Next Generation Wide Area Optical Networks

9508239慕克吉这个项目将(I)探索采用光技术的下一代网络的新架构，特别是波分复用(WDM)，以实现广域(全国)覆盖，以及(Ii)通过使用实际的工作负载(流量)模型来评估和压力测试这些网络的性能。这种几乎全光的广域WDM网络将在路由节点中使用波长复用器和光开关，从而可以在给定的物理光纤网络上嵌入任意的虚拟拓扑。虚拟拓扑是分组交换的，并且由一组“全光光路”组成，它被设置为利用光学和电子学的相对优势--信息分组在光域中“尽可能地”由虚拟拓扑承载，但无论何时需要，从光路到光路的分组转发都是通过电子交换执行的。由于波长的空间重用，这种基于WDM的网络体系结构提供了高的聚合系统容量，在给定有限数量的波长的情况下支持大量且可扩展的用户，并且对单个用户的波长可调光学设备的要求非常宽松。在微观层面上，本研究将对WDM路由节点的成本、效率和吞吐量进行优化。在宏观层面上，我们将(A)调查与设备能力一致的全国性WDM网络的总体设计、分析、可升级性和优化(包括成本和性能之间的权衡)；(B)检查相关设备问题，如光放大、光纤非线性等；(C)研究与网络的交换、路由和性能管理相关的流量控制问题，以开发“自适应重新配置算法”，以便在所提供的流量模式发生变化时重新配置虚拟拓扑；以及(D)为新兴的网络服务(如组播)开发光硬件支持和算法。*达琳·费舍尔项目经理网络和通信研究项目4201威尔逊大道。弗吉尼亚州阿灵顿22230(703)306-306-06211175室(传真)

9508239 Mukherjee This project will (i) explore new architectures for the next generation of networks employing optical technology, in particular wavelength-division multiplexing (WDM), for wide-area (nationwide) coverage, and (ii) evaluate and stress-test the performance of these networks by employing realistic workload (traffic) models. This ``almost-all-optical'' wide-area WDM network will utilize wavelength multiplexers and optical switches in a routing node, so that an arbitrary virtual topology can be imbedded on a given physical fiber network. The virtual topology, which is packet switched and which consists of a set of ``all-optical lightpaths'', is set up to exploit the relative strengths of both optics and electronics -- packets of information are carried by the virtual topology ``as far as possible'' in the optical domain, but packet forwarding from lightpath to lightpath is performed via electronic switching, whenever required. This WDM-based network architecture provides high aggregate system capacity due to spatial reuse of wavelengths, support for a large and scalable number of users given a limited number of wavelengths, and very lenient requirements on the wavelength-tunable optical devices of the individual users. On a microscopic level, this research will optimize the cost, efficiency and throughput of the WDM routing node. On a macroscopic level, we will (a) investigate the overall design, analysis, upgradability, and optimization (including cost vs. performance tradeoffs) of a nationwide WDM network consistent with device capabilities; (b) examine related device issues such as optical amplification, fiber nonlinearities, etc.; (c) study traffic control issues related to switching, routing, and performance management of the network to develop ``adaptive reconfiguration algorithms'' in order to reconfigure the virtual topology when the pattern of offered traffic changes; and (d) develop optical hardware support and algorithms for emerging networking services such as multicasting. *** ******* Darleen Fisher Program Manager Networking and Communications Research Program 4201 Wilson Blvd. Room 1175 Arlington Va 22230 (703) 306-1949 (703) 306-0621 (FAX)