact on the utilization of the system's resources. Our paper focuses on the resources which are directly associated with packet processing power, signaling capacity, and flow cache table size. Our study indicates that the presently available static flow classification methods have a vital shortcoming in balancing the utilization of the system's resources. We propose a novel approach for adaptive flow classification based on the min-max objective for the system resource utilizations to match with the time-varying traffic/resource characteristics based on the monotone properties and sensitivity analysis of the resource utilizations as functions of the control parameters, we first prove that the optimal solution of the static min-max problem is achieved at a unique balance point for the resource utilizations. With the intuition gained from the static results, we then design an adaptive controller formulated as a hierarchical stochastic automata control system with local search. The optimality of the proposed adaptive controller is tested against the static optimal control based on real trace simulations. The simulation studies in highly nonstationary environments show the viability of the proposed flow adaptation for dynamic resource management in hybrid switching system design. The algorithm is simple to implement and only requires the adaptation of two global variables at time intervals of every few seconds based on the present usage of resources.
Read full abstract