Optical Passive Star Research Articles

Scalability of Wavelength Division Multiplexed Optical Passive Star Networks with Range Limited Tunable Transceivers

The number of stations attached to a single optical passive star is limited by current state of the art in optical technology. Also, the wavelength range of tunable optical transceivers is limited by current technology. Many high performance computing applications require the use of large size regular topologies for communication between computing nodes. Scalability of passive star networks built with these two limitations becomes an important issue for building larger networks. This is the subject of our study in this paper. In a previous related work we explored the design issues for networks built on a single passive star employing transceivers of a limited tuning range. Here we extend that study by considering the problem of connecting several optical passive stars, each embedded with a given virtual topology, to create larger aggregate networks. The design issues are analyzed and a number of design rules are proposed for building such aggregate networks. We study the scalability of embedded optical passive stars by considering the most commonly employed virtual topologies—complete graph, mesh and hypercube.

WDM multiple access protocol using node grouping scheme for passive double star networks

A WDM multiple access protocol for optical passive double star networks is proposed. It is presumed in the proposed protocol that all the nodes in the network are clustered to form multiple groups using passive star sub-hubs, and that the groups are connected together via a central passive star hub. A WDM channel is particularly allocated to each group as its home channel for data and control packet reception. Packets are transmitted over the pre-assigned TDM slots. Each node is equipped with a wavelength-tunable transmitter and a wavelength-fixed receiver tuned at the home channel of the group to which it belongs. An arbitration algorithm is also included to resolve data channel collision. It is shown in the performance evaluations that the proposed protocol has the advantages of the higher wavelength channel utilisation and less sensitivity to propagation delay time compared with the other protocols previously reported.

Last advances in optical fiber communications Passive optical star couplers

Uno de los principales componentes de las nuevas redes de fibra optica que soportan multiples servicios, son los acopladores opticos. Se presenta un estudio detallado de la estructura de reflexion dentro de un acoplador optico en estrella, teniendo en cuenta los patrones de radiacion de ondas electromagneticas y las condiciones de difraccion de Bragg. Se analizan los campos electromagneticos producidos de acuerdo a la geometria del acoplador y se presenta un ejemplo sencillo de un acoplador transmisivo.

A performance comparison between graph and hypergraph topologies for passive star WDM lightwave networks

Wavelength division multiplexing (WDM) allows the huge bandwidth of optical fiber to be divided into several high-speed channels in optical passive star based networks. For such processor networks, most of the proposed architectures for interconnecting nodes are based on graph topologies. Recently, topologies based on the hypergraph theory have emerged, motivated by the observation that each multiplexed channel can actually be seen as a logical resource shared among many processors, and not only between two of them. In this paper, we show that these hypergraph passive star WDM lightwave networks present many advantages with respect to graph-based ones, in terms of simulated packet delivery time, average number of hops, link utilization, and throughput. Furthermore, they use only a constant number of transceivers per node, and a sub-linear number of multiplexed channels.

TWDM multichannel lightwave hypercube networks

The hypercube is a widely used interconnection topology as it presents a lot of attractive properties. Recently, the hypercube has been proposed as a virtual topology for TWDM multihop lightwave networks based on optical passive star couplers. However, in most of previous works, each station in the network has only one fixed or tunable transmitter and one fixed or tunable receiver. The tunable transmitters and receivers suffer from high cost, long tuning delay and small tunable range. While the fixed transceiver configuration has low cost, its performance such as transmission concurrence is greatly limited. In this paper, we propose the transceiver configuration that each station uses multiple fixed transmitters and multiple fixed receivers. This configuration can greatly improve the performance while being able to emulate the tunability of the tunable transceivers without suffering tuning delay. We will present a wavelength assignment scheme for the transceivers. The maximal concurrence that can be achieved by the network is also given in terms of the number of transmitters and receivers at each station.

Topological embedding into WDM optical passive star networks with tunable transmitters of limited tuning range

Wavelength Division Multiplexing (WDM) has been widely used for studying the performance of optical networks, especially those employing optical passive star couplers. Many models have been proposed for WDM on an optical passive star coupler, such as each station equipped with a single tunable transmitter and a single fixed wavelength receiver, and each station with multiple tunable transmitters and multiple tunable receivers. The current technology only allows the transceivers to be tunable in a small range, a fact ignored in previous studies. In this paper, we focus on the design of WDM optical passive star networks with tunable transmitters of limited tuning range and fixed wavelength receivers. The limited tuning range has effects on the maximum delay, the total number of wavelengths which can be used, and the topological embedding. Complete graphs, meshes, and hypercubes are the three topologies studied in this paper. The relationship between the total number of wavelengths which can be utilized and the embedded topology is established. The bound for the maximum delay is analyzed. The optimal embedding algorithms are given for the systems embedded with one of the three topologies.

Realizing common communication patterns in partitioned optical passive stars (POPS) networks

We consider the problem of realizing several common communication structures in the all-optical Partitioned Optical Passive Stars (POPS) topology. We show that, often, the obvious or "natural" method of implementing a communication pattern in the POPS does not efficiently utilize its communication capabilities. We present techniques which distribute the communication load uniformly in the POPS for four of the most common communication patterns (all-to-all personalized, global reduction operations, ring, and torus). We prove that these techniques provide optimal performance in the sense that they minimize the time required to deliver the messages from each node to its neighbors.

A Collision-Free Reservation Protocol for WDM Optical Star Networks

WDM single-hop networks allow a pair of nodes to exchange data packets directly and require an efficient protocol that coordinates the process of data transmission. However, the network performance with such protocols can be deteriorated by collisions that occur on control channel, data channel, destination node and source node. We present a Collision-Free Reservation Protocol (CFRP) for WDM single-hop networks with a passive optical star coupler. To eliminate all causes of collision, the CFRP properly distributes the transmission schedule both in time (position of data channel on the time axis) and space (wavelength of data channel to be used). Compared with the previous reservation-based protocols, the proposed CFRP enhances the overall network performance. This improvement in terms of network throughput and delay is verified by simulation.

Optimal transmission schedules in TWDM optical passive star networks

This paper is concerned with optimal transmission schedules in the TWDM (time and wavelength division multiplexed) optical passive star network. Our model of the network consists of a set V of N nodes with N tunable transmitters and N fixed-tuned receivers (where each node is assigned a transmitter-receiver pair), k wavelengths (each wavelength is shared by N k receivers where N k is an integer), and tuning time δ > 0 (in units of time slot, for transmitters to tune from one wavelength to another). We assume that at any given time slot, at most one transmission can be done per wavelength. An optimal transmission schedule is defined to be the one that schedules transmissions such that for each node v in V, the transmitter in v transmits once to every receiver in V — { v} within a repeating cycle of minimum length. We present an optimal transmission schedule for each tuning time, and show that the cycle length of any optimal transmission schedule is max { N( N — 1)/ k, kδ + N — 1}.

Scheduling nonuniform traffic in a packet-switching system with small propagation delay

A new model of nonuniform traffic is introduced for a single-hop packet-switching system. This traffic model allows arbitrary traffic streams subject only to a constraint on the number of data packets which can arrive at any, individual source in the system or for any individual destination in the system over time periods of specified length. The nonuniform traffic model is flexible enough to cover integrated data networks carrying diverse classes of data. The system model is rather general, and includes passive optical star wavelength-division networks. Transmission algorithms are introduced for a single-hop packet-switching system with such nonuniform traffic and with propagation delay that is negligible relative to the packet length. The algorithms are based on collision-free scheduling of packets using graph-matching algorithms since the global state of the system is known to all stations at any time.

Multiaccess processor interconnection using subcarrier and wavelength division multiplexing

The optical technology contributes significantly to high speed long distance communications and local area networks (LANs). The wavelength division multiplexing (WDM) and the subcarrier multiplexing (SCM) are two technologies widely employed to fully utilize the huge bandwidth available on optical fibers and alleviate the speed mismatch between the components in the electronic domain and those in the optical domain. In this paper, we extend these technologies to parallel processing multicomputers. The design philosophy is to incorporate advantages of both the WDM and the SCM into the multiaccess processor interconnection for multicomputers. The objective is to provide high bandwidth and high data rate under the physical limits and the performance requirements. A novel interprocessor architecture, the receiver oriented architecture (ROA), is proposed. Based on the passive optical star coupler, the ROA has been implemented and referred as ROA-SC which is single-hop accessible and optically self-routing. The implementation also speeds up the processing in the electronic domain. Besides, the presentation includes three media access protocols for both the reservation and the preallocation approaches. Extensive analysis has been performed and the proposed ROA-SC is found to have very good modularity and scalability so that it is very suitable for practical applications.

Partitioned optical passive star (POPS) multiprocessor interconnection networks with distributed control

This paper presents a partitioned optical passive star (POPS) interconnection topology and a control methodology that, together, provide the high throughput and low latency required for tightly coupled multiprocessor interconnection applications. The POPS topology has constant and symmetric optical coupler fanout and only one coupler between any two nodes of the network. Distributed control is based on the state sequence routing paradigm which multiplexes the network between a small set of control states and defines control operations to be transformations of those states. These networks have highly scalable characteristics for optical power budget, resource count, and message latency. Optical power is uniformly distributed and the size of the system is not directly limited by the power budget. Resource complexity grows as O(n) for the couplers, O(n/spl radic/n) for transceivers, and O[/spl radic/nlog(n)] for control. We present analysis and simulation studies which demonstrate the ability of a POPS network to support large scale parallel processing (1024 nodes) using current device and coupler technology.

Design Principles for Multi-Hop Wavelength and Time Division Multiplexed Optical Passive Star Networks

Wavelength Division Multiplexing (WDM) has been shown to be one of the most promising ways to exploit the enormous bandwidth of a single mode optical fiber. Networks employing WDM are commonly based on optical passive star couplers. The major cost and limitations of such networks lie in the interface (both transmitters and receivers) providing optical-electronic conversion between stations and communication media. Based on current technology, interfaces based on fast tunable devices are still in the infant stage of development at this time. Commercially available fixed wavelength devices are much cheaper and reliable. With fixed wavelength device in each station, several stations may transmit and receive on the same wavelength. Time-Division Multiplexing (TDM) is often employed for those stations accessing the same wavelength. The resulting networks, called multi-hop Wavelength-and Time-Division Multiplexed (WTDM) Networks, may require a multi-hop path to deliver packets between two stations. In this paper we study multi-hop WTDM networks where each station has only one fixed wavelength transmitter and one fixed wavelength receiver. We propose a graph model, called a Receiving Graph Model, to represent these networks such that their inherent properties can be easily understood and alternative designs can be compared. Furthermore, we discuss several design principles and theoretical performance limitations of such networks.

Scalable High-Speed Protocols for WDM Optical Star Networks

This paper proposes scalable conflict-free media-access protocols for WDM optical passive star networks using shared parallel queueing and wormhole scheduling. Shared parallel queueing is to associate several parallel queues with a data channel, rather than one deep queue (as in DT-WDMA) or N static queues (as in [5] and [6], N is the number of stations). This significantly reduces both the hardware resource requirement and the control signalling demand. Wormhole scheduling is to schedule multiple successive packets which are destined to the same receiver at one time, decreasing the overhead of tuning caused by relatively slow filter and relieving the electronic processing bottleneck. An analytical model is presented and verified through simulation. Numerical results from analysis and simulation indicate that with only 5-6 parallel queues, the protocols are capable of achieving high throughput. Thus the protocols can be scaled up for networks with a large number of stations and could lead to a potential implementation.

Access protocols for passive optical star networks

Abstract Through Wavelength Division Multiplexing (WDM), the huge bandwidth of optical fiber can be divided into a set of high-speed logical channels. A passive star coupler can be used to configure a multichannel network with these WDM channels. The users in these networks have access to one or more channels. Hence, one of the major issues in these networks is the channel access protocols users have to follow in order to transmit their packets to other users. This paper reviews many of the proposed protocols that appeared in the literature. These protocol are divided into three different categories: fixed assignment (or pre-allocation) protocols, random access protocols and hybrid protocols. The random access protocols are further divided into reservation, switching and collision avoidance protocols.

A simplified optical star network using distributed channel controllers

Future photonic networks may be based on emerging wavelength-division-multiplexing (WDM) technology. In single-hop LAN's using a passive optical star coupler, stations normally access the network using some combination of wavelength-agile transmission and reception. Unfortunately, this parallel channel architecture tends to increase and complicate the user station hardware and protocols. In this paper, a new network architecture is presented. The objective of the design is to simplify the user stations as much as possible. This is accomplished through the use of a set of distributed channel controllers-one for each WDM channel. The network is thus referred to as the distributed channel controller network (DCCN). The channel controllers assist in the operation of the network in a number of ways. To further simplify the design, bandwidth is allocated hierarchically on each channel. This decouples system operation into two levels. At the higher level, band width partitioning may be done in a static or dynamic fashion. The lower level determines the dynamic use of slots. Two options for media access are considered. The first is a hybrid approach based upon custom hardware-based request scheduling. Allocations are generated by the channel controllers electronically and data transmission occurs using station wavelength agility. The second is much more distributed. Each set of competing stations builds a distributed queue based upon observed requests. It is found that the proposed architecture supports higher throughput than in other similar networks with the same hardware requirements. An analytic model is introduced for calculating mean station delay. Simulations show that it accurately predicts network performance. >

An efficient communication protocol for high-speed packet-switched multichannel networks

A media-access protocol for high-speed packet-switched multichannel networks that are based on a broadcast topology, such as optical passive star networks using wavelength-division multiple access, is described. The protocol supports connection-oriented traffic with or without bandwidth reservation, as well as datagram traffic to integrate transport-layer functions with the media-access layer. It uses the bandwidth efficiently while keeping the processing requirements low by requiring stations to compute their transmission and reception schedules only at the start and end of each connection. Analysis results show that low blocking probabilities for connections and high network throughput can be achieved. >

A media-access protocol for time- and wavelength-division multiplexed passive star networks

A media access protocol is presented for time- and wavelength-division multiplexed optical passive star networks. The protocol is based on a bus-mesh virtual topology. The network provides minimum latency and high throughput while requiring only a single fixed wavelength transmitter and receiver at each station. The use of nonagile, fixed wavelength devices, readily available with current technology, reduces costs, improves reliability and avoids tuning delays and limitations. The multihop access protocol operates effectively in an environment with lengthy propagation delays. The wavelength-division multiplexing system is required to support only a small, easily achievable number of wavelength channels. >

Wavelength division multiplexed CATV distribution service overlay on two-fibre passive optical dialogue star networks

The 1.3 μm/1.55 μm wavelength division integration of 5.18Mbit/s dialogue services and analogue BK450MHz CATV distribution service in fibre optic subscriber access systems (fibre-in-the-loop) is considered. The mutual interference of the services is investigated. Based on a two-fibre passive optical star network the optimum concept is derived from theoretical and experimental data.

Design and Analysis of a Hybrid Access Control to an Optical Star Using WDM

A passive optical star is an ideal shared medium, from both fault tolerant and access synchronization points of view. The communication over an optical star merges to a single point in space and then broadcasts back to all the nodes. This circular symmetry facilitates the solution for two basic distributed synchronization problems, which are presented in this work: (i) the generation of a global event clock for synchronizing the nodes′operation, and (ii) distributed scheduling for accessing the shared passive medium, which is a hybrid (deterministic and random) technique. We present, prove, and analyze this hybrid scheduling algorithm, which is equivalent to a distributed queue, and, therefore, is also algorithmically fair. Furthermore, our solution has two additional properties: destination overflow prevention and destination fairness. The effective solution of these problems can be used for efficiently implementing a local area network based on a passive optical star.