Light-trail is an efficient and feasible technology for IP transport over all-optical networks. The proposition of light-trails for all-optical networks has demonstrated a number of advantages over other paradigms such as Wavelength Routing (WR), Optical Burst Switching (OBS) and Optical Packet Switching (OPS). This article tackles the routing problem of light-trails with the solution objective of minimizing the number of needed light-trails to accommodate an offered traffic matrix. We present two enhancements to the Integer Linear Programming (ILP) formulation of the routing problem. We also propose a computationally efficient routing heuristic for use with static and incremental traffic models. The heuristic is based on routing flows one-by-one. This is done by assigning a set of attributes to each flow and to each network path. The flow attributes are used to determine the order in which flows are presented to the routing algorithm. The path attributes are used to determine which path is selected to route the flow at hand. The efficiency of the proposed heuristic is confirmed using example problems of different network topologies.

No abstract

No abstract

No abstract

Abstract:The paper addresses the issue of reserving resources at packet switches along the path of flows requiring a deterministic bound on end-to-end delay. The switches are assumed to schedule outgoing packets using the RateControlled Earliest-Deadline-First (RC-EDF) scheduling discipline. EDF is known to be an optimal scheduling discipline for deterministic delay services in the single scheduler case. We propose a number of static and dynamic reservation policies for mapping the end-to-end delay requirement of a flow into local delay deadlines to be reserved at each scheduler. These policies are based on non-even resource reservation where the resources reserved depend on the capacities and loading at each node in the network. We define and prove the optimality of a certain non-even policy for the case of a single path network with homogenous static traffic. We present extensive simulation results for different scenarios which show that dynamic non-even resource reservation provides superior performance when compared to simple policies such as even dividing of end-to-end delay among the schedulers.