CG4SR: Near Optimal Traffic Engineering for Segment Routing with Column Generation

Jadin, Mathieu; Aubry, François; Schaus, Pierre; Bonaventure, Olivier

doi:10.1109/infocom.2019.8737424

Cited by 31 publications

(33 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the time of this writing, the most advanced proposals for TE are based on refined optimization algorithms, such as Constraint Programming [7], Local Search [21], Mixed Integer Linear Programming [22] or Column Generation [23]. All these solutions offer significant performance improvements with respect to traditional routing strategies, such as shortest path routing or load balancing.…”

Section: Introductionmentioning

confidence: 99%

Is Machine Learning Ready for Traffic Engineering Optimization?

Bernárdez¹,

Suárez-Varela²,

López³

et al. 2021

2021 IEEE 29th International Conference on Network Protocols (ICNP)

View full text Add to dashboard Cite

Traffic Engineering (TE) is a basic building block of the Internet. In this paper, we analyze whether modern Machine Learning (ML) methods are ready to be used for TE optimization.We address this open question through a comparative analysis between the state of the art in ML and the state of the art in TE.To this end, we first present a novel distributed system for TE that leverages the latest advancements in ML. Our system implements a novel architecture that combines Multi-Agent Reinforcement Learning (MARL) and Graph Neural Networks (GNN) to minimize network congestion. In our evaluation, we compare our MARL+GNN system with DEFO, a network optimizer based on Constraint Programming that represents the state of the art in TE. Our experimental results show that the proposed MARL+GNN solution achieves equivalent performance to DEFO in a wide variety of network scenarios including three real-world network topologies. At the same time, we show that MARL+GNN can achieve significant reductions in execution time (from the scale of minutes with DEFO to a few seconds with our solution).

show abstract

Section: Introductionmentioning

confidence: 99%

Is Machine Learning Ready for Traffic Engineering Optimization?

Bernárdez¹,

Suárez-Varela²,

López³

et al. 2021

2021 IEEE 29th International Conference on Network Protocols (ICNP)

View full text Add to dashboard Cite

show abstract

“…For future work, the idea of using constraint separation could be investigated further, or other ideas of improving the runtime could be explored. Alternatively, using a completely different approach to more efficiently optimize SR paths, such as proposed in [17], could be looked into.…”

Section: Discussionmentioning

confidence: 99%

Failure Resiliency With Only a Few Tunnels – Enabling Segment Routing for Traffic Engineering

Schüller

Aschenbruck

Chimani

et al. 2021

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

Traffic engineering is an important concept that allows Internet Service Providers (ISPs) to utilize their existing routing hardware more efficiently. One technology that can be used is Segment Routing (SR). In this paper, we address the use of SR to increase the resilience against failure scenarios. In addition, we develop solutions that are manageable and, thus, deployable in a tier 1 ISP network. We propose a post-convergence aware SR based optimization model. With it, we can proactively find a single SR configuration that is beneficial in all predefined failure scenarios, including single link failures, shared risk link group failures, and node failures. In addition to this usecase, we also extend the optimization model to include other important practical requirements such as keeping the number of SR tunnels to a minimum, avoiding arbitrary traffic splitting, or meeting latency bounds. We evaluate our approaches with recently measured data from a tier 1 ISP and show that we can improve over state of the art routing approaches.

show abstract

“…To quickly react to unexpected traffic changes and failures, Hartert et al proposed a new approach based on local search [18]. In [19], the authors proposed an algorithm based on column generation to solve the large-scale linear problems with guaranteeing the theory gap bound. In [16], the authors evaluated segment routing mechanism to do traffic engineering in real-world topologies and traffic demands.…”

Section: B Work Related To This Papermentioning

confidence: 99%

Optimal Deployment of SRv6 to Enable Network Interconnection Service

Ren

Guo

Yuan

et al. 2022

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

Many organizations nowadays have multiple sites at different geographic locations. Typically, transmitting massive data among these sites relies on the interconnection service offered by ISPs. Segment Routing over IPv6 (SRv6) is a new simple and flexible source routing solution which could be leveraged to enhance interconnection services. Compared to traditional technologies, e.g., physical leased lines and MPLS-VPN, SRv6 can easily enable quick-launched interconnection services and significantly benefit from traffic engineering with SRv6-TE. To parse the SRv6 packet headers, however, hardware support and upgrade are needed for the conventional routers of ISP.In this paper, we study the problem of SRv6 incremental deployment to provide a more balanced interconnection service from a traffic engineering view. We formally formulate the problem as an SRID problem with integer programming. After transforming the SRID problem into a graph model, we propose two greedy methods considering short-term and long-term impacts with reinforcement learning, namely GSI and GLI. The experiment results using a public dataset demonstrate that both GSI and GLI can significantly reduce the maximum link utilization, where GLI achieves a saving of 59.1% against the default method.

show abstract

CG4SR: Near Optimal Traffic Engineering for Segment Routing with Column Generation

Cited by 31 publications

References 19 publications

Is Machine Learning Ready for Traffic Engineering Optimization?

Is Machine Learning Ready for Traffic Engineering Optimization?

Failure Resiliency With Only a Few Tunnels – Enabling Segment Routing for Traffic Engineering

Optimal Deployment of SRv6 to Enable Network Interconnection Service

Contact Info

Product

Resources

About