Quadro-Star: a high performance optical WDM star network
TL;DR: The proposed solution does not suffer performance degradation under heterogeneous traffic conditions and increasing number of nodes, and is unique in offering the potential of an all-optical solution providing at the same time high throughput, low delay, small buffer requirements, and robustness under all traffic conditions.
Abstract: This paper proposes an original approach to controlling WDM Passive optical stars, termed queuing arrivals for delayed reception operation (Quadro). In WDM stars the fundamental problem of receiver conflicts leads to severe performance degradation. In current solutions conflicts are prevented by scheduling transmissions or resolved by retransmissions. Both approaches waste bandwidth and involve electronic processing and buffering. The proposed approach is conceptually different in introducing a local conflict resolution mechanism at each receiver incorporating delay lines. This solution brings optical star networks a step closer to an all-optical realization. In addition, it allows an almost total utilization of the channels, as obtainable until now only by TDM control. Contrary to TDM, however, the proposed solution does not suffer performance degradation under heterogeneous traffic conditions and increasing number of nodes. It is thus unique in offering the potential of an all-optical solution providing at the same time high throughput, low delay, small buffer requirements, and robustness under all traffic conditions. >
Citations
More filters
TL;DR: The authors present a "baseline" architecture for a 2/spl times/2 buffered packet switch that is work conserving and has the first-in, first-out (FIFO) property and introduces cascaded optical delay line (COD) architectures.
Abstract: Architectures for packet switches are approaching the limit of electronic switching speed. This raises the question of how best to utilize advances in photonic technology to enable higher speeds. The authors introduce cascaded optical delay line (COD) architectures. The COD architectures utilize an extremely simple distributed electronic control algorithm to configure the states of 2/spl times/2 photonic switches and use optical fiber delay lines to temporarily buffer packets if necessary. The simplicity of the architectures may also make them suitable for "lightweight" all-electronic implementations. For optical implementations, the number of 2/spl times/2 photonic switches used is a significant factor determining cost. The authors present a "baseline" architecture for a 2/spl times/2 buffered packet switch that is work conserving and has the first-in, first-out (FIFO) property. If the arrival processes are independent and without memory, the maximum utilization factor is /spl rho/, and the maximum acceptable packet loss probability is /spl epsiv/, then the required number of 2/spl times/2 photonic switches is O(log(/spl epsiv/)/log(/spl gamma/)), where /spl gamma/=/spl rho//sup 2//(/spl rho//sup 2/+4-4/spl rho/). If one modifies the baseline architecture by changing the delay line lengths then the system is no longer work conserving and loses the FIFO property, but the required number of 2/spl times/2 photonic switches is reduced to O(log[log(/spl epsiv/)/log(/spl gamma/)]). The required number of 2/spl times/2 photonic switches is essentially insensitive to the distribution of packet arrivals, but long delay lines are required for bursty traffic.
101 citations
TL;DR: The efficiency of protocols coordinating the data transmission between the transmitter and receivers in a network of stations connected using a passive star coupler, equipped with fixed transmitters and tunable receivers, and using wavelength-division multiplexing is discussed.
Abstract: The efficiency of protocols coordinating the data transmission between the transmitter and receivers in a network of stations connected using a passive star coupler, equipped with fixed transmitters and tunable receivers, and using wavelength-division multiplexing is discussed. Two reservation-based protocols with varying degrees of signaling complexity are proposed: the dynamic allocation scheme (DAS), which dynamically assigns slots on a packet-by-packet basis, and the hybrid time-division-multiplexing (TDM) scheme (HTDM), which combines the TDM and the DAS scheme and allows both preassigned and dynamic slot assignment. Analytical results are derived for the delay performance of the two schemes and compared with that of TDM. It is shown that the performance of DAS under ideal conditions is close to optimal, but its signaling costs are exorbitantly high. On the other hand, HTDM has lower signaling needs, but has higher delays when compared to DAS. >
98 citations
TL;DR: This work presents a solution that makes use of multibuffer fiber delay lines which allow multiple packets to be concurrently stored (propagated) on each line, and it is shown that this solution increases the total storage capacity and significantly improves switch and network performance.
Abstract: This paper proposes an efficient contention resolution switching architecture which can serve as the basis for all-optical switching nodes. The presented solution builds on fiber delay lines used as temporary optical storage and 2/spl times/2 space photonic switches, a solution principle also known as Quadro or switched delay lines (SDLs). The efficiency of SDLs is fundamentally linked to its storage capacity, i.e., the length of the fiber delay lines, while its cost depends on the number of 2/spl times/2 photonic switches, i.e., the number of stages in the switch. This work presents a solution that makes use of multibuffer fiber delay lines which allow multiple packets to be concurrently stored (propagated) on each line. With a novel switch control, it is shown that this solution increases the total storage capacity and significantly improves switch and network performance, without increasing the number of the 2/spl times/2 switches in the system, i.e., its cost.
94 citations
Patent•
03 Oct 1995TL;DR: In this article, the authors propose a communication platform which employs a TDM bus, a controller, a passive Ethernet bus, and a centralized Ethernet hub to provide for the communication of data, voice, and/or video signals among a plurality of endpoint devices.
Abstract: Communications systems and methods are directed to a novel communications platform which employs a TDM bus, a TDM bus controller, a passive Ethernet bus, and a centralized Ethernet hub to provide for the communication of data, voice, and/or video signals among a plurality of endpoint devices. The TDM bus controller provides a plurality of B-Channels on the TDM bus. The centralized Ethernet hub is coupled to the TDM bus controller via a control link. Each endpoint device is connected to at least one of the passive Ethemet bus and the TDM bus. The centralized Ethernet hub operates over the passive Ethernet bus to dynamically allocate one or more individual B-Channels of a single B-Channel set amongst a group of endpoint devices, such as telephone equipment, video communications equipment, processors, and/or computing devices. The centralized Ethernet hub provides a logical control channel to each endpoint device for call establishment. Each endpoint device is coupled to the logical control channel over at least one of a first path comprising the passive Ethernet bus and a second path comprising the TDM bus, the TDM bus controller, and the control link. The logical control channel executes B-channel seizure algorithms for establishment of communications to and from selected endpoint devices.
45 citations
09 Apr 1997
TL;DR: This paper shows how slot contention penalties can be reduced through the use of switched delay lines (SDL) at the bridges through the combination of the photonic slot routing and the switcheddelay lines.
Abstract: Photonic slot routing (PSR) is a promising approach to solving the fundamental scalability problem of all-optical packet switched WDM networks. In this approach adjacent subnetworks can exchange wavelength sensitive traffic through bridges using wavelength non-selective devices which can be constructed using proven technologies. With photonic slot routing, packets sharing a common subnetwork destination are aggregated to form a photonic slot which is individually routed in order to reach the destination subnetwork. Photonic slots from different subnetworks can originate contentions at the bridge, leading to potential penalties of slot loss and retransmission. This paper shows how slot contention penalties can be reduced through the use of switched delay lines (SDL) at the bridges. The combination of these two innovative techniques, the photonic slot routing and the switched delay lines, leads to a unique solution that is shown to nearly achieve throughput and delay performance obtainable in absence of slot contentions.
25 citations
References
More filters
IBM1
TL;DR: A dynamic time-wavelength division multiaccess protocol (DT-WDMA) is proposed for metropolitan-sized multichannel optical networks employing fixed wavelength transmitters and tunable optical receivers.
Abstract: A dynamic time-wavelength division multiaccess protocol (DT-WDMA) is proposed for metropolitan-sized multichannel optical networks employing fixed wavelength transmitters and tunable optical receivers. Control information is sent over a dedicated signaling channel and data are sent over channels owned by the transmitters. Time is divided into slots on each channel and slots on the control channel are further split into mini-slots. Fixed time-division multiaccess (TDM) is used within each slot on the control channel. Transmitters indicate their intention to transmit a packet by transmitting the destination address during their appropriate mini-slot in the control channel and then transmit their packet in the next slot on their data channel. Receivers listen to the control channel and tune to the appropriate channel to receive packets addressed to them. A common but distributed arbitration algorithm is used to resolve conflicts when packets from many transmitters contend for the same receiver. Each receiver executes the same deterministic algorithm to choose one of the contending packets. Each transmitter uses the same algorithm to determine the success or failure of its packet. >
280 citations
TL;DR: This paper proposes several protocols that require each user to have a tunable receiver and shows that in typical applications an average throughput of up to 0.95 can be achieved at a reasonable average delay using one of these protocols.
Abstract: This paper deals with the problem of interconnection of many high-speed bursty traffic users via an optical passive star coupler. Each user can tune its laser over a range of wavelengths, thus resulting in a wavelength division multiplexed communication. The total number of wavelengths over which user tunability exists could be much smaller than the number of users. Therefore, some form of random access sharing and packet switching may be necessary. We propose several protocols that require each user to have a tunable receiver. The information on "where" and "when" to tune the laser is confined to a control (setup) channel that users tune to when in idle mode. An interconnection between two users lasting for the length of a data packet is set up on the control channel by the transmitting user who informs the receiving user where to tune in order to receive the data packet. No centralized control or coordination is required among the users. After analyzing each protocol, we present the throughput/ delay versus the offered traffic and the delay versus throughput in a sequence of plots. We show that in typical applications an average throughput of up to 0.95 can be achieved at a reasonable average delay using one of these protocols. In our benchmark examples we present an optical local area network (LAN) with a total throughput of 100- Gbit/s in which every user has access to a 1-Gbit/s data rate and the network can support over 1000 users. The protocols can be used in a) large LAN's that do not require a large capacity, b) small LAN's (1 kin) that require a large capacity and c) large LAN's (tens of kilometers) that require a rather large capacity.
255 citations
TL;DR: Two synchronous multiple access schemes, TDMA and CDMA, are proposed for fiber optic networks using optical signal processing, using a central modelocked laser which also serves as the source for each station.
Abstract: Two synchronous multiple access schemes, TDMA and CDMA, are proposed for fiber optic networks using optical signal processing. Network synchronization is achieved by using a central modelocked laser which also serves as the source for each station. The data are converted into a high-bandwidth optical signal using electrooptic modulators. The accessing schemes use optical fiber delay lines. The feasibility of these schemes is discussed.
220 citations
IBM1
TL;DR: A first-generation design, called Rainbow, for optical wavelength division multiaccess (WDMA) computer networks is described, which takes the form of a direct detection, circuit-switched metropolitan-area-network (MAN) backbone consisting of 32 IBM PD/2's as gateway stations.
Abstract: A first-generation design, called Rainbow, for optical wavelength division multiaccess (WDMA) computer networks is described. The Rainbow research prototype takes the form of a direct detection, circuit-switched metropolitan-area-network (MAN) backbone consisting of 32 IBM PD/2's as gateway stations, communicating with each other at 200-Mb/s data rates and submillisecond switching times. The prototype architectural options for realizing WDMA networks are discussed, along with reasons for choosing this design point. Experimental measurements on the prototype are presented. Ways of extending this prototype to more stations, higher bit rates, and faster setup times are given. >
199 citations
TL;DR: In this article, the feasibility of a polarization-insensitive waveguide frequency selection switch for 10-GHz intervals and a frequency-shift-keying (FSK) direct-detection scheme employing a Mach-Zehnder filter is verified.
Abstract: A 100-channel optical frequency-division multiplexing (FDM) transmission/distribution experiment at 622 Mb/s is demonstrated for a fiber length of 50 km. The feasibility of a polarization-insensitive waveguide frequency selection switch for 10-GHz intervals and a frequency-shift-keying (FSK) direct-detection scheme employing a Mach-Zehnder filter is verified. The demodulation circuit employs a Mach-Zehnder filter and a balanced receiver, which utilizes optical power more efficiently than the Fabry-Perot filter. No receiver sensitivity degradation is observed due to interchannel crosstalk of the 128-channel tunable waveguide frequency selection switch (FS-SW) or fiber four-wave mixing for transmissions over a 50-km-long nondispersion-shifted (NDS) fiber and a 26-km-long dispersion-shifted (DS) fiber. >
132 citations