Statistical analysis of network traffic for class of service inpacket-switched networks

The goals of the class-of-service (COS) routing concept in packet-switched networks are to meet user requirements and to maximize network resource utilization. A statistical analysis model is proposed to analyze network traffic using all recorded data to determine what COSs are present and their associated bandwidth and delay requirements. The UNINET call-record database is used to demonstrate the COS concept. The experimental results show that the traffic patterns defined by COS exist. The bandwidth distribution for 300-b/s call is approximately normal. However, bandwidth distributions for calls equal to or greater than 1200 b/s are exponential, indicating that bandwidth is not a very predictable parameter for these speeds. Lower speeds tend to have a low input bandwidth and slightly higher output bandwidth     

Minimum cost dimensioning of ring optical networks

We consider the problem of traffic grooming of low-rate traffic circuits in WDM rings where circuits are associated with a set of heterogeneous granularities. While networks are no longer limited by transmission bandwidth, the key issue in WDM network design has evolved towards the processing capabilities of electronic switches, routers and multiplexers. Therefore, we focus here on traffic grooming with minimum interconnecting equipment cost. We first formulate the problem as an integer linear programming (ILP) or a mixed integer linear programming (MILP) problem depending on the design specifications: UPSR vs BLSR, fixed vs variable wavelength capacities, non-bifurcated vs bifurcated flows, wavelength continuity vs possible signal regeneration on a different wavelength. Considering the case study of the second SONET ring generation with MSPP like interconnection equipment, we define the cost by a function of the number of transport blades, taking into account that the number of MSPP transport blades makes up a significant portion of the overall network design cost. Using the CPLEX linear programming package, we next compare the optimal solutions of the ILP or MILP programs for different design assumptions, including the classical ring network design scheme with a single hub where the lightpaths directly connect the hub to all other nodes.     

Node dimensioning in optical burst switching networks

Network dimensioning should be progressed for pursuing the ultimate efficiency of network system resources in order to satisfy target performance. This article studies node dimensioning as a method of resource optimization in optical burst switching (OBS) networks. OBS is a new switching technology for pursuing bufferless transparent optical networks by sending control packets prior to data burst in order to provision resources for the burst. However, the basic assumption of a bufferless node implies burst contention at a core node when more than two bursts attempt to move forward the same output simultaneously. Thus, burst contention is a critical performance metric and this article takes it into account as a constraint on node dimensioning and target performance. In this article, we first present node dimensioning issues for OBS networks. Two constraints from the transport plane and the control plane which affect burst contention are then introduced. The effect of the burst assembly process on node dimensioning is also presented. From numerical analysis, the optimal number of wavelengths in a link, which provides the lowest blocking probability, is obtained to suggest a guideline for node dimensioning.     

A new approach to dimensioning optical networks

A network dimensioning method allocates appropriate capacities to the links based on the network topology and traffic requirements. We introduce the concept of absorption probability instead of blocking probability which is a more appropriate measure to express the grade of service of an optical network, in many cases. Absorption probability can be obtained from transient analysis of a Markov chain. Computation of exact absorption probabilities requires large computing resources and is thus feasible only for small networks. We present a method to approximate the absorption probability of a wavelength-routed network with arbitrary topology and traffic patterns assuming the nodes have full wavelength conversion capability. We show that the approximation method performs well especially in the desired range of absorption probabilities and it is computationally efficient     

Resource management and dimensioning in ATM networks

A general overview of resource management aspects of ATM networks is presented, and mechanisms of load control have been considered. A general framework of resource management is first addressed. Two main aspects of traffic characterization are then examined from the traffic engineering point of view: teleservice characterization and user characterization. These form the basis of the analysis that follows. In particular, a bandwidth assignment proposal is presented and evaluated by simulation. Policing issues are discussed. The advantages of the proposed assigned method over the peak bit rate allocation method is proved for two typical dimensioning cases     

Performance analysis and dimensioning of multi-granular optical networks

Recent years have demonstrated the limited scalability of electronic switching to realize transport networks. In response, all-optical switching has been identified as a candidate solution to enable high-capacity networking in the future. One of the fundamental challenges is to efficiently support a wide range of traffic patterns, and thus emerges the need for equipment that is both practical and economical to construct and deploy. We have previously proposed the use of multi-granular optical cross-connects (MG-OXC), which support switching on both the wavelength and sub-wavelength level. To this end, the MG-OXCs are equipped with cheap, highly scalable slow switching fabrics, as well as a small number of expensive fast switching ports. The goal of this work is two-fold: first to demonstrate that a small number of fast switching ports suffices to support a wide range of traffic requirements, and second that multi-granular optical switching can offer cost-benefits on a network-wide scale. The first objective is studied through simulation analysis of a single switching node, and results indicate that a limited number of fast switching ports can significantly improve burst blocking performance over slow only switches. Furthermore, under certain circumstances, the MG-OXC can even approach the performance of a fast only switch design. Secondly, we introduce an Integer Linear Programming model for the total network installation cost, and our evaluation indicates that multi-granular optical switching can be a cost-effective solution on the network level, in comparison to slow only or fast only approaches. Furthermore, we can achieve reduced costs of individual OXC nodes, which allows us to minimize scalability problems corresponding to emerging fast switching fabrics.     

Multicast routing and bandwidth dimensioning in overlay networks

Multicast services can be provided either as a basic network service or as an application-layer service. Higher level multicast implementations often provide more sophisticated features and can provide multicast services at places where no network layer support is available. Overlay multicast networks offer an intermediate option, potentially combining the flexibility and advanced features of application layer multicast with the greater efficiency of network layer multicast. In this paper, we introduce the multicast routing problem specific to the overlay network environment and the related capacity assignment problem for overlay network planning. Our main contributions are the design of several routing algorithms that optimize the end-to-end delay and the interface bandwidth usage at the multicast service nodes within the overlay network. The interface bandwidth is typically a key resource for an overlay network provider, and needs to be carefully managed in order to maximize the number of users that can be served. Through simulations, we evaluate the performance of these algorithms under various traffic conditions and on various network topologies. The results show that our approach is cost-effective and robust under traffic variations.     

Analysis and dimensioning of switchless networks for single-layeroptical architecture

The “switchless” all-optical network is an alternative networking approach being developed in the framework of the ACTS project named SONATA, which aims to provide a future single layer, advanced transport architecture on a national scale. The single hop, shared access network employs time and wavelength agility (a WDMA/TDMA scheme), using fast tunable transmitters and receivers, to set up individual customer connections through a single wavelength router (suitably replicated for resilience). The dimensioning of this type of network is one of the main tasks for the design of networks serving a certain number of customers, connected together by means of passive optical networks (PONs). This paper reports an analytical model which allows the network dimensioning according to some relevant design parameters: the number of customers per PON, the number of PONs, the offered traffic per single user (either considering residential or business user), and the required system performance expressed in terms of blocking probability. Furthermore, relevant issues related to the dimensioning of switchless networks are discussed and some results achieved for relevant network scenarios are reported, to assess the feasibility of the system concept     

Joint routing and dimensioning of optical burst switching networks

Existing methods for handling routing and dimensioning in dynamic WDM networks solve the two problems separately. The main drawback of this approach is that a global minimum cost solution cannot be guaranteed. Given that wavelengths are costly resources, determining the minimum network cost is of fundamental importance. We propose an approach which jointly solves the routing and dimensioning problems in optical burst switching (OBS) networks, guaranteeing a target blocking per connection. The method finds the set of routes and the number of wavelengths per network link that minimise the total network cost. To accomplish this, an integer linear programming problem is solved. The proposed method was applied to ring networks, where the optimal solution achieves a reduction in the network cost of 10–40% (for traffic loads <0.4, compared to solving both problems separately). In the case of mesh topologies, to reduce the computational complexity of the method, we applied a variation of it which achieves a local minimum. Even so, a reduction of 5–20% (for traffic loads <0.4) in the network cost was obtained. This ability to lower network cost could make the proposed method the best choice to date for dynamic network operators.     

A framework for resource dimensioning in GPON access networks

In gigabit passive optical networks (GPONs), the ports of the optical line terminal (OLT) support passive optical networks (PONs). An optical split ratio supported on an OLT chassis determines the number of optical network units (ONUs) which can share PON link capacity. Generally, network planners tend to do dimensioning for PON link capacity (OLT port) based on the number of subscribers and their type (i.e. residential or business). Although this dimensioning approach is simple, it does not guarantee a selection of optical split ratio which can optimally allocate bandwidth to end‐subscribers. In this paper, we develop an integrated mathematical framework for optimally dimensioning resources in an GPON access network, namely OLT capacity. This framework comprises three resource‐dimensioning approaches which are based on user requirements: GPON link utilization and capacity optimization. Our mathematical framework has been integrated into software for GPON resource dimensioning, which we have developed to evaluate the support and performance of services in GPON access networks. Copyright © 2011 John Wiley & Sons, Ltd.     

Scalable dimensioning of optical transport networks for grid excess load handling

Grids consist of the aggregation of numerous dispersed computational and storage resources, able to satisfy even the most demanding computing jobs. An important aspect of Grid deployment is the allocation and activation of installed network capacity, needed to transfer data and jobs to and from remote resources. Due to the data-intensive nature of Grid jobs, it is expected that optical transport networks will play an important role in Grid deployment. As Grids possibly consist of high numbers of resources, and users, solving the network dimensioning problem (i.e. determining the number of wavelength channels per fiber and wavelength granularity required) using straightforward Integer Linear Programs (ILP) does not scale well with increasing number of jobs. Therefore, we propose the use of Divisible Load Theory (DLT) when modeling the OCS (with wavelength translation) dimensioning problem in this context. We compare this approach to both an exact ILP and heuristic (derived from the exact ILP) approach as a function of the job arrival process, network related parameters and the Grid job scheduling strategy on the Grid. Results show the convergence of the DLT-based and the exact ILP approach, which indicates that the DLT-based approach is of practical use in cases where the exact ILP-based problem becomes intractable. We study an excess load scenario and evaluate the network cost for varying wavelength granularity, fiber/wavelength cost models, network topology and traffic demand asymmetry under multiple Grid scheduling strategies. Results indicate the suitability of our DLT-based approach as an Optical Transport Network dimensioning tool to be used by network operators.     

Traffic routing and link dimensioning in the common channel signaling networks

Signaling can be defined as the exchange of information specifically concerned with the establishment and control of connections, and with network management, in a telecommunications network. It constitutes the command/control infrastructure of the modern telecommunications networks. The Common Channel Signaling (CCS) network not only forms the foundation for control and management in the modern telecommunications environments but also provides database transaction processing capability for special services such as the 800 Service and Alternate Billing Service (ABS). The CCS network is the backbone for providing the Integrated Services Digital Network (ISDN) signaling, the Advanced Intelligent Network (AIN) services, and the Personal Communications Service (PCS). It is therefore critical to provide adequate switching and transmission (link) capacities so that performance of CCS networks can be ensured. This paper describes a flexible link set dimensioning algorithm for supporting CCS network and traffic engineering. We first show that increasing a link set by one or more links may not always increase the link set capacity accordingly because of the current routing procedure defined in the Signaling System No. 7 (SS7) protocol. We then demonstrate a theorem that enables us to construct the number of all possible meaningful links in a CCS link set. Based on the theorem, an efficient and flexible procedure for implementing the link dimensioning algorithm in software is devised to support the mechanization of the CCS network planning traffic engineering functions. Finally, we show an approach to improve the CCS link utilization efficiency and its sufficient and necessary conditions.     

A simulation based approach for network resources dimensioning in video delivery systems

The availability of high-performance networking technologies and processing power allows creation of new multimedia services and applications in broadband integrated services networks. Such new services will be successful only if delivered to end-users at low cost. At present, for wide-area distributed systems, communication has a relevant impact on the overall costs. As a consequence, adequate methodologies for an efficient dimensioning of the network resources need to be devised. Simulation techniques represent a powerful instrument for the analysis and evaluation of real systems. This paper, moving from the definition of mathematical models for VBR video sources, presents the application of a simulation approach to verify the compatibility of the communication load related to a set of video streams with the data transport capability of an existing network architecture for the delivery of video streams, in the case of CBR communication links.     

Network dimensioning and performance of multiservice, multirateloss networks with dynamic routing

We address a multiservice, multirate loss network environment with dynamic routing. In this setting, we consider multiple traffic load periods (multihour) during the day, and by observing network dynamics, we present a network dimensioning model that consists of two steps: a bandwidth estimation step, followed by a multicommodity flow model for multiple services and traffic loads. For network operations, we discuss a probabilistic admission control policy and three multiservice routing schemes. We have used a ten-node network with multiple asymmetric traffic data sets (partially extracted from an actual network) for our study. It was found that the capacity obtained using the analytic network dimensioning model provides a good estimate of network capacity required for meeting the grade-of-service goal for each service type in each traffic load period; this observation is based on a simulated network environment that uses the proposed admission control and the dynamic routing schemes. Our observation suggests that it may not be not necessary for the dimensioning model to explicitly incorporate an admission control policy, but admission control is needed for network operation to provide desirable grade-of-service     

GA-based optimal dimensioning of three-level traffic shaper for statistical multiplexing in ATM networks

In this paper we discuss genetic algorithm (GA)- based optimal dimensioning of the three-level traffic shaper (tlts) for statistical multiplexing in atm networks. As the objective function for the optimal dimensioning, we consider three alternatives — the variance of the output cell service periods, the variance of the output cell rates, and the sum of squared differences of adjacent cell service periods. We perform simulations for optimal dimensioning of the tlts for statistical multiplexing of vbr video services, and we confirm that the objective function based on the variance of the output cell rates is the most suitable among the three alternatives. The framework of the optimal dimensioning procedure introduced in this paper can be easily extended to other optimal design problems in atm networks for which traditional gradient- based optimal dimensioning methods or random search techniques are not easily applicable due to the nonlinearities and complexities of the related functions and the discreteness of the involved parameters.     

A framework for the dimensioning of broadband mobile networks supporting wireless Internet services

The integration of heterogeneous flows in wireless mobile networks requires that new methodologies for network design and resource dimensioning be developed. We discuss a framework for the dimensioning of such networks by taking into account differentiated user and traffic profiles. Distinct QoS requirements from various applications result in different aggregate throughput per cell being achievable for the same loading factor and network layout depending on user mix. Therefore, appropriate characterization of user mixes and aggregation techniques that map these mixes into resource requirements are key in the design of third-generation systems.     

Routing and dimensioning in optical networks under traffic growth models: an asymptotic approach

We consider the problem of routing and dimensioning in a large optical network where traffic is growing over time. A model of traffic in optical network lightpaths is presented. Lightpaths arrive randomly according to a time-varying Poisson process and hold for a random time with a general distribution. We propose a wavelength division multiplexing network that requires no capacity upgrading in a given time period T while allowing the operator to accommodate all the lightpath requests. We obtain an exact solution of the routing and dimensioning problem under an asymptotic regime where both the capacities and the arrival rates are large. For moderate link capacities, we propose a method to dimension the links so that the first lightpath request rejection occurs, with high probability, after the specified time T. This involves the computation of capacity-exhaustion probability $the probability that at least one lightpath request is rejected in the time period (0, T) due to lack of bandwidth/capacity on some link. Computation of the exact capacity-exhaustion probability is possible for a few specific holding time distributions (e.g., exponential). Since this requires large computing resources, it is feasible only for small networks. We propose a method to estimate the capacity-exhaustion probabilities for a large optical network with general holding time distribution based on the results of an asymptotic analysis. We show that this method has a low computational complexity and is quite accurate in the desired range of low capacity-exhaustion probabilities.     

Topological design,routing and capacity dimensioning for ISL networks in broadband LEO satellite systems

This paper considers the network design of intersatellite link (ISL) networks in broadband LEO satellite systems, where the major challenge is the topology dynamics. First, a general method to design convenient ISL topologies for connection‐oriented operation is presented, and a reference topology for numerical studies is derived. A permanent virtual topology is then defined on top of the orbiting physical one, thus forming a framework for discrete‐time dynamic traffic routing. On this basis, heuristic and optimization approaches for the combined routing and dimensioning task, operating on discrete time steps, are presented and their performance is numerically compared. It is shown that minimizing the worst‐case link capacity is an appropriate target function, which can be formulated as linear optimization problem with linear constraints. Using linear programming (LP) techniques, the dimensioning results are clearly better than with simple heuristic approaches. Copyright © 2001 John Wiley & Sons, Ltd.