Per-flow performance analysis in network coding: An approach based on real-time calculus

Network coding provides a powerful mechanism for improving performance of communication networks. In this paper, we present an analytical approach for per-flow performance analysis in network coding. Prior work on performance analysis in network coding mainly focuses on the throughput of the overall network. Our approach aims to analyze the end-to-end performance of each flow in the network. The theoretical basis of our approach is Real-Time Calculus (RTC). Under the framework of RTC, we obtain theoretical formulations for computing the backlog and delay bounds of flows in network coding. Based on the formulations, we evaluate the per-flow performance in representative scenarios and investigate the effect of coding opportunities. Numerical results show that the coding opportunities at coding nodes can significantly affect the end-to-end performance of flows in network coding.