Traffic Aggregation Research Articles

Monitoring Edge-to-Edge Traffic Aggregates in Differentiated Services Networks

Differentiated Services (DiffServ), which are currently being standardized in the IETF DiffServ working group, is a solution that can provide different qualities of service to different network users. DiffServ aggregates network packets at edge routers and forwards the aggregated packets to core routers with different priorities. In this paper, we propose methods using the SNMP framework for monitoring edge-to-edge traffic aggregates in a DiffServ domain, which consists of a set of DiffServ-enabled routers. In order to manage each DiffServ router, we have analyzed the DiffServ MIB and instrumented it in the router. Further, we propose monitoring behaviors of edge-to-edge traffic aggregates by combining topology and performance information from MIB II and DiffServ MIB. Construction procedures and graphical representation of the edge-to-edge traffic aggregates are explained in detail. We also extend our efforts to implement a DiffServ domain monitoring system that monitors a set of DiffServ-enabled routers and traffic aggregates between every edge router pair. We believe that the proposed monitoring methods can serve as useful building blocks for managing DiffServ networks.

Photonic slot routing: a cost effective approach to designing all-optical access and metro networks

In the backbone network, the high level of traffic aggregation achieved by numerous users is efficiently served by means of optical circuit switched solutions-the so-called wavelength routing approach. In the access and metro networks, on the contrary, the reduced level of traffic aggregation makes wavelength routing solutions inadequate. The finer and more dynamic bandwidth allocation provided by packet-interleaved optical time-division multiplexing is thus advocated in these network areas. This article presents a survey of an OTDM approach, known as photonic slot routing, or PSR. It is illustrated how this approach may provide a cost-effective solution to deploying all-optical access and metro networks with today's technology.

End-to-end performance analysis with traffic aggregation

The provisioning of end-to-end services in the presence of traffic aggregation is evaluated in the framework of the Differentiated Services (diffserv) QoS architecture. The effect of stream multiplexing on delay and jitter-sensitive traffic is analyzed through an experimental approach. Aggregation is evaluated in three different scenarios: with different aggregate traffic loads, with a variable number of flows multiplexed in the same class, and with different packet sizes. Two different scheduling algorithms are considered: Priority Queuing (PQ) and Weighted Fair Queuing (WFQ).

A low cost approximation for a controlled load service in a bridged/switched LAN environment

This paper reports the design and the implementation results of a Controlled Load service in a bridged/switched Local Area Network (LAN). In contrast to other approaches, the service was built based on traffic aggregation and simple two level Static Priority scheduling within LAN switches. All complex control functions such as the per-flow packet classification, policing and traffic reshaping are only performed within end-nodes (hosts or routers) of the LAN. Admission Control is used to restrict the access to the new service. Measurement results received in a bridged test network exhibit low average end-to-end delay characteristics and no packet loss despite: 1) the simplicity of the traffic control implemented in our LAN switches, 2) a worst-case network load, and 3) the use of long range dependent data sources within the experiments.

Modeling and simulation of broadband satellite networks. II. Traffic modeling

For p.I see ibid., vol.37, no.3, p.72-9 (1999). Traffic models for satellite network simulation must cover a broad range of traffic types and characteristics because the type of users/terminals that will access a satellite channel will range from a single home user (low traffic aggregation) to Internet backbone nodes (very high traffic aggregation). In addition, since satellite resources are generally considered more scarce than their fiber counterparts, the accuracy and practicality of traffic models play a crucial role. We address these challenges by identifying three traffic modeling areas for satellite network simulation, and propose an effective and flexible traffic model for each area: a discrete autoregressive process for MBone video source modeling; the superposition of fractal renewal processes (Sup-FRP) model for Web request arrivals; and a generalized shot-noise-driven Poisson point process (GSNDP) for aggregate traffic flows modeling. The efficacy of the first two models is demonstrated based on statistical analysis of various video and Web traces. These simulation-oriented models provide accurate descriptions of source traffic at various levels of traffic aggregation, and thus enable satellite network researchers and practitioners to understand key network design and engineering issues such as QoS provisioning based on simulation.

Slot Routing as a Solution for Optically Transparent Scalable WDM Wide Area Networks

All-optical Wavelength Division Multiplexing (WDM) backbones are believed to be a fundamental component in future high speed networks. Currently, the most pursued approach for Wide Area Networks (WANs) is wavelength routing, in which communication circuits are established between node pairs by means of lightpaths (paths of light) spanning one or more fiber-optic links. This approach has, however, two drawbacks. Since the number of wavelengths and links in a network is finite, not all node pairs can be connected via a dedicated lightpath directly. Consequently, some node pairs will communicate using a concatenation of lightpaths, which requires electronic switching of in transit information, loosing the advantages of optical transparency. Secondly, typically some form of (electronic) traffic grooming will be necessary to make efficient use of the fixed lightpath capacity. This paper proposes to design all-optical WANs using a novel approach, called photonic slot routing. With photonic slot routing, entire slots, each carrying multiple packets on distinct wavelengths, are switched transparently and individually, using available fast and wavelength non-sensitive devices. The advantage of using photonic slot routing is threefold. All node pairs in the network communicate all-optically. Traffic aggregation necessary to efficiently use the capacity of the wavelength channels is optically achieved. The solution is practical as it is based on proven optical technologies. In addition, through the use of wavelength non-sensitive devices the proposed WAN design yields intrinsic scalability in the number of wavelengths.

Architectural principles of optical regional and metropolitan access networks

High-end access networks that serve large businesses and campuses will greatly benefit from the introduction of WDM technology, in terms of greater bandwidth, increased flexibility, and enhanced services. We refer to such networks as optical regional and metropolitan access networks (ORMA-Nets). Here, we qualitatively and quantitatively investigate many important principles, as well as challenges, in deploying ORMA-Nets. Access networks in general are functionally comprised of a feeder network, which is responsible for traffic aggregation, and a distribution network, which directly interfaces with the customer premises. We present several configurable, scalable designs for the feeder network that are capable of aggregating a range of traffic types and rates. We also present architectures for achieving a high degree of functionality using relatively low-cost, passive optical components in the distribution network. We explore topics such as optimal switch placement and wavelength banding, and emphasize the technologies that are needed to deliver advanced capabilities. Various underlying themes run throughout the paper, such as optionally not always using bandwidth as efficiently as possible in order to simplify the architecture, and the importance of transparency in providing enhanced services and architectural flexibility.

An ATM-friendly MAC for traffic concentration in HFC systems

Proliferating deployment of amphidromic broadband services over commercial cable TV networks is bringing a taste of IBCN capabilities to vast numbers of domestic customers. The fluctuating and unpredictable traffic of the new services favours TDMA multiplexing of traffic from many customers inside each channel for flexible and dynamic bandwidth sharing on the basis of a medium access protocol. As penetration grows, traffic aggregations will exceed the capabilities of store-and-forward switching bringing more and more into prominence fast switching techniques and ATM networking. The first HFC systems designed primarily for LAN interconnection and Internet traffic are not optimised for ATM sources even when they employ ATM cells as a unit of transport. A novel contention approach designed to greatly reduce the distortions to traffic profiles characterising first generation HFC medium access protocols is the theme of this paper. The proposed method provides a high number of simultaneous orthogonal contention opportunities which allow quick identification of cell arrivals which is a key to preserving temporal relationships of contending traffic, vastly reducing cell delay variations in line with the traffic control philosophy of ATM.

Optical versus electronic switching for broadband networks

The authors compare the use of electronic and optical switching for broadband networks. Their technological merits and their ability to meet traffic demand when multimedia communications become ubiquitous are considered. The authors conclude that electronic ATM switches are adequate and commercially mature for local access. An ATM-mesh switch with multihop routing can be used to achieve capacity of several hundreds of gigabits per second. Beyond access, the authors argue that traffic aggregation may allow switching to be performed on much longer time scales than that of ATM cells. Wavelength and mechanical fiber switching may be used economically for trunk switching, avoiding the expensive processes of optoelectronic conversions and demultiplexing.

A parameterizable methodology for Internet traffic flow profiling

We present a parameterizable methodology for profiling Internet traffic flows at a variety of granularities. Our methodology differs from many previous studies that have concentrated on end-point definitions of flows in terms of state derived from observing the explicit opening and closing of TCP connections. Instead, our model defines flows based on traffic satisfying various temporal and spatial locality conditions, as observed at internal points of the network. This approach to flow characterization helps address some central problems in networking based on the Internet model. Among them are route caching, resource reservation at multiple service levels, usage based accounting, and the integration of IP traffic over an ATM fabric. We first define the parameter space and then concentrate on metrics characterizing both individual flows as well as the aggregate flow profile. We consider various granularities of the definition of a flow, such as by destination network, host-pair, or host and port quadruple. We include some measurements based on case studies we undertook, which yield significant insights into some aspects of Internet traffic, including demonstrating (i) the brevity of a significant fraction of IP flows at a variety of traffic aggregation granularities, (ii) that the number of host-pair IP flows is not significantly larger than the number of destination network flows, and (iii) that schemes for caching traffic information could significantly benefit from using application information. >