Network-design sensitivity analysis

Tune, Paul; Roughan, Matthew

doi:10.1145/2591971.2591979

Cited by 11 publications

(11 citation statements)

References 30 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such matrices express the global amounts of traffic that is expected to traverse the network infrastructure. ISPs often estimate traffic demand matrices to improve resource management tasks and there are several techniques to obtain such matrices ( [9], [21]). A traffic demand matrix usually summarizes, for each source/destination edge router pair, a given bandwidth required to be supported by the network domain.…”

Section: Routing Configurationmentioning

confidence: 99%

“…Such traffic demands are usually expressed by traffic matrices (e.g. [9], [21]) which are used by ISPs to better understand the traffic aggregates traversing the network domain. Thus, by combining the traffic demands and the traffic forwarding dynamics assumed by the routing protocols, it is possible to foresee which links of the network topology might be overloaded.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Improving Routing Configurations using Multi-Objective Optimization Mechanisms

Sousa

Pereira

Cortez

et al. 2017

JCOMSS

View full text Add to dashboard Cite

IP networks are nowadays well established technologiesbeing used to support a myriad of applications and services,thus assuming a crucial role in todays telecommunication systems. Nevertheless, such infrastructures usually require network administrators to perform a wide set of complex planning and management tasks trying to attain adequate network configurations. Many of such management tasks can be mathematically formulated as NP-hard optimization problems, sometimes involving several objective functions. In this context, this work explores and demonstrates the potential of using computational intelligence methods as optimization engines to tackle complex network optimization problems. In particular, Multi-objective Evolutionary Algorithms (MOEAs) are used to attain near-optimal link state routing configurations robust to distinct operational conditions. As result, network administrators will be provided with a set of alternative routing configurations representing distinct tradeoffs between the considered optimization goals. The robustness of the proposed methods is illustrated by presenting several multiobjective optimization examples able to improve the performance and resilience levels of a network infrastructure. In this perspective, this work presents a contribution for this research area by proposing specific MOEAs based optimization methods able to improve network routing configurations. Furthermore, the devised methods are also integrated in a freely available Traffic Engineering optimization framework able to be used by network administrators interested in improving the routing configurations of their network infrastructures.

show abstract

Section: Routing Configurationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Framework for Improving Routing Configurations using Multi-Objective Optimization Mechanisms

Sousa

Pereira

Cortez

et al. 2017

JCOMSS

View full text Add to dashboard Cite

show abstract

“…Another work addressing the synthesis problem is [40], but its focus is entirely different. Our conceptual model in that paper was to help a network operator understand the effect of errors in predictions of TMs.…”

Section: Entropy and Tm Modelsmentioning

confidence: 99%

Spatiotemporal Traffic Matrix Synthesis

TunePaul

Roughan

2015

SIGCOMM Comput. Commun. Rev.

Self Cite

View full text Add to dashboard Cite

Traffic matrices describe the volume of traffic between a set of sources and destinations within a network. These matrices are used in a variety of tasks in network planning and traffic engineering, such as the design of network topologies. Traffic matrices naturally possess complex spatiotemporal characteristics, but their proprietary nature means that little data about them is available publicly, and this situation is unlikely to change. Our goal is to develop techniques to synthesize traffic matrices for researchers who wish to test new network applications or protocols. The paucity of available data, and the desire to build a general framework for synthesis that could work in various settings requires a new look at this problem. We show how the principle of maximum entropy can be used to generate a wide variety of traffic matrices constrained by the needs of a particular task, and the available information, but otherwise avoiding hidden assumptions about the data. We demonstrate how the framework encompasses existing models and measurements, and we apply it in a simple case study to illustrate the value.

show abstract

“…as in [4], [5]) among many other multifaceted objectives that could be defined. Such TE mechanisms usually use as input the denominated Traffic Matrices [3], which are estimations of the overall edge-to-edge traffic that traverses the ISP infrastructure. Thus, by its unpredictable nature P2P overlay traffic makes much harder the computation of such matrices and the associated estimation errors will negatively affect the quality of all TE mechanisms that depend on traffic matrices [9] [10].…”

Section: Introductionmentioning

confidence: 99%

Towards Effective Control of P2P Traffic Aggregates in Network Infrastructures

Sousa

2015

JCOMSS

View full text Add to dashboard Cite

Nowadays, many P2P applications proliferate in the Internet. The attractiveness of many of these systems relies on the collaborative approach used to exchange large resources without the dependence and associated constraints of centralized approaches where a single server is responsible to handle all the requests from the clients. As consequence, some P2P systems are also interesting and cost-effective approaches to be adopted by content providers and other Internet players. However, there areseveral coexistence problems between P2P applications and Internet Service Providers (ISPs) due to the unforeseeable behavior of P2P traffic aggregates in ISP infrastructures.In this context, this work proposes a collaborative P2P/ISPsystem able to underpin the development of novel Traffic Engineering (TE) mechanisms contributing for a better coexistence between P2P applications and ISPs. Using the devised system, two TE methods are described being able to estimate and control the impact of P2P traffic aggregates on the ISP network links. One of the TE methods allows that ISP administrators are able to foresee the expected impact that a given P2P swarm will have in the underlying network infrastructure. The other TE method enables the definition of ISP friendly P2P topologies, where specific network links are protected from P2P traffic. As result, the proposed system and associated mechanisms will contributefor improved ISP resource management tasks and to foster the deployment of innovative ISP-friendly systems.

show abstract

Network-design sensitivity analysis

Cited by 11 publications

References 30 publications

A Framework for Improving Routing Configurations using Multi-Objective Optimization Mechanisms

A Framework for Improving Routing Configurations using Multi-Objective Optimization Mechanisms

Spatiotemporal Traffic Matrix Synthesis

Towards Effective Control of P2P Traffic Aggregates in Network Infrastructures

Contact Info

Product

Resources

About