MATE: MPLS adaptive traffic engineering

Elwalid, A.; Jin, Cheng; Low, Steven H.; Widjaja, Indra

doi:10.1109/infcom.2001.916625

Cited by 377 publications

(321 citation statements)

References 16 publications

Supporting

Mentioning

315

Contrasting

Unclassified

Order By: Relevance

“…TeXCP [19], MATE [14], and REPLEX [15] split flows on different paths based on load, however their long control loops make them inapplicable in the data center context which requires faster response times to deal with short flows and dynamic traffic changes. FLARE [28] exploits the inherent burstiness in TCP flows to schedule "flowlets" (bursts of packets) on different paths to reduce extensive packet reordering.…”

Section: Related Workmentioning

confidence: 99%

Dahu: Commodity switches for direct connect data center networks

Radhakrishnan

Tewari

Kapoor

et al. 2013

Architectures for Networking and Communications Systems

View full text Add to dashboard Cite

Solving "Big Data" problems requires bridging massive quantities of compute, memory, and storage, which requires a very high bandwidth network. Recently proposed direct connect networks like HyperX [1] and Flattened Butterfly [20] offer large capacity through paths of varying lengths between servers, and are highly cost effective for common data center workloads. However data center deployments are constrained to multi-rooted tree topologies like Fat-tree [2] and VL2 [16] due to shortest path routing and the limitations of commodity data center switch silicon.In this work we present Dahu 1 , simple enhancements to commodity Ethernet switches to support direct connect networks in data centers. Dahu avoids congestion hot-spots by dynamically spreading traffic uniformly across links, and forwarding traffic over non-minimal paths where possible. By performing load balancing primarily using local information, Dahu can act more quickly than centralized approaches, and responds to failure gracefully. Our evaluation shows that Dahu delivers up to 500% improvement in throughput over ECMP in large scale HyperX networks with over 130,000 servers, and up to 50% higher throughput in an 8,192 server Fat-tree network.

show abstract

Section: Related Workmentioning

confidence: 99%

Dahu: Commodity switches for direct connect data center networks

Radhakrishnan

Tewari

Kapoor

et al. 2013

Architectures for Networking and Communications Systems

View full text Add to dashboard Cite

show abstract

“…In particular, in [17], a Tabu Search algorithm is proposed to find a layout of MPLS paths with the minimum number of hops, whereas in [18] the MPLS routing problem is modeled in terms of an offline multiobjective Mixed Integer Linear Programming model, that looks for the best trade-off between the minimal routing delay, the optimal load balancing, and the minimal splitting of traffic trunks. In [19] and in [20] a multipath adaptive traffic engineering mechanism is introduced. The approach aims at avoiding the network congestion by adaptively balancing the load among multiple paths based on measurements and analysis of the path level.…”

Section: Related Workmentioning

confidence: 99%

Primary and backup paths optimal design for traffic engineering in hybrid IGP/MPLS networks

Mereu

Cherubini²,

Fanni

et al. 2009

2009 7th International Workshop on Design of Reliable Communication Networks

View full text Add to dashboard Cite

Abstract-The paper describes an optimization model which aims at minimizing the maximum link utilization of IP telecommunication networks under the joint use of the traditional IGP protocols and the more sophisticated MPLS-TE technology. The survivability of the network is taken into account in the optimization process implementing the path restoration scheme. This scheme benefits of the Fast Re-Route (FRR) capability allowing service providers to offer high availability and high revenue SLAs (Service Level Agreements). The hybrid IGP/MPLS approach relies on the formulation of an innovative Linear Programming mathematical model that, while optimizing the network utilization, provides optimal user performance, efficient use of network resources, and 100% survivability in case of single link failure. The possibility of performing an optimal exploitation of the network resources throughout the joint use of the IGP and MPLS protocols provides a flexible tool for the ISP (Internet Service Provider) networks traffic engineers.The efficiency of the proposed approach is validated by a wide experimentation performed on synthetic and real networks. The obtained results show that a limited number of LSP tunnels have to be set up in order to significantly reduce the congestion level of the network while at the same time guaranteeing the survivability of the network.

show abstract

“…Examples of these models can be found in Bourquia et al (2003); Elwalid et al (2001); Franzke and Pönitz (2002) (for MPLS networks) and Kochkar et al (2001); Mitra et al (1999); Rombaut et al (2002). For instance, in Mitra et al (1999) propose a generic routing model for multirate circuit-switched loss networks.…”

Section: Overview Of Multiobjective Routing Models For Mplsmentioning

confidence: 99%

A meta-model for multiobjective routing in MPLS networks

Craveirinha

Girão‐Silva

Clímaco

2007

cent.eur.j.oper.res.

View full text Add to dashboard Cite

MPLS (Multiprotocol Label Switching) enables the utilisation of explicit routes and other advanced routing mechanisms in multiservice packet networks, capable of dealing with multiple and heterogeneous QoS (Quality of Service) parameters. Firstly the paper presents a discussion of conceptual and methodological issues raised by multiobjective routing optimisation models for MPLS networks. The major contribution is the proposal of a multiobjective routing optimisation framework for MPLS networks. The major features of this modelling framework are: the formulation of a three-level hierarchical routing optimisation problem including network and service performance objectives, the inclusion of fairness objectives in the different levels of optimisation and a two-level stochastic representation of the traffic in the network (traffic flow and packet stream levels). A variant of the general model for two classes Work partially supported by programme POSI of the III EC programme cosponsored by FEDER and national funds. of traffic flows, QoS traffic and Best Effort traffic, is also presented. Finally a stochastic teletraffic modelling approach, underlying the optimisation model, is fully described.

show abstract

MATE: MPLS adaptive traffic engineering

Cited by 377 publications

References 16 publications

Dahu: Commodity switches for direct connect data center networks

Dahu: Commodity switches for direct connect data center networks

Primary and backup paths optimal design for traffic engineering in hybrid IGP/MPLS networks

A meta-model for multiobjective routing in MPLS networks

Contact Info

Product

Resources

About