George N. Rouskas

Traffic grooming in WDM networks: past and future

Traffic grooming refers to techniques used to combine low-speed traffic streams onto high-speed wavelengths in order to minimize the networkwide cost in terms of line terminating equipment and/or electronic switching. Such techniques become increasingly important for emerging network technologies, including SONET/WDM rings and MPLS/MP/spl lambda/S backbones, for which traffic grooming is essential. In this article we formally define the traffic grooming problem, and we provide a general formulation that captures the features of a wide range of problem variants. We then present a comprehensive comparative survey of the literature that unveils the significant amount of research on this subject (the traffic grooming past). We also offer a broad set of ambitious research directions (the traffic grooming future) that are motivated by the exciting new challenges arising with the advent of MP/spl lambda/S technology.

JumpStart: a just-in-time signaling architecture for WDM burst-switched networks

We present an architecture for a core dWDM network which utilizes the concept of optical burst switching coupled with a just-in-time signaling scheme. It is a reservation-based architecture whose distinguishing characteristics are its relative simplicity, its amenability to hardware implementation, and the ability to support multicast natively. Another important feature is data transparency-the network infrastructure is independent of the format of the data being transmitted on individual wavelengths. We present the signaling protocol designed for this architecture, as well as an unified signaling message structure to be used in conjunction with the protocol. We also present the future directions of this research.

Optical layer multicast: rationale, building blocks, and challenges

Optical layer multicast refers to the support of point-to-multipoint connections directly at the physical layer by employing passive devices capable of splitting the power of an input signal among several outputs. Optical multicast technology enables a broad set of applications and opens new directions to network design. We examine the underlying principles and essential components for a practical optical multicast service. We also present a set of key research challenges along with a survey of the literature.

Power Efficient Traffic Grooming in Optical WDM Networks

Power-awareness in networking attracts more attention as the trends in the energy consumption of the Internet raise growing concerns about the environmental impacts and sustainability of the network expansion. Building energy efficient equipment is definitely an integral part of the solution. However, such a strategy should be complemented with appropriate network protocols and routing methods to achieve maximum performance. In this paper, total power consumption of an optical WDM network is modeled in terms of the power consumed by individual lightpaths. The proposed model is then used to develop an ILP (Integer Linear Programming) formulation of the grooming problem. The exact solution of the formulation on a small network indicates that significant energy savings can be achieved with power efficient grooming.

The SILO Architecture for Services Integration, controL, and Optimization for the Future Internet

We propose a new internetworking architecture that represents a departure from current philosophy and practice, as a contribution to the ongoing debate regarding the future Internet. Building upon our experience with the design and prototyping of the just-in-time protocol suite, we outline a framework consisting of (1) building blocks of fine-grain functionality, (2) explicit support for combining elemental blocks to accomplish highly configurable complex communication tasks, and (3) control elements to facilitate (what is currently referred to as) cross-layer interactions. In this position paper, we take a holistic view of network design, allowing applications to work synergistically with the network architecture and physical layers to select the most appropriate functional blocks and tune their behavior so as to meet the applications needs within resource availability constraints. The proposed architecture is flexible and extensible so as to foster innovation and accommodate change, it supports a unified Internet, it allows for the integration of security and management features at any point in (what is now referred to as) the networking stack, and it is positioned to take advantage of hardware-based performance-enhancing techniques.

MTCP: scalable TCP-like congestion control for reliable multicast

We present MTCT, a congestion control scheme for large-scale reliable multicast. Congestion control for reliable multicast is important because of its wide applications in multimedia and collaborative computing, yet nontrivial, because of the potentially large number of receivers involved. Many schemes have been proposed to handle the recovery of lost packets in a scalable manner; but there is little work on the design and implementation of congestion control schemes for reliable multicast. We propose new techniques that can effectively handle instances of congestion occurring simultaneously at various parts of a multicast tree. Our protocol incorporates several novel features: (1) hierarchical congestion status reports that distribute the load of processing feedback from all receivers across the multicast group, (2) the relative time delay (RTD) concept which overcomes the difficulty of estimating round-trip times in tree-based multicast environments, (3) window-based control that prevents the sender from transmitting faster than packets leave the bottleneck link an the multicast path through which the senders traffic flows, (4) a retransmission window that regulates the flow of repair packets to prevent local recovery from causing congestion, and (5) a selective acknowledgment scheme that prevents independent (i.e., non-congestion-related) packet loss from reducing the senders transmission rate. We have implemented MTCP both on UDP in SunOS 5.6 and on the simulator ns, and we have conducted extensive Internet experiments and simulation to test the scalability and inter-fairness properties of the protocol. The encouraging results we have obtained support our confidence that TCP-like congestion control for large-scale reliable multicast is within our grasp.

A path decomposition approach for computing blocking probabilities in wavelength-routing networks

We study a class of circuit-switched wavelength-routing networks with fixed or alternate routing and with random wavelength allocation. We present an iterative path decomposition algorithm to evaluate accurately and efficiently the blocking performance of such networks with and without wavelength converters. Our iterative algorithm analyzes the original network by decomposing it into single-path subsystems. These subsystems are analyzed in isolation, and the individual results are appropriately combined to obtain a solution for the overall network. To analyze individual subsystems, we first construct an exact Markov process that captures the behavior of a path in terms of wavelength use. We also obtain an approximate Markov process which has a closed-form solution that can be computed efficiently for short paths. We then develop an iterative algorithm to analyze approximately arbitrarily long paths. The path decomposition approach naturally captures the correlation of both link loads and link blocking events. Our algorithm represents a simple and computationally efficient solution to the difficult problem of computing call-blocking probabilities in wavelength-routing networks. We also demonstrate how our analytical techniques can be applied to gain insight into the problem of converter placement in wavelength-routing networks.

Network Virtualization: Technologies, Perspectives, and Frontiers

Network virtualization refers to a broad set of technologies. Commercial solutions have been offered by the industry for years, while more recently the academic community has emphasized virtualization as an enabler for network architecture research, deployment, and experimentation. We review the entire spectrum of relevant approaches with the goal of identifying the underlying commonalities. We offer a unifying definition of the term “network virtualization” and examine existing approaches to bring out this unifying perspective. We also discuss a set of challenges and research directions that we expect to come to the forefront as network virtualization technologies proliferate.

Multicast routing with end-to-end delay and delay variation constraints

We study the problem of constructing multicast trees to meet the quality of service requirements of real-time, interactive applications operating in high-speed packet-switched environments. In particular, we assume that multicast communication depends on (a) bounded delay along the paths from the source do each destination, and (b) bounded variation among the delays along these paths. We first establish that the problem of determining such a constrained tree is NP-complete. We then derive heuristics that demonstrate good average case behavior in terms of the maximum inter-destination delay variation of the final tree. We also show how to dynamically reorganize the initial tree in response to changes in the destination set, in a way that is minimally disruptive to the multicast session.

Wavelength selection in OBS networks using traffic engineering and priority-based concepts

A fundamental assumption underlying most studies of optical burst switched (OBS) networks is that full wavelength conversion is available throughout the network. In practice, however, economic and technical considerations are likely to dictate a more limited and sparse deployment of wavelength converters in the optical network. Therefore, we expect wavelength assignment policies to be an important component of OBS networks. In this paper, we explain why wavelength selection schemes developed for wavelength routed (circuit-switched) networks are not appropriate for OBS. We then develop a suite of adaptive and nonadaptive policies for OBS switches. We also apply traffic engineering techniques to reduce wavelength contention through traffic isolation. Our performance study indicates that, in the absence of full conversion capabilities, intelligent choices in assigning wavelengths to bursts at the source can have a profound effect on the burst drop probability in an OBS network.