Soichiro Araki

Hybrid hierarchical optical networks

Hybrid hierarchical optical cross-connects enhance the performance/cost ratio of optical networks by providing transparent (optical) switching of sets of wavelengths (wavebands) in addition to opaque (electrical) switching of individual wavelengths. As network bandwidth gets cheaper, and the performance bottleneck moves to switching nodes, these systems provide an attractive scalable solution for next-generation optical networks. We describe key technological components (including flexible nonuniform wavebands) of hybrid hierarchical optical cross-connects and discuss their performance/cost implications.

User-Space Communication: A Quantitative Study

Powerful commodity systems and networks offer a promising direction for high performance computing because they are inexpensive and they closely track technology progress. However, high, raw-hardware performance is rarely delivered to the end user. Previous work has shown that the bottleneck in these architectures is the overheads imposed by the software communication layer. To reduce these overheads, researchers have proposed a number of user-space communication models. The common feature of these models is that applications have direct access to the network, bypassing the operating system in the common case and thus avoiding the cost of send/receive system calls. In this paper we examine five user-space communication layers, that represent different points in the configuration space: Generic AM, BIP-0.92, FM-2.02, PM-1.2, and VMMC-2. Although these systems support different communication paradigms and employ a variety of different implementation tradeoffs, we are able to quantitatively compare them on a single testbed consisting of a cluster of high-end PCs connected by a Myrinet network. We find that all five communication systems have very low latency for small messages, in the range of 5 to 17 s. Not surprisingly, this range is strongly influenced by the functionality offered by each system. We are encouraged, however, to find that features such as protected and reliable communication at user level and multiprogramming can be provided at very low cost. Bandwidth, however, depends primarily on how data is transferred between host memory and the network. Most of the investigated libraries support zero-copy protocols for certain types of data transfers, but differ significantly in the bandwidth delivered to end users. The highest bandwidth, between 95 and 125 MBytes/s for long message transfers, is delivered by libraries that use DMA on both send and receive sides and avoid all data copies. Libraries that perform additional data copies or use programmed I/O to send data to the network achieve lower maximum bandwidth, in the range of 60-70 MBytes/s.

Hierarchical routing in layered ring and mesh optical networks

We consider hierarchical optical networks with different granularities of paths (wavelengths and wavebands). We introduce classification layers for routing models in these networks (separated and integrated routing, homogeneous and heterogeneous networks, online and offline routing). We also propose and analyze two heuristic routing and aggregation algorithms (online and offline) to be used for homogeneous networks in the separate routing framework. The analysis is based on ring topology; its results are supported by simulations of large scale networks (Europe and USA). These simulations demonstrate a significant cost reduction achieved by employing hierarchical routing (from 33% in the online algorithm to almost 60% in the offline one).

Security in Photonic Networks: Threats and Security Enhancement

We address emerging threats to the security of photonic networks as these networks become heterogeneous being opened to the upper layers, other operators, and end users. We review the potential threats, mainly loss of the confidentiality of user data transmitted through optical fibers and disturbances of network control, both of which could seriously damage the entire network. We then propose a novel conceptual model of a secure photonic network by introducing a quantum key distribution (QKD) network to its legacy structure. Secure keys generated by the QKD network are managed by key management agents (KMAs) and used to encrypt not only user data but also control signals. The KMAs cooperate with the generalized multiprotocol label-switching controller for secure path provisioning and drive photonic and modern crypto engines in appropriate combinations. Finally, we present a roadmap of a deployment scenario, starting from niche applications such as mission critical and business applications and the next. Digital cinema distribution through a photonic network is presented as an example of a niche application.

A 2.56 Tb/s throughput packet/cell-based optical switch-fabric demonstrator

A packet/cell-based optical switch-fabric demonstrator has been successfully developed that is upgradable to 2.56 Tb/s throughput. The number of optical components in a 256/spl times/256 switch-fabric is dramatically reduced to one-eighth that of a conventional switch-fabric.

Photonic network R&D activities in Japan-current activities and future perspectives

R&D activities on photonic networks in Japan are presented. First, milestones in current ongoing R&D programs supported by Japanese government agencies are introduced, including long-distance and wavelength division multiplexing (WDM) fiber transmission, wavelength routing, optical burst switching (OBS), and control-plane technology for IP backbone networks. Their goal was set to evolve a legacy telecommunications network to IP-over-WDM networks by introducing technologies for WDM and wavelength routing. We then discuss the perspectives of so-called PHASE II R&D programs for photonic networks over the next 5 years until 2010, by focusing on the report that has been recently issued by the Photonic Internet Forum (PIF), a consortium that has major carriers, telecom vendors, and Japanese academics as members. The PHASE II R&D programs should serve to establish a photonic platform to provide abundant bandwidth on demand, at any time on a real-time basis, through the customers initiative to promote bandwidth-rich applications, such as grid computing, real-time digital-cinema streaming, medical and educational applications, and network storage in e-commerce.

Multi-domain ASON/GMPLS network operation: current status and future evolution

This paper describes clarifications and comparisons of routing models for multi-domain optical networks as well as the current status and future perspective for ASON/GMPLS technologies. The three routing models, the per-domain routing, the ASON hierarchical routing, and the PCE-based routing, have been being standardized for the ASON/GMPLS multi-domain networks. In this paper, we compare these three routing models in terms of path computation capabilities, on-line multiple path planning capability and inter-domain confidentiality. According to our analyses, the PCE-based routing and the ASON hierarchical routing models have rich path computation capabilities enough for multi-domain ASON/GMPLS network operation, while the per-domain routing does not provide much capabilities. One of the significant issues left for the ASON hierarchical routing model is an appropriate abstraction mechanism which strongly affects the path computation capabilities and inter-domain confidentiality. In addition to the sufficient path computation capabilities, the PCE-based routing model offers the on-line bulk optimization for multiple requests. Therefore, we concluded that the PCE-based routing is the most suitable for multi-domain ASON/GMPLS networks.

Challenging Terabit-Class LAN Over Wide Area Networks

The lambda access (2006-2010) and the lambda utility (2006-2010) projects are two of the major photonic network R&D Projects supported by the Ministry of Internal Affairs and Communications (MIC) and National Institute of Information and Communications Technology (NICT) Japan. The two projects aim at actualizing terabit-class LANs over wide area networks, which enable users to enjoy stress-free access to high bit-rate services such as super high definition video, high performance computing, and GRID computing. The Lambda Access Project develops network access technologies with single- or multi-lambda interfaces at 100 Gbps, meanwhile the Lambda Utility Project develops wide area network control technologies and high capacity link technologies. This paper describes the targets and recent achievements of these projects.

GByte-class skewless parallel-optical-data-link subsystem

This paper describes 48 x 100 Mbit/s data link subsystem using a 6 x 1.1 Gbit/s arrayed optical transceiver module and 15-ns deskew function ICs. This link will be applied to the real world computing (RWC)-1, which is one of the massively parallel computer with 1,000-class processor elements.

A time-shift scheduling-enabled optical flow switched network architecture and its performance.

Optical flow switching (OFS) has been proposed as a simple and cost-effective transport technology for users with large transactions (>1 second). In previous studies, a fast wavelength reservation method was deployed for flow transmission in OFS-based networks. However, reserving a single wavelength for users with small transactions encounters a very common problem: inefficient wavelength utilization. In this paper, a flow transmission cycle is introduced to each wavelength, and each cycle consists of multiple slots, so that flows of different transactions can be multiplexed onto a single wavelength. It is assumed that inter-metropolitan area network (MAN) traffic is transported over wide area network (WAN). A global time-shift scheduling methodology taking into account propagation delays in MAN is designed to avoid potential contentions occurring among different flows which are carried by the same wavelength in WAN. The contributions of this paper are, first it provides a new OFS network architecture which can achieve better throughput and average wavelength utilization performance without losing the feature of simple transport structure provided by OFS; second, it is the first time that issues of how OFS networks are managed and controlled are addressed from a system point of view.