Given the ever increasing demand for network bandwidth, and the phenomenal advances in optical wavelength division multiplexing (WDM) networking technologies, a major component of the next generation Internet will be an Internet protocol (IP)-based optical WDM network. As IP over WDM networking technologies mature, a number of important architectural, management and control issues have surfaced. These issues need to be addressed before a true next generation optical Internet can emerge. We enumerate some of the key architectural, management and control issues and discuss corresponding approaches and advances made toward addressing these issues. We first review the different IP/WDM networking architectural models and their tradeoffs. We outline and discuss several management and control issues and corresponding approaches related to the configuration, fault, and performance management of IP over dynamic WDM networks. We present an analysis and supporting simulation results demonstrating the potential benefits of dynamic IP over WDM networks. We then discuss the issues related to IP/WDM traffic engineering in more detail, and present the approach taken in the NGI SuperNet Network Control and Management Project funded by DARPA. In particular, we motivate and present an innovative integrated traffic-engineering framework for reconfigurable IP/WDM networks. It builds on the strength of multiprotocol label switching for fine-grain IP load balancing, and on the strength of reconfigurable WDM networking for reducing the IP network's weighted-hop-distance, and for expanding the bottleneck bandwidth.

With the widespread deployment of Internet protocol/wavelength division multiplexing (IP/WDM) networks, it becomes necessary to develop traffic engineering (TE) solutions that can effectively exploit WDM reconfigurability. More importantly, experimental work on reconfiguring lightpath topology over testbed IP/WDM networks is needed urgently to push the technology forward to operational networks. This paper presents a performance and testbed study of topology reconfiguration for IP/WDM networks. IP/WDM TE can be fulfilled in two fashions, overlay vs. integrated, which drives the network control software, e.g., routing and signaling protocols, and selects the corresponding network architecture model, e.g., overlay or peer-to-peer. We present a traffic management framework for IP over reconfigurable WDM networks. Three "one-hop traffic maximization"-oriented heuristic algorithms for lightpath topology design are introduced. A reconfiguration migration algorithm to minimize network impact is presented. To verify the performance of the topology design algorithms, we have conducted extensive simulation study. The simulation results show that the topologies designed by the reconfiguration algorithms outperform the fixed topology with throughput gain as well as average hop-distance reduction. We describe the testbed network and software architecture developed in the Defense Advanced Research Projects Agency (DARPA) Next Generation Internet (NGI) SuperNet Network Control and Management project and report the TE experiments conducted over the testbed.

With the widespread deployment of IP over WDM networks, it becomes necessary to develop dynamic lightpath and topology reconfiguration mechanisms and reconfiguration triggers that can effectively exploit WDM reconfigurability. A reconfiguration model for overlay IP/WDM networks is introduced. An IP over WDM network testbed has been set up using Telcordia MONET WADM and IP routers. The testbed network and software architecture is presented and the traffic-engineering experiments and convergence measurements conducted over the testbed are reported.

In this paper we present two traffic-engineering approaches, overlay and integrated, for IP over reconfigurable WDM networks. The overlay approach presents a layered model between IP and WDM, in which the IP layer requests transport services from the WDM layer. Traffic engineering is performed in each layer, where the two layers communicate through defined interfaces. The integrated approach emulates a peer-to-peer model between the IP/WDM nodes, each of which is capable of IP traffic engineering control, and makes physical resource allocation decisions based on the locally maintained IP/WDM network state information. We outline a functional framework for traffic engineering applicable to either approach, and describe the corresponding software implementation architecture for these approaches.

Optical networking using WDM technology has matured considerably, and commercial WDM network equipment and WDM network control and management prototypes have appeared. To use such a network efficiently, a scheduling facility and its enabling mechanisms have to be provided. This scheduling facility should be integrated to interoperate with the rest of the network control and management software such as connection manager or signaling daemon. We present a scheduling application to address this need. The architecture for the application and its key components are presented. Agent-related enabling mechanisms are introduced to monitor the optical signal quality and collect performance measurements. A resource broker is used to manage the communication and interoperability between agents and the application. An event service is developed to decouple the communication between the agents and the scheduling application, and to enable the communication among the agents themselves. The scheduling application consists of the quality of signal information and threshold objects, current network usage, history data module, scheduling module, and access to a performance database. To provide traffic control and high network resource utilization, the application is equipped with wavelength scheduling algorithms. An experimental study for the basic scheduling algorithms has been conducted over the MONET DC network.

To sustain the ever growing demand for bandwidth in cost-effective, efficient and robust ways, it is anticipated that the next-generation transport network architecture will consist of several different technology layers. However, managing such multi-layered transport networks will be complicated and difficult, due to the scale of the networks and the correlation between different technology layers. Unfortunately, existing network management systems mainly manage a single technology, and management systems for different technologies may not interoperate. Therefore, to effectively manage the emerging multi-layered transport networks, an integrated network management system is urgently needed. In this paper, we describe work on integrated management of ATM/SONET/WDM networks from both information modeling's and software architecture's perspectives. We describe how the standard work on network-level information models may be used to model different transport technology layers and their inter-relationships. We will also describe how the CORBA technology may be used to realize the integrated information model so that the resulting integrated network management system is distributed and complies with TMN Logical Layered Architecture.

In this paper, we describes a CORBA-based framework that helps to realize the notion of the network as database. This framework shall build abstraction layers that present a distributed object database abstraction for the networks to their managers. At the bottom layer, work of the X/Open and NMF Joint Inter-Domain Management is utilized and extended to encapsulate heterogeneous network resources with CORBA objects. On top of that, standardized network-level information models define entity-relationship data models which represent logical structures of the databases containing network resources. These distributed network resources, as represented by CORBA objects, collectively constitute the distributed object database which is organized according to the data model. Facilities, such as query, trigger, and view, are then provided to facilitate network management operations. We will illustrate how the framework may be realized via CORBA Object Services, and describe its application for modeling a WDM network. With the distributed CORBA object database representation of network resources, network management activities may be carried out as conveniently as database operations, The results not only facilitate effective and consistent network management operations, but also ease the integration with Service and Business Management Layers of the TMN architecture.

To meet the demand for huge bandwidth created by the multimedia communications revolution, there is an urgent need to dramatically upgrade the existing telecommunications infrastructure. In today's infrastructure, fiber-optics is used in point-to-point transmission links, with all networking and services functions done electronically. To upgrade such an infrastructure in a cost-effective way, Wavelength Division Multiplexing (WDM) technology may be used to transmit multiple optical channels per fiber. This way, network capacity may grow in response to increased demand. In addition, with the reconfigurability of WDM networks, network configuration may adapt in response to changing traffic patterns. To ensure successful deployment and operations of WDM networks, it becomes essential to have a comprehensive network control and management system which is versatile, robust, and scaleable. In this paper, we describe a network control and management system prototype developed under the Multiwavelength Optical Networking (MONET) project funded by the US government's Defense Advanced Research Project Agency. The prototype system provides configuration, connection, fault, and performance management functionalities for reconfigurable WDM all-optical networks. The design of the prototype system follows the TMN logical layered architecture, and it is implemented on a fault-tolerant, CORBA-compliant distributed object computing platform which facilitates robust and scaleable operations.

This paper describes the connection management research done by the Network Control and Management (NC&M) task force under the multiwavelength optical networking (MONET) program. MONET is sponsored by the Defense Advanced Research Project Agency (DARPA) the US Government Department of Defense, with participation from Bellcore, AT&T, Lucent Technologies, several government agencies, and regional Bell operating companies. MONET's vision is to develop a flexible reliable high-capacity high-performance cost-effective national optical network based on multiwavelength fiber optic technology. As an important component in realizing this vision, the MONET program includes the architecture and design of a prototype network control and management system for MONET's reconfigurable wavelength-division multiplexing (WDM) all-optical network. The primary objectives of the prototype research work are to develop the architecture and framework for managing national-scale transparent reconfigurable WDM optical networks and to demonstrate the feasibility of the NC&M prototype system in a field experiment network in Washington, DC. This prototype system allows the program participants to conduct experiments and gain experience in the management and operations of reconfigurable optical networks. This paper describes the connection management aspects of the prototype system, addressing issues such as the management architecture, information model, and provisioning algorithms of the prototype management system.

The manager/agent model has been the de facto paradigm used for designing network management systems. However, as the network size grows and new network and computing technology emerges, consistency, flexibility, reliability, and scalability issues of distributed network management systems might not be fully addressed within the model. This paper proposes an extension to the manager/agent model, called the manager/agency paradigm, to address these issues. In the manager/agency paradigm, a manager performs management functions through an agency of cooperating management entities, (lower-level) managers and/of agents, which are collaboratively working together to achieve consistent management goals. Agencies may recursively constitute other agencies, based on the layering and partitioning principles, to scale with ever growing network size. They may be organized flexibly according to different management functionalities, goals and policies, and may present a single management view to their (upper-level) managers by hiding management complexity. Inside an agency, various fault tolerant schemes, such as active replication or primary-backup approach, may be used to implement reliable management functionality transparently to its manager. The paper begins by describing the anatomy and semantics of an agency and comparing the manager/agency model against the manager/agent model. It then demonstrates its applications to address the consistency and reliability issues of network management problems. Finally, applications of the manager/agency model to the broader, distributed enterprise management is discussed.