Agile All-photonic Network Research Articles

New Scheduling Algorithms for Agile All-Photonic Networks

AbstractAn optical overlaid star network is a class of agile all-photonic networks that consists of one or more core node(s) at the center of the star network and a number of edge nodes around the core node. In this architecture, a core node may use a scheduling algorithm for transmission of traffic through the network. A core node is responsible for scheduling optical packets that arrive from edge nodes and switching them toward their destinations. Nowadays, most edge nodes use virtual output queue (VOQ) architecture for buffering client packets to achieve high throughput. This paper presents two efficient scheduling algorithms called discretionary iterative matching (DIM) and adaptive DIM. These schedulers find maximum matching in a small number of iterations and provide high throughput and incur low delay. The number of arbiters in these schedulers and the number of messages exchanged between inputs and outputs of a core node are reduced. We show that DIM and adaptive DIM can provide better performance in comparison with iterative round-robin matching with SLIP (iSLIP). SLIP means the act of sliding for a short distance to select one of the requested connections based on the scheduling algorithm.

Flow-based load-balancing architecture for the agile all-photonic network

A novel routing architecture that balances incoming Internet flows over the agile all-photonic network (AAPN) is proposed. The architecture is based on the adaptive highest random weight (adaptive HRW) algorithm proposed to design load-balanced Internet routers. Extensive numerical evaluation of static and adaptive variations of the routing architecture is studied, and their effect on the network performance in terms of packet drop and flow remapping is presented. The architecture can be seen as a combination of adaptive core node scheduling and adaptive load balancing at the edge nodes. It is stateless and can compute routes quickly based on the packet flow identifier.

Response of fibre optic parametric amplifiers to channel add/drop in agile all-photonic networks

Using numerical simulations, we investigate the performance of fibre optical parametric amplifiers (FOPAs) within the context of agile, multi-wavelength photonic networks. In particular, we study the steady-state and dynamic response of FOPAs following changes in network operating conditions. These include changes in the gain spectrum (gain tilt) due to variations in the total input power to the amplifier or as a result of channel add/drop, as well as the characteristics of the gain transients following channel add/drop. Initially, we examine the worst case scenario where all channels are in-phase and exactly equispaced. We compare these results with the ones obtained for random initial phases and inexact channel spacings. We find that the complex nature of the interactions occurring in a FOPA make it very difficult to predict their behaviour a priori and their deployment in WDM systems will require special attention. Moreover, we confirm that unequal spacing can vastly improve the performance of multichannel FOPAs.

Topological design and dimensioning of Agile All-Photonic Networks

We present the design and analysis of an Agile All-Photonic Network (AAPN); in the context of our study, the agility is derived from sub-microsecond photonic switching and global network synchronization. We have articulated a set of circuit design alternatives in terms of switch configurations referred to as symmetric and asymmetric designs, and two-layer and three-layer designs and discuss the implications of these alternatives in terms of transmitter and receiver design and synchronization requirements. In order to evaluate performance and cost of this range of design alternatives, we developed a set of software tools and methodologies for designing and dimensioning our vision of an AAPN. The topological design problem consists of determining the optimal number, size and placement of edge nodes, selector/multiplexers and core switches as well as the placement of the DWDM links so as to minimize network costs while satisfying performance requirements of the supported traffic. A new mixed integer linear programming formulation is presented for core node placement and link connectivity. A methodology has been developed for two-layer and three-layer network topology design and implemented in software. These tools were exercised under a wide variety of equipment cost assumptions for both a metropolitan network and a long-haul network assuming a gravity model for traffic distribution and a flat community of interest factor. Key findings include the determination of near cost optimal designs for both metropolitan (two-layer design) and a Canadian wide area network (WAN, three-layer design). We also show the cost and topology sensitivity to the selector switch size and the preferred size in terms of port count and number of switches.