Inter-domain Traffic Engineering Research Articles

Design and implementation of efficient control for incoming inter-domain traffic with Information-Centric Networking

Efficient and accurate control of incoming inter-domain traffic is critically important for Autonomous Systems (ASes). However, it is extremely difficult for two neighboring ASes to efficiently control incoming traffic over multiple inter-domain links in the current Internet. By contrast, Information-Centric Networking (ICN) is a novel network paradigm and has many inherent features, which can support finer granularity of routing policies and provide more opportunities to realize Traffic Engineering (TE). In this paper, we explore the potentials of ICN in controlling incoming inter-domain traffic between neighboring ASes who have multiple inter-domain links. We present a heuristic algorithm and extend it with different information on network status and content metadata. We implement them in a real prototype and compare them with a classic inter-domain TE approach in the current Internet (i.e., the IP-prefixes negotiation approach, IPN) in three scenarios. Three interesting conclusions are drawn from extensive experiments on the prototype. First, ICN makes it easier to control inter-domain traffic compared with IPN. In particular, ICN approaches have shorter negotiation delay and lower negotiation overhead. Second, content metadata (e.g., content size) in ICN is quite beneficial to control traffic since it can help estimate traffic volumes so as to achieve more accurate control of traffic. Third, ICN can efficiently handle the bursty traffic and link failures compared with IPN.

Two-dimensional routing based inter-domain traffic engineering model

Two-dimensional routing based inter-domain traffic engineering model

DIMR: Disjoint Interdomain Multipath Routing

Interdomain Multipath Routing, which allows an AS to transport packets to the same destination via different paths, is a promising technique for achieving high bandwidth, high resiliency and fast reaction to failures. However, previous Interdomain Multipath Routing algorithms often produce overlapped paths, thus are vulnerable to the failure of bottlenecks, and are also inefficient to support interdomain traffic engineering or concurrent multipath transfer. In this paper, we propose Disjoint Interdomain Multipath Routing (DIMR), which helps more ASes to discover two disjoint paths for each destination AS. The core idea of DIMR is a novel concept named path pair, which combines two disjoint or partly disjoint paths. We design the rules of path pair selection and build a theoretical model to formally prove the convergence of a network running DIMR. To fully utilize the disjoint paths, we also propose two packet forwarding approaches, both of which are guaranteed to be loop-free. Our simulation results show thatDIMR enables about 90% of multi-connected ASes to install two disjoint paths.

Efficient inter-domain traffic engineering with transit-edge hierarchical routing

The relentless growth of Internet, which has resulted in the increase of routing table sizes, requires consideration and new direction to address Internet scalability and resiliency. A possible direction is to move away from the flat legacy Internet routing to hierarchical routing, and introduce two-level hierarchical routing between edge networks and across transit networks. In this way, there is also an opportunity to separate the routing locator from the terminal identifier, to better manage IP mobility and mitigate important routing security issues. In this paper, we study the extended traffic engineering capabilities arising in a transit-edge hierarchical routing, focusing on those multi-homed edge networks (e.g., Cloud/content providers) that aim at increasing their Internet resiliency experience. We model the interaction between distant independent edge networks exchanging large traffic volumes using game theory, with the goal of seeking efficient edge-to-edge load-balancing solutions. The proposed traffic engineering framework relies on a non-cooperative potential game, built upon locator and path ranking costs, that indicates efficient equilibrium solution for the edge-to-edge load-balancing coordination problem. Simulations on real instances show that in comparison to the available standard protocols such as BGP and LISP, we can achieve a much higher degree of resiliency and stability.1A preliminary version of this paper has been presented at the 2011 IEEE Int. Conference on Communications (ICC 2011) [1].1

An Effective approach to control Inter-domain Traffic Engineering among Heterogeneous Networks

The Flow of packets inside an IP networks can be effectively controlled by appropriate traffic engineering. Today’s internet routing mainly concentrates on controlling the ingress and egress traffic which occurs through border routers. There are different ways by which we can control the traffic between autonomous systems. In most cases redistribution communities are used for the control over traffic engineering. In this paper we focus on alternative approaches like Multi Protocol Label Switching (MPLS) and Ambient Networks, through which there can be an effective control over traffic engineering. Ambient Networks are designed to solve switching problems between heterogeneous networks.

Rehoming edge links for better traffic engineering

Traditional traffic engineering adapts the routing of traffic within the network to maximize performance. We propose a new approach that also adaptively changes where traffic enters and leaves the network---changing the "traffic matrix", and not just the intradomain routing configuration. Our approach does not affect traffic patterns and BGP routes seen in neighboring networks, unlike conventional inter-domain traffic engineering where changes in BGP policies shift traffic and routes from one edge link to another. Instead, we capitalize on recent innovations in edge-link migration that enable seamless rehoming of an edge link to a different internal router in an ISP backbone network---completely transparent to the router in the neighboring domain. We present an optimization framework for traffic engineering with migration and develop algorithms that determine which edge links should migrate, where they should go, and how often they should move. Our experiments with Internet2 traffic and topology data show that edge-link migration allows the network to carry 18.8% more traffic (at the same level of performance) over optimizing routing alone.

AIR: a Scalable Inter-domain Routing Protocol

As the Internet booms in size and evolves toward a ubiquitous information infrastructure, its interdomain routing mechanism is going to encounter predictable scalability problems in the future. This paper introduces a new scalable inter-domain routing protocol, AS-level Inter-domain Routing (AIR) which is tailored for the Internet that we can envision today. We design AIR at the routing granularity of the Autonomous System (AS) level and take advantages of the Multi Protocol Label Switch (MPLS) to facilitate the packet forwarding between ASes. Compared with the Border Gateway Protocol (BGP), AIR enhances the routing scalability of the next generation Internet while preserving the economic/administrative model of the inter-domain operations. Our design focuses on MPLS enabled AS-level transit routes and retains the flexibility of supporting inter-domain routing policies as well as rational inter-domain traffic engineering. Our proposal synthetically adopts various practical techniques and integrates them into a fruitful design.

GATEway: symbiotic inter-domain traffic engineering

There are a group of problems in networking that can most naturally be described as optimization problems (network design, traffic engineering, etc.). There has been a great deal of research devoted to solving these problems, but this research has been concentrated on intra-domain problems where one network operator has complete information and control. An emerging field is inter-domain engineering, for instance, traffic engineering between large autonomous networks. Extending intra-domain optimization techniques to inter-domain problems is often impossible without the information available within a domain, and providers are often unwilling to share such information. This paper presents an alternative: we propose a method for traffic engineering that does not require sharing of important information across domains. The method extends the idea of genetic algorithms to allow symbiotic evolution between two parties. Both parties may improve their performance without revealing their data, other than what would be easily observed in any case. We show the method provides large reductions in network congestion, close to the optimal shortest path routing across a pair of networks. The results are highly robust to measurement noise, the method is very flexible, and it can be applied using existing routing.

Cooperative Interdomain Traffic Engineering Using Nash Bargaining and Decomposition

We present a novel approach to interdomain traffic engineering based on the concepts of Nash bargaining and dual decomposition. Under this scheme, ISPs use an iterative procedure to jointly optimize a social cost function, referred to as the Nash product. We show that the global optimization problem can be separated into subproblems by introducing appropriate shadow prices on the interdomain flows. These subproblems can then be solved independently and in a decentralized manner by the individual ISPs. Our approach does not require the ISPs to share any sensitive internal information, such as network topology or link weights. More importantly, our approach is provably Pareto-efficient and fair. Therefore, we believe that our approach is highly amenable to adoption by ISPs when compared to past approaches. We also conduct simulation studies of our approach over several real ISP topologies. Our evaluation shows that the approach converges quickly, offers equitable performance improvements to ISPs, is significantly better than unilateral approaches (e.g., hot-potato routing) and offers the same performance as a centralized solution with full knowledge.

Managing interdomain traffic in Latin America: a new perspective based on LISP

The characteristics of Latin American network infrastructures have global consequences, particularly in the area of interdomain traffic engineering. As an example, Latin America shows the largest de-aggregation factor of IP prefixes among all regional Internet registries, being proportionally the largest contributor to the growth and dynamics of the global BGP routing table. In this article we analyze the peculiarities of LA interdomain routing architecture, and provide up-to-date data about the combined effects of the multihoming and TE practices in the region. We observe that the Internet Research Task Force initiative on the separation of the address space into locators and identifiers can not only alleviate the growth and dynamics of the global routing table, but can also offer appealing TE opportunities for LA. We outline one of the solutions under discussion at the IRTF, the Locator/Identifier Separation Protocol, and examine its potential in terms of interdomain traffic management in the context of LA. The key advantage of LISP is its nondisruptive nature, but the existing proposals for its control plane have some problems that may hinder its possible deployment. In light of this, we introduce a promising control plane for LISP that can solve these issues, and at the same time has the potential to bridge the gap between intradomain and interdomain traffic management.

Provisioning QoS in inter-domain traffic engineering

This work describes an architectural framework that allows inter-domain Traffic Engineering Label Switched Paths (TE-LSPs) with guaranteed quality of service (QoS) to be setup. Such TE-LSPs, called EQ-links, are setup by coordinating path computation elements (PCEs) of neighboring autonomous systems (ASs) along a pre-determined inter-AS path, computed through cooperative interaction between pairs of neighboring ASs. After defining the architectural requirements for the framework, we describe and analyze the Inter-AS Path Computation Protocol (IA-PCP), which computes an interdomain path at the AS level, i.e., selecting a sequence of ASs to the destination, based on a loose source routing approach. The results of the IA-PCP computations are then fed to the PCEs for complete path computation. The proposed architecture has been actually implemented within the testbed of the EuQoS project, which is aimed at enabling end-to-end QoS in the Internet. We report results related to the setup time of EQ-links, measured in the pan-European testbed of the EuQoS project, showing that path computation and setup takes an affordable time overhead.

Combined intra- and inter-domain traffic engineering using hot-potato aware link weights optimization

A well-known approach to intradomain traffic engineering consists in finding the set of link weights that minimizes a network-wide objective function for a given intradomain traffic matrix. This approach is inadequate because it ignores a potential impact on interdomain routing due to hot-potato routing policies. This may result in changes in the intradomain traffic matrix that have not been anticipated by the link weights optimizer, possibly leading to degraded network performance. We propose a BGP-aware link weights optimization method that takes these hot-potato effects into account. This method uses the interdomain traffic matrix and other available BGP data, to extend the intradomain topology with external virtual nodes and links, on which all the well-tuned heuristics of a classical link weights optimizer can be applied. Our method can also optimize the traffic on the interdomain peering links.

Operational Evaluation of ASON/GMPLS Interdomain Capability over a JGN II Network Testbed

Traffic engineering in backbone networks is an important issue in supporting an appropriate QoS level to accommodate various types of traffic flows efficiently. Automatically switched optical networks and generalized multiprotocol label switching control planes are promising functionalities to achieve the sophisticated mechanism of interdomain traffic engineering. In this article we address dynamic operational scenarios to control IP traffic flows using the ASON/GMPLS control plane. This includes cut-through IP/MPLS routers and the rerouting of failed links through the tunnel of optical label-switched paths. This article presents an operational evaluation of traffic engineering. More specifically, we present QoS recovery for protecting high priority traffic using policy controllers and fault recovery of inter-domain LSPs over the JGN II network testbed. This article evaluates and discusses the feasibility of these operational scenarios using state-of-the-art optical switching and control- plane technologies.

Traffic Engineering an Operational Network with the TOTEM Toolbox

We explain how the TOTEM toolbox can be used to engineer an operational network. TOTEM is an open source TOolbox for Traffic Engineering Methods which covers IP- based and MPLS-based intradomain traffic engineering (TE) algorithms, but also interdomain TE. In this paper, we use the toolbox as an off-line simulator to optimise the traffic of an operational network. To help an operator choose between an IP-based or MPLS-based solution, or find the best way to load- balance a network for a given traffic, our case study compares several IP and MPLS routing algorithms, evaluates the impact of hot-potato routing on the intradomain traffic matrix, and analyses the worst-case link failure. This study reveals the power of a toolbox that federates many traffic engineering algorithms.

Interdomain traffic engineering in ASON/GMPLS controlled multilayer optical networks

Optical control planes such as automatically switched optical networks or generalized multiprotocol label switching (GMPLS) have been viewed as one key enabling technology for future broadband communication networks for their capabilities of dynamic provisioning of flexible and effective services. To support end-to-end service delivery in optical networks, one of the most challenging issues for the optical control plane to address is how to design traffic engineering (TE) under a heterogeneous interdomain scenario. We propose a dynamic TE scheme for interdomain multilayer optical networks that supports setting up paths transparently for both intradomain and interdomain requests. The proposed scheme also disseminates through advertisement precomputed cost tables pertaining to traffic quality of service requirements, which can help optimize the utilization of both all-optical and optical-electrical-optical resources during the TE process throughout the network. We studied the TE scheme in networks with either instantaneous status update or with periodical status update. Our simulation results show that in both cases the proposed TE scheme outperforms existing TE solutions by setting up intradomain and interdomain paths integrally using the cost tables. Furthermore, we find that optimal network status update interval should vary with traffic load.

Building an AS-topology model that captures route diversity

An understanding of the topological structure of the Internet is needed for quite a number of networking tasks, e. g., making decisions about peering relationships, choice of upstream providers, inter-domain traffic engineering. One essential component of these tasks is the ability to predict routes in the Internet. However, the Internet is composed of a large number of independent autonomous systems (ASes) resulting in complex interactions, and until now no model of the Internet has succeeded in producing predictions of acceptable accuracy.We demonstrate that there are two limitations of prior models: (i) they have all assumed that an Autonomous System (AS) is an atomic structure - it is not, and (ii) models have tended to oversimplify the relationships between ASes. Our approach uses multiple quasi-routers to capture route diversity within the ASes, and is deliberately agnostic regarding the types of relationships between ASes. The resulting model ensures that its routing is consistent with the observed routes. Exploiting a large number of observation points, we show that our model provides accurate predictions for unobserved routes, a first step towards developing structural mod-els of the Internet that enable real applications.

On route selection for interdomain traffic engineering

In this article we investigate a model of route selection for interdomain traffic engineering where routing to multiple destinations can be coordinated. We identify potential routing instability and inefficiency problems, and derive a set of practical guidelines to guarantee stability without global coordination. Using a realistic Internet topology, we show that route oscillations can happen even when a small number of ASes coordinate route selection for just a small number of destinations if the coordination does not follow our guidelines. Wc further extend our model so that ASes can adopt any route selection algorithms in a class of algorithms we call rational route selection algorithms; and the local ranking of routes of an AS can depend on ingress traffic patterns. We show that persistent route oscillations can happen in certain network settings even if the ASes strictly follow the constraints imposed by business considerations, and adopt any rational route selection algorithms.

End-to-end quality of service provisioning through inter-provider traffic engineering

This paper addresses the issue of delivering solutions that will enable the incremental implementation of inter-domain quality of service (QoS) in the multi-provider commercial Internet. The paper first introduces a holistic architecture that describes the key functions required to support inter-domain QoS, and then proceeds to present results from two major components of the architecture. A genetic algorithm for QoS-aware offline inter-domain traffic engineering is first presented, and it is shown through simulation studies how this can optimise the apportionment of QoS provisioning between adjacent domains. Secondly, QoS enhancements to BGP are proposed and the results of a testbed implementation are described, demonstrating how this QoS-enhanced BGP can deliver inter-domain QoS routing.

An open source traffic engineering toolbox

We present the TOTEM open source Traffic Engineering (TE) toolbox and a set of TE methods that we have designed and/or integrated. These methods cover intra-domain and inter-domain TE, IP-based and MPLS-based TE. They are suitable for network optimisation, better routing of traffic for providing QoS, load balancing, protection and restoration in case of failure, etc. The toolbox is designed to be deployed as an on-line tool in an operational network, or used off-line as an optimisation tool or as a traffic engineering simulator.

A MULTIPLE-OBJECTIVES EVOLUTIONARY PERSPECTIVE TO INTERDOMAIN TRAFFIC ENGINEERING

We present an application of multiple-objectives evolutionary optimisation to the problem of engineering the distribution of the interdomain traffic in the internet. We show that this practical problem requires such a heuristic due to the potentially conflicting nature of traffic-engineering objectives. Furthermore, having to work on the parameter's space (BGP routing) of the real problem makes such techniques as evolutionary optimisation very easy to use. We show the successful application of our algorithm to two practically relevant problems in interdomain traffic engineering.