The Impact of Link Scheduling on Long Paths: Statistical Analysis and Optimal Bounds
The authors study how the choice of packet scheduling algorithms influences end-to-end performance on long network paths. Taking a network calculus approach, they consider both deterministic and statistical performance metrics. A key enabling contribution for their analysis is a significantly sharpened method for computing a statistical bound for the service given to a flow by the network as a whole. For a suitably parsimonious traffic model they develop closed-form expressions for end-to-end delays, backlog, and output burstiness. The deterministic versions of their bounds yield optimal bounds on end-to-end backlog and output burstiness for some schedulers, and are highly accurate for end-to-end delay bounds.