160 Gbit/s/port optical packet switch prototype with variable-length packet BER and loss real-time measurement

We propose and experimentally demonstrate a prototype 160-Gbit/s/port optical packet switch with narrow-band alloptical code-label processing, optical switching, high-extinction-ratio optical buffering, electrical scheduling, and optical MUX/DEMUX. As related technologies, we also propose and demonstrate a novel system for measuring variable-length packet BER and loss and a burst-mode optical packet 3R receiver.

An optical packet switch design using optical switching and shared electronic buffering is described and analyzed. The electronic buffering and add/drop unit allows random memory access, variable packet length, and aggregation/segregation of low bit rate streams. The design is scalable to a large number of wavelengths, and employs contention resolution by using the wavelength dimension combined with electronic buffering. The number of buffer inputs, i.e. the number of optoelectronic conversions, is minimized. The packet loss and delay performance when using fixed packet length and electronic buffering are investigated by simulation. If the link utilization is moderate, the buffering requirements becomes minimal. If number of wavelengths in the link is increased, the number of buffer inputs can be reduced. With a sufficiently high number of wavelengths, the buffer requirements is minimal, even when the link utilization is high.

We present a 1 × 2 all-optical packet switch. All the processing of the header information is carried out in the optical domain. The optical headers are recognized by employing the two-pulse correlation principle in a semiconductor laser amplifier in loop optical mirror (SLALOM) configuration. The processed header information is stored in an optical flip-flop memory that is based on a symmetric configuration of two coupled lasers. The optical flip-flop memory drives a wavelength routing switch that is based on cross-gain modulation in a semiconductor optical amplifier. We also present an alternative optical packet routing concept that can be used for all-optical buffering of data packets. In this case, an optical threshold function that is based on a asymmetric configuration of two coupled lasers is used to drive a wavelength routing switch. Experimental results are presented for both the 1 × 2 optical packet switch and the optical buffer switch.

Packet contention is a major issue in asynchronous optical packet switching networks. Optical buffering, which is implemented by fiber delay lines (FDLs), is fundamental to many optical switch implementations for resolving contention. Most existing optical buffering implementations are output-based and require a huge amount of FDLs as well as larger switch sizes, which impose extra cost on the overall system. In this paper, we consider a shared optical buffering architecture which can reduce the buffer size at a switch. We propose an analytical model to evaluate the packet loss probability and the average delay For shared buffers at a single switch. We then compare the performance of output buffers to shared buffers under different granularities of FDLs. We observe that, by choosing an appropriate granularity, the shared buffering scheme can significantly reduce packet loss with much smaller switch sizes and fewer FDLs than the output buffering architecture. The accuracy of the analytical model is also confirmed by extensive simulation

This paper deals with massive number of optical code (OC) label generation and recognition for scalable optical packet switching (OPS) networks. In order to expand the system scalability of code label processing, we develop a record port count 128 x 128 optical encoder/decoder (E/D) and propose a novel three-dimensional (3-D) optical label combining code label with wavelength and polarization. In the experiment, we conduct a proof-of-concept demonstration of 4-code x 2-wavelength x 2-polarization and validate that the 3-D labeling scheme can consequently increase the available number of code label up to more than 1,000 labels. Real-time labeling performance using a field programmable gate array (FPGA)-based processor and crosstalk influence at an optical switch are also experimentally evaluated.

As data centers enter the exascale computing era, the traffic exchanged between internal network nodes, increases exponentially. Optical networking is an attractive solution to deliver the high capacity, low latency, and scalable interconnection needed. Among other switching methods, packet switching is particularly interesting as it can be widely deployed in the network to handle rapidly-changing traffic of arbitrary size. Nanosecond-reconfigurable photonic integrated switch fabrics, built as multi-stage architectures such as the Clos network, are key enablers to scalable packet switching. However, the accompanying control plane needs to also operate on packet timescales. Designing a central scheduler, to control an optical packet switch in nanoseconds, presents a challenge especially as the switch size increases. To this end, we present a highly-parallel, modular scheduler design for Clos switches along with a proposed routing scheme to enable nanosecond scalable scheduling. We synthesize our scheduler as an application-specific integrated circuit (ASIC) and demonstrate scaling to a 256 × 256 size with an ultra-low scheduling delay of only 6.0 ns. In a cycle-accurate rack-scale network emulation, for this switch size, we show a minimum end-to-end latency of 30.8 ns and maintain nanosecond average latency up to 80% of input traffic load. We achieve zero packet loss and short-tailed packet latency distributions for all traffic loads and switch sizes. Our work is compared to state-of-the-art optical switches, in terms of scheduling delay, packet latency, and switch throughput.

The wide deployment of wavelength-division multiplexing technology and new transmission techniques have resulted in significant increases in the transmission capacity in optical fibers, both in the number of wavelengths and the bandwidth of each wavelength channel. Meanwhile, the fast growth of the Internet demands more data switching capacity in the network in order to deliver high bandwidth to end users. Although the capacity of electronic routers has been increasing consistently in the past, optical switching appears to be a more cost-effective way to switch individual wavelengths. As the bit rate per wavelength channel continues to grow, optical subwavelength switching emerges as a new paradigm capable of dynamically delivering the vast bandwidth WDM offers. This article discusses one of such techniques, namely optical packet switching, and its performance perceived by end users in optical mesh networks. Specifically, our investigation reveals the benefit of using electrical ingress buffering and traffic aggregation to reduce packet-loss rate of optical packet-switched networks. Through simulation experiments, we present an evaluation of the network's TCP-level performance based on the proposed architecture.

The photonic crystal optical switch is one of the most important applications of photonic crystals in telecommunication networks. Switching is a main process in digital computers and signal processing systems. The growth of optical signal processing systems draws particular attention to the design of ultra-fast optical switches. In this reported work, first a directional coupler switch based on photonic crystals is designed and the linear state has been analysed and simulated. Then, the principles of nonlinear optics are used to perform optical switching at a wavelength of 1550 nm by COMSOL Multiphysics in micron dimension. The dielectric rods of this photonic crystal lattice are made of AlGaAs. The central row is an important factor for attaining the required power in nonlinear switching performance. Finally, the radius of rods in the central nonlinear row is changed several times and the results are compared with each other. In this switch, the output power ratio, called the extinction ratio, and the required refractive index change for the nonlinear status are taken into account. The former is for the evaluation of directional coupler efficiency and the latter is generally an important factor in optical nonlinear switches.

Optical packet switch with multicast capability enables a broad range of applications in next generation optical networks. In this paper, we propose a cost-effective scheme to enhance the traffic performance of our earlier reported optical wavelength-routed multicast packet switch by modifying rather than adding multicast modules in the switch. A packet scheduling technique is introduced to substantially reduce the output contention for the switch. The effectiveness of our proposed scheme in conjunction with the scheduling technique is analyzed and validated by evaluation of packet loss performance of the modified multicast packet switch through simulations. The simulation results show that the multicast packet loss probability of the modified multicast switch can be significantly reduced without increasing the number of multicast modules by our proposed scheme. This means that to achieve an acceptable level of the multicast packet loss probability, the modified multicast switch requires fewer multicast modules in comparison with our earlier reported switch.

Scheduling traffic for maximum switch lifetime in optical data center fabrics

We have already proposed a Gigabit Ethernet-Optical Switched Access Network (GE-OSAN) architecture that realizes longer transmission distances and achieves higher security than the conventional Passive Optical Network (PON). To confirm the technical feasibility of the architecture, we introduce here a GE-OSAN prototype system for down-stream transmission. We present the Optical Switching Module (OSM), which uses (Pb,La)(Zr,Ti)O3 (PLZT) optical packet switches, and show that it realizes switching within 10ns of the designed position in the Inter-Frame Gap (IFG). We also introduce an Optical Network Unit (ONU) with optical burst receiver that uses off-the-shelf commercial devices to reduce its cost; two types of an optical to electrical signal (O/E) converter are implemented for performance comparison. After testing both of them, we select the one that satisfies our acquisition time requirement of 64ns.

Among all proposed structures for optical networks, the optical packet switching (OPS) scheme, due to its practical implementation of IPs in an optical configuration and the consequent advantages, is a prizeworthy candidate for being employed in metropolitan area network and local area network communication levels. One of the few problems frequently met using the OPS structure in the fiber-optics realm is the lack of optical buffers, thus deteriorating the system's flexibility and quality of service. For example, optical label switching networks that have been developed recently based on the generalized multiprotocol label switching protocol, profoundly suffer from this setback which is considered as a great hurdle in their evolution. In this paper, we first introduce the input and output buffer switching models while deducing their blocking probability formulations. Then, by utilizing codes in the OPS structure, we closely examine the potential of code and/or wavelength switching in packet switching networks and also determine their blocking probability. Due to close similarities between different scenarios, we present the prospect of virtual optical buffers using codes, which have close performance to input and output buffers in sight of block probability. The most significant distinction in using virtual buffers is the fact that due to their substantial nature, they happen to exhibit some error probability. However, on account of the advantageous features of codes, the simulated and formulated error probability for both coherent and noncoherent optical code division multiple access (OCDMA), such as Spectrally phase encoded OCDMA and optical orthogonal codes, using virtual buffers, tends to be negligible. Two main code and wavelength switching schemes are also brought to attention in this work, the intelligent and random methods. These scenarios demonstrate an even greater behavioral performance to that of the mere code switching scenario, leading into a more reliable adaptation of virtual buffers. In addition, simulations results happen to provide clear verifications to our analytical approach.

In optical burst switching and optical packet switching, contention of bursts (or packets) can be dealt with most effectively through a combination of wavelength conversion and optical buffering. While this is generally accepted in the optical networking community, and validated through simulation, analytic performance results for optical buffers were limited to the single-wavelength case, and the performance gain from wavelength conversion was never traced analytically for general assumptions. Quantifying this gain analytically is the scope of the current contribution. Relying on generating functions, we developed a fiber delay line (FDL) buffer model with wavelength conversion, which assumes the buffer located at the output of an optical switch, having access to multiple wavelengths. This document presents our model, validates its accuracy, and compares its output for different burst sizes (fixed or varying), scheduling policies and buffer sizes. Several numerical examples assess the applicability of our approximation, and show that our approach yields accurate results.

Due to lack of optical RAM buffers in fast optical switches (FOS), statistical multiplexing technologies using FOS like Optical Burst Switching (OBS) or Optical Packet Switching (OPS) are expected to have higher data losses than conventional electronic networks. Consequently, applications transferring data by means of TCP can suffer from a lower throughput. In this paper, we show that this low-throughput problem is mainly an artifact caused by the conventional TCP congestion control algorithms, and can be remedied by using a simple yet effective stop-and-wait congestion control algorithm instead, as long as the propagation delay between TCP source and TCP destination is small compared to the transmission time of an optical packet. We show that such a condition holds for a wide range of scenarios, including fat-tree-based data center networks. We also show that the throughput achieved in a FOS network using stop-and- wait can be the same as, or higher than that in an equivalent, conventional electronic network. I. INTRODUCTION

Wavelength conversion and optical buffer are the two most commonly used and most useful contention resolution schemes. This paper presents a comprehensive study of them in a multiwavelength optical burst switching network. Specially, we focus on 1) how does the wavelength conversion degree affect the burst blocking performance? 2) how does the optical buffer affect the burst blocking performance? Different from the studies in literature, we will not only investigate the effect of optical buffer length on the blocking performance, but also we investigate the effect of the granularity, which is defined the length of an FDLs and measured in terms of a delay unit, of optical buffers on the burst blocking performance. 3) how does various combinational schemes can be architected and how they perform.