Academia.eduAcademia.edu

Outline

Title
Abstract
Key Takeaways
Figures
Introduction
Related Work
Methodology
Summary and Outlook
References
All Topics
Computer Science
Computer Networks

Replex

Profile image of Nils KammenhuberNils Kammenhuber

2006

https://doi.org/10.1145/1368436.1368438
visibility

…

description

14 pages

link

1 file

Abstract

One major challenge in communication networks is the problem of dynamically distributing load in the presence of bursty and hard to predict changes in traffic demands. Current traffic engineering operates on time scales of several hours which is too slow to react to phenomena like flash crowds or BGP reroutes. One possible solution is to use load sensitive routing. Yet, interacting routing decisions at short time scales can lead to oscillations, which has prevented load sensitive routing from being deployed since the early experiences in Arpanet. However, recent theoretical results have devised a game theoretical rerouting policy that provably avoids such oscillation and in addition can be shown to converge quickly. In this paper we present REPLEX, a distributed dynamic traffic engineering algorithm based on this policy. Exploiting the fact that most underlying routing protocols support multiple equal-cost routes to a destination, it dynamically changes the proportion of traffic that is routed along each path. These proportions are carefully adapted utilising information from periodic measurements and, optionally, information exchanged between the routers about the traffic condition along the path. We evaluate the algorithm via simulations employing traffic loads that mimic actual Web traffic, i. e., bursty TCP traffic, and whose characteristics are consistent with self-similarity. The simulations quickly converge and do not exhibit significant oscillations on both artificial as well as real topologies, as can be expected from the theoretical results.

Key takeaways
sparkles

AI

  1. REPLEX effectively addresses dynamic load distribution in communication networks to improve traffic engineering.
  2. The algorithm demonstrates quick convergence without oscillations, based on game-theoretic principles.
  3. Simulation results show REPLEX enhances throughput by up to 64% compared to traditional methods.
  4. REPLEX functions across various routing protocols, such as OSPF, MPLS, and BGP, enhancing scalability.
  5. The approach adapts weights according to measured traffic conditions, optimizing for link utilization.
Figures (15)
where wp is the weight of path P, i.e., for P € A(u;,u), we have wp = i w(uj,t,ui+1). The measurement value of the next-hop edge ¢;), can be evaluated at r. Let us now specify the information that router v; sends to r. We define
where wp is the weight of path P, i.e., for P € A(u;,u), we have wp = i w(uj,t,ui+1). The measurement value of the next-hop edge ¢;), can be evaluated at r. Let us now specify the information that router v; sends to r. We define
Algorithm 2 Procedure ADAPTWEIGHTS
Algorithm 2 Procedure ADAPTWEIGHTS
Algorithm 1 Main loop of the REPLEX-algorithm
Algorithm 1 Main loop of the REPLEX-algorithm
Figure 2: The Web servers are connected to two client subnets, each reachable via two different routes. Bottleneck edges are dashed.
Figure 2: The Web servers are connected to two client subnets, each reachable via two different routes. Bottleneck edges are dashed.
Figure 1: A set of HTTP servers is connected to a set of HTTP clients via two different routes (7, v1 ,v3) and (7, v2, v3).
Figure 1: A set of HTTP servers is connected to a set of HTTP clients via two different routes (7, v1 ,v3) and (7, v2, v3).
Figure 3: The above plots show how weights are adapted for two routes with speeds 10 Mbit and 100 Mbit over time. The optimal weights for this scenario are 1/11 and 10/11, respectively. For various values of A, T, and 1 the above plots show the weights for two different routes over time. For every choice of parameters, we have two plots of weights, one for each route. We observe that oscillation vanishes as A = A/T decreases.
Figure 3: The above plots show how weights are adapted for two routes with speeds 10 Mbit and 100 Mbit over time. The optimal weights for this scenario are 1/11 and 10/11, respectively. For various values of A, T, and 1 the above plots show the weights for two different routes over time. For every choice of parameters, we have two plots of weights, one for each route. We observe that oscillation vanishes as A = A/T decreases.
Figure 4: The weights assigned to the routes for different rela- tions of bandwidths. The upper plot shows the weights whereas the lower plot shows the link utilisation of the two routes.
Figure 4: The weights assigned to the routes for different rela- tions of bandwidths. The upper plot shows the weights whereas the lower plot shows the link utilisation of the two routes.
Figure 5: Dependence of the stability of the solution dependent on the number of hosts 7.
Figure 5: Dependence of the stability of the solution dependent on the number of hosts 7.
Figure 6: The Rocketfuel topology for EBONE (AS 1755, .r0 map) consists of 172 routers.
Figure 6: The Rocketfuel topology for EBONE (AS 1755, .r0 map) consists of 172 routers.
Figure 8: A set of D Web clients is connected to router v3 and a set of D/k clients waking up at time 7; = 500s is connected to router v>.
Figure 8: A set of D Web clients is connected to router v3 and a set of D/k clients waking up at time 7; = 500s is connected to router v>.
acca castoris Se tie east eects) Figure 11: Network performance during 1 hour of simulation time. Application layer throughput increases even after the main weight shift has occurred (vertical line) and only ceases increasing well after 10 minutes.
acca castoris Se tie east eects) Figure 11: Network performance during 1 hour of simulation time. Application layer throughput increases even after the main weight shift has occurred (vertical line) and only ceases increasing well after 10 minutes.
Figure 10: Development of weight shifts during the first 10 min- utes. Large weight shifts occur only within the first 2 minutes (vertical line).
Figure 10: Development of weight shifts during the first 10 min- utes. Large weight shifts occur only within the first 2 minutes (vertical line).
Figure 7: Simulation results for the topology depicted in Fig. 2 using bandwidths 10 Mbit, 34 Mbit and 100 Mbit, respectively for the bottleneck edges and 100 Mbit for the other edges.
Figure 7: Simulation results for the topology depicted in Fig. 2 using bandwidths 10 Mbit, 34 Mbit and 100 Mbit, respectively for the bottleneck edges and 100 Mbit for the other edges.

Related papers

A Routing and Resource Preservation Strategy for Traffic Engineering in Communication Networks
annie gravey

18

This paper presents a method for dynamic load balancing in data networks. When multiple routes are available, it determines their load shares as a function of a composite metric that takes into account the paths’ length and load. A general resource preserva- tion mechanism is also presented that complements the proposed random routing strategy when the network is heavily loaded. We compare our approach with trunk reservation in the particular case of fully meshed networks and evaluate its performance in any net- work, where an equivalent mechanism is missing. We validate our approach by means of simulation and provide insights on the routing solutions that it obtains.

View PDFchevron_right
Resilient routing of variable traffic with performance guarantees
James Orlin

2009 17th IEEE International Conference on Network Protocols, 2009

View PDFchevron_right
On the relevance of on-line traffic engineering
Steve Uhlig

The evaluation of dynamic Traffic Engineering (TE) algorithms is usually carried out using some specific network(s), traffic pattern(s) and traffic engineering objective(s). As the behavior of a TE algorithm is a consequence of the interactions between the network, the traffic demand and the algorithm itself, the relevance of TE may depend on several network design aspects. In this paper, we evaluate well-known TE algorithms using real-world and generated network topologies and traffic demands. By re-scaling observed traffic demands, we are able to observe the behavior of TE algorithms under a variety of situations, which may not be observable in reality. We identify distinct network load regimes that correspond to different behaviors of the TE algorithms. We also study the impact of several network design aspects, like network provisioning and redundancy, on the relevance of TE algorithms. We find that there are specific situations under which TE algorithms are useful. These situations depend highly on shortcomings in the network provisioning as well as on the availability of alternative paths in the network.

View PDFchevron_right
Profile-based routing and traffic engineering
Marcel Waldvogel

Computer Communications, 2003

View PDFchevron_right
A Self-adaptive Interdomain Traffic Engineering Scheme
Marilia Curado

In this paper we propose, design, and test a self-adaptive Traffic Engineering (TE) scheme for multihomed stub Autonomous Systems (ASes). This scheme is based on a reduced set of self-adaptive and collaborative Smart Routing Managers (SRMs), which are exclusively located at those multihomed stub ASes participating in our scheme. These SRMs are able to improve the end-to-end traffic performance of delay-sensitive applications. In addition, the SRMs significantly contribute to overall network stability based on their capability to learn from and adapt to the mid and long-term network dynamics. In this sense, the TE actions performed by the SRMs not only depend on the current picture or state of the network. They also depend on the dynamic of these states, since the SRMs are able to evolve jointly with the network dynamics. This has two significant advantages. First, it substantially improves overall network stability. Second, this adaptive feature allows the traffic reallocation decision process to become transparent to the network dynamics.

View PDFchevron_right
A realistic model to evaluate routing algorithms in the Internet
Renato Lo Cigno

GLOBECOM'01. IEEE Global Telecommunications Conference (Cat. No.01CH37270), 2001

This paper addresses the problem of evaluating routing algorithms via simulation in packet-switched networks when elastic traffic is involved. It highlights some deficiencies of classic approaches that fail to capture both the complex interactions of connections traversing multiple bottlenecks and common user behaviors. The paper describes an approach devised to overcome these limitations, which is particularly suited for the evaluation of routing algorithms in presence of best-effort traffic. The simulation results presented offer a deeper insight into wellknown routing algorithms. Through this analysis it is clear that quantitative and also qualitative behaviors of dynamic routing algorithms based on traffic measurements may be fairly different depending on the nature of the traffic loading the network, as well as depending on its interactions with the network parameters and behavior.

View PDFchevron_right
Routing and Traffic Engineering in Dynamic Packet-Oriented Networks
Ales Svigelj

Telecommunications Networks - Current Status and Future Trends, 2012

View PDFchevron_right
Robust traffic engineering
Himanshu Agrawal

2008

View PDFchevron_right
Resilient Traffic Engineering in a Transit-Edge Separated Internet Routing
Stefano Secci

2011 IEEE International Conference on Communications (ICC), 2011

The significant growth of Internet traffic and increase of routing tables require solutions to address Internet scalability and resiliency. A possible direction is to move away from the flat legacy Internet routing to hierarchical routing, separating edge networks from transit networks. In this paper, we study the extended traffic engineering capabilities arising in a transit-edge separated Internet routing, focusing on those multi-homed edge networks (e.g., Cloud/content providers) that aim at increasing their Internet resiliency experience. We model using game theory the interaction between distant independent edge networks exchanging large traffic volumes, with the goal of seeking efficient edge-to-edge load-balanced routing solutions. The proposed traffic engineering framework relies on a noncooperative potential game, built upon locator and path ranking costs, that indicates efficient equilibrium solution for the edge-toedge load-balancing coordination problem. Simulations on real instances show that in comparison to BGP and LISP we can achieve significantly higher resiliency and stability 1 .

View PDFchevron_right
Improved routing strategies for Internet traffic delivery
yamir moreno

Physical Review E, 2004

We analyze different strategies aimed at optimizing routing policies in the Internet. We first show that for a simple deterministic algorithm the local properties of the network deeply influence the time needed for packet delivery between two arbitrarily chosen nodes. We next rely on a real Internet map at the autonomous system level and introduce a score function that allows us to examine different routing protocols and their efficiency in traffic handling and packet delivery. Our results suggest that actual mechanisms are not the most efficient and that they can be integrated in a more general, though not too complex, scheme.

View PDFchevron_right

References (50)

  1. REFERENCES
  2. D. Applegate and E. Cohen. Making intra-domain routing robust to changing and uncertain traffic demands: Understanding fundamental tradeoffs. In Proc. ACM SIGCOMM Conference, 2003.
  3. B. Awerbuch and R. D. Kleinberg. Adaptive routing with end-to-end feedback: Distributed learning and geometric approaches. In Proc. 36th Ann. ACM. Symp. on Theory of Comput. (STOC), 2004.
  4. P. Barford and M. Crovella. Generating representative Web workloads for network and server performance evaluation. In Proc. ACM SIGMETRICS Conference, 1998.
  5. M. Beckmann, C. B. McGuire, and C. B. Winsten. Studies in the Economics and Transportation. Yale University Press, 1956.
  6. P. Berenbrink, T. Friedetzky, L. A. Goldberg, P. Goldberg, Z. Hu, and R. Martin. Distributed selfish load balancing. In Proc. 17th Ann. ACM-SIAM Symp. on Discrete Algorithms (SODA), 2006.
  7. A. Blum, E. Even-Dar, and K. Ligett. Routing without regret, 2005. Manuscript.
  8. Z. Cao, Z. Wang, and E. W. Zegura. Performance of hashing-based schemes for Internet load balancing. In Proc. IEEE INFOCOM Conference, 2000.
  9. H. Dreger, A. Feldmann, M. Mai, V. Paxson, and R. Sommer. Dynamic application-layer protocol analysis for network intrusion detection. In Proc.15thUsenix Security Symposium, 2006 (to appear).
  10. A. Elwalid, C. Jin, S. Low, and I. Widjaja. MATE: MPLS adaptive traffic engineering. In Proc. IEEE INFOCOM Conference, 2001.
  11. E. Even-Dar and Y. Mansour. Fast convergence of selfish rerouting. In Proc. 16th Ann. ACM-SIAM Symp. on Discrete Algorithms (SODA), 2005.
  12. A. Feldmann, A. Gilbert, P. Huang, and W. Willinger. Dynamics of IP traffic: A study of the role of variability and the impact of control. In ACM SIGCOMM Conference, Sept. 1999.
  13. A. Feldmann, A. Greenberg, C. Lund, N. Reingold, and J. Rexford. NetScope: Traffic engineering for IP networks. IEEE Network Magazine, 2000.
  14. S. Fischer, H. Räcke, and B. Vöcking. Fast convergence to Wardrop equilibria by adaptive sampling methods. In Proc. 38th Ann. ACM. Symp. on Theory of Comput. (STOC), Seattle, WA, USA, May 2006. ACM.
  15. S. Fischer and B. Vöcking. On the evolution of selfish routing. In S. Albers and T. Radzik, editors, Proc. 12th Ann. European Symp. on Algorithms (ESA), number 3221 in Lecture Notes in Comput. Sci., Bergen, Norway, September 2004. Springer-Verlag.
  16. S. Fischer and B. Vöcking. Adaptive routing with stale information. In M. K. Aguilera and J. Aspnes, editors, Proc. 24th Ann. ACM SIGACT-SIGOPS Symp. on Principles of Distributed Computing (PODC), Las Vegas, NV, USA, 2005.
  17. B. Fortz, J. Rexford, and M. Thorup. Traffic engineering with traditional IP routing protocols. In IEEE Communication Magazine, 2002.
  18. B. Fortz and M. Thorup. Internet traffic engineering by optimizing OSPF weights. In Proc. IEEE INFOCOM Conference, 2000.
  19. B. Fortz and M. Thorup. Optimizing OSPF/IS-IS weights in a changing world. In IEEE Journal on Selected Areas in Communications, Vol. 20, No. 4, 2002.
  20. W. Hao and R. Ito. Dynamics of load-sensitive adaptive routing. In Proc. IEEE International Conference on Communications (ICC), 2005.
  21. J.-Y. Jo, Y. Kim, H. J. Chao, and F. Merat. Internet traffic load balancing using dynamic hashing with flow volume. In Proc.SPIE ITCom, 2002.
  22. S. Kandula, D. Katabi, B. Davie, and A. Charny. Walking the tightrope: responsive yet stable traffic engineering. In Proc. ACM SIGCOMM, 2005.
  23. D. Katz, K. Kompella, and D. Yeung. Traffic engineering extensions to OSPF version 2. Internet Draft, 2003.
  24. A. Khanna and J. Zinky. The revised ARPANET routing metric. In Proc. ACM SIGCOMM Conference, 1989.
  25. T. Krämer. IP traffic engineering-OSPF vs. MPLS. Master's thesis, Universität des Saarlandes, 2003.
  26. B. Krishnamurthy and J. Rexford. Web Protocols and Practice. Addison-Wesley, 2001.
  27. M. Laor and L. Gendel. The effect of packet reordering in a backbone link on application throughput. IEEE Network, September/October 2002.
  28. Y. Liu and A. L. N. Reddy. Multihoming route control among a group of multihomed stub networks. Technical Report TAMU-ECE-2006-01, 2006.
  29. K. Park and W. Willinger, editors. Self-Similar Network Traffic and Performance Evaluation. Wiley-Interscience, 2000.
  30. C. Pelsser, S. Uhlig, and O. Bonaventure. On the difficulty of establishing interdomain LSPs. In IEEE IPOM, 2004.
  31. J. Postel et al. RFC 793, September 1981. http://www.ietf.org/rfc/rfc793.txt.
  32. V. Raghunathan and P. R. Kumar. A Wardrop routing protocol for ad hoc wireless networks. In IEEE CDC, 2004.
  33. V. Raghunathan and P. R. Kumar. Issues in Wardrop routing in wireless networks. In IEEE WICON, 2005.
  34. Renesys. The SSFNet network simulator. http://www.ssfnet.org/.
  35. M. Roughan, M. Thorup, and Y. Zhang. Traffic engineering with estimated traffic matrices. In Proc. ACM SIGCOMM Conference, 2003.
  36. T. Roughgarden and É. Tardos. How bad is selfish routing? J. ACM, 49(2), 2002.
  37. N. Skrypnyuk. Load-sensitive routing. Master's thesis, TU München, 2006.
  38. N. Spring, R. Mahajan, and D. Wetherall. Measuring ISP topologies with Rocketfuel. In Proc. ACM SIGCOMM Conference, Pittsburgh, PA, USA, August 2002. ACM.
  39. A. Sridharan, R. Guérin, and C. Diot. Achieving near-optimal traffic engineering solutions for current OSPF/IS-IS networks. In Proc. IEEE INFOCOM Conference, 2003.
  40. R. Teixeira. Network Sensitivity to Intradomain Routing Changes. PhD thesis, University of California San Diego, August 2005.
  41. R. Teixeira, N. Duffield, J. Rexford, and M. Roughan. Traffic matrix reloaded: Impact of routing changes. In Proc. Passive and Active Measurement, 2005.
  42. C. Vollmert. A Web workload generator for the SSFNet network simulator. Bachelor's thesis, Technische Universität München, 2004.
  43. J. Wallerich. Design and implementation of a WWW workload generator for the ns-2 network simulator. Master's thesis, Universität des Saarlandes, 2001.
  44. J. Wallerich, H. Dreger, A. Feldmann, B. Krishnamurthy, and W. Willinger. A methodology for studying persistency aspects of Internet flows. ACM SIGCOMM Computer Communication Review, 35, 2005.
  45. H. Wang, H. Xie, L. Qiu, Y. R. Yang, Y. Zhang, and A. Greenberg. COPE: Traffic engineering in dynamic networks. In Proc. ACM SIGCOMM Conference, 2006.
  46. J. G. Wardrop. Some theoretical aspects of road traffic research. In Proc. of the Institute of Civil Engineers, Pt. II, 1952.
  47. X. Xiao, A. Hannan, B. Bailey, and L. Ni. Traffic engineering with MPLS in the Internet. In IEEE Network Magazine, March 2000.
  48. W. Xu and J. Rexford. Miro: Multi-path interdomain routing. In Proc. ACM SIGCOMM Conference, 2006.
  49. C. Zhang, Z. Ge, J. Kurose, Y. Liu, and D. Towsley. Optimal routing with multiple traffic matrices: Tradeoff between average case and worst case performance. In Proc. 13th International Conference on Network Protocols (ICNP), 2005.
  50. Y. Zhang, M. Roughan, C. Lund, and D. Donoho. An information-theoretic approach to traffic matrix estimation. In Proc. ACM SIGCOMM, 2003.

Related papers

Traffic-adaptive routing
Nils Kammenhuber

2008

Despite the bursty and highly volatile traffic, routing in the Internet today is optimised only on coarse time scales, as load-adaptive routing is known to induce performance deterioration by causing massive oscillations. We describe ReplEx, an universally applicable distributed algorithm for dynamic routing/traffic engineering, which is based on game theory. We show through extensive realistic simulations that ReplEx does not oscillate, and that it achieves performance gains comparable to traditional static traffic engineering. To obtain a better understanding of the traffic to be routed, we furthermore analyse global traffic matrices and search engine induced traffic, based on traffic measurements. Moreover we describe EaC, a universally applicable memory efficient algorithm that identify the most popular nodes in a search tree, which can serve to pin down main traffic contributors.

View PDFchevron_right
REPLEX—Dynamic traffic engineering based on Wardrop routing policies
Nils Kammenhuber

2006

One major challenge in communication networks is the problem of dynamically distributing load in the presence of bursty and hard to predict changes in traffic demands. Current traffic engineering operates on time scales of several hours which is too slow to react to phenomena like flash crowds or BGP reroutes. One possible solution is to use load sensitive routing. Yet, interacting routing decisions at short time scales can lead to oscillations, which has prevented load sensitive routing from being deployed since the early experiences in Arpanet. However, recent theoretical results have devised a game theoretical re-routing policy that provably avoids such oscillation and in addition can be shown to converge quickly. In this paper we present REPLEX, a distributed dynamic traffic engineering algorithm based on this policy. Exploiting the fact that most underlying routing protocols support multiple equal-cost routes to a destination, it dynamically changes the proportion of traffic th...

View PDFchevron_right
TeXCP: Responsive yet stable traffic engineering
Srikanth Kandula

Intra-domain Traffic Engineering (TE) aims to route around failures and congestion, and balance load in an ISP's network. Current TE relies on offline methods which use long term average traffic demands. It cannot react to traffic changes caused by BGP reroutes, diurnal traffic variations, attacks, or flash crowds. Further, current TE deals with network failures by pre-computing alternate routings for a limited set of failures. It may fail to prevent congestion when unanticipated or combination failures occur even though the network may have enough capacity to handle those failures. Since ISPs must ensure that each path in the network can cope with the peak load both during normal operation and under failures, current TE requires extensive over-provisioning. This paper presents TeXCP, an online distributed TE protocol that balances load in real-time, responding to actual traffic demands and failures. TeXCP uses multiple paths to deliver demands from an ingress to an egress router, adaptively moving traffic from overutilized to under-utilized paths. These adaptations are carefully designed such that, though done independently by each edge router based on local information, they balance load in the whole network without oscillations. We prove TeXCP is stable and show it is easy to implement. Our extensive simulations show that, for the same traffic demands, a network that uses TeXCP can support the same utilization and failure resilience as a network that uses traditional offline TE, but with a half or a third of the capacity.

View PDFchevron_right
COPE: traffic engineering in dynamic networks
Haiyong Xie

2006

Traffic engineering plays a critical role in determining the performance and reliability of a network. A major challenge in traffic engineering is how to cope with dynamic and unpredictable changes in traffic demand. In this paper, we propose COPE, a class of traffic engineering algorithms that optimize for the expected scenarios while providing a worst-case guarantee for unexpected scenarios. Using extensive evaluations based on real topologies and traffic traces, we show that COPE can achieve efficient resource utilization and avoid network congestion in a wide variety of scenarios.

View PDFchevron_right
Load-Sensitive Routing of Long-Lived IP Flows
Jennifer Rexford

Computer Communication Review, 1999

Internet service providers face a daunting challenge in provisioning network resources, due to the rapid growth of the Internet and wide fluctuations in the underlying traffic patterns. The ability of dynamic routing to circumvent congested links and improve application performance makes it a valuable traffic engineering tool. However, deployment of load-sensitive routing is hampered by the overheads imposed by link-state update propagation, path selection, and signalling. Under reasonable protocol and computational overheads, traditional approaches to load-sensitive routing of IP traffic are ineffective, and can introduce significant route flapping, since paths are selected based on out-of-date link-state information. Although stability is improved by performing load-sensitive routing at the flow level, flapping still occurs, because most IP flows have a short duration relative to the desired frequency of link-state updates. To address the efficiency and stability challenges of load-sensitive routing, we introduce a new hybrid approach that performs dynamic routing of long-lived flows, while forwarding short-lived flows on static preprovisioned paths. By relating the detection of long-lived flows to the timescale of link-state update messages in the routing protocol, route stability is considerably improved. Through simulation experiments using a one-week ISP packet trace, we show that our hybrid approach significantly outperforms traditional static and dynamic routing schemes, by reacting to fluctuations in network load without introducing route flapping.

View PDFchevron_right

Related topics

  • Computer Science
  • Community Networks
  • Multipath Routing
  • Flash crowds
  • Dynamic Routing
  • convergence time
  • Early experience

    • Cited by

    Conflict-free rerouting scheme through flow splitting for virtual networks using switches
    Vianney Kengne Tchendji

    Journal of Internet Services and Applications

    The weaknesses of the Internet led to the creation of a new network paradigmnetwork virtualization. Virtualization is a very successful technique for sharing and reusing resources, which results in higher efficiency. Despite its advantages, including flexibility in network architecture, virtualization imposes many challenges, such as physical resource allocation to virtual devices. An efficient allocation strategy for these resources can ensure good Quality of Service (QoS) in virtual networks, whether in node or link failure events. This paper presents a conflict-free rerouting scheme with efficient additional capacity usage for link and node failure resilience in a virtual network using switches. Combining an IP Fast Rerouting approach and flow-splitting strategy, this scheme provides short reaction time, stable performance and low complexity because the rerouting calculation and configuration are performed in advance. We show that rerouting by traffic splitting based on the entering arc and destination is sufficient to address all link-failure situations in the network, assuming that the network is two-link connected. After modelling the dimensioning problem as an Integer Linear Programme, we demonstrate through practical implementation of our rerouting scheme on different networks that the scheme can substantially minimize the additional capacity draw on the substrate network. A solution using multiple virtual planes is also provided to solve several conflict problems in the case of simultaneous multiple link failures.

    View PDFchevron_right
    Enabling content-aware traffic engineering
    Georgios Smaragdakis

    ACM SIGCOMM Computer Communication Review, 2012

    Today, a large fraction of Internet traffic is originated by Content Delivery Networks (CDNs). To cope with increasing demand for content, CDNs have deployed massively distributed infrastructures. These deployments pose challenges for CDNs as they have to dynamically map end-users to appropriate servers without being fully aware of the network conditions within an Internet Service Provider (ISP) or the end-user location. On the other hand, ISPs struggle to cope with rapid traffic shifts caused by the dynamic server selection policies of the CDNs. The challenges that CDNs and ISPs face separately can be turned into an opportunity for collaboration. We argue that it is sufficient for CDNs and ISPs to coordinate only in server selection, not routing, in order to perform traffic engineering. To this end, we propose Content-aware Traffic Engineering (CaTE), which dynamically adapts server selection for content hosted by CDNs using ISP recommendations on small time scales. CaTE relies on the observation that by selecting an appropriate server among those available to deliver the content, the path of the traffic in the network can be influenced in a desired way. We present the design and implementation of a prototype to realize CaTE, and show how CDNs and ISPs can jointly take advantage of the already deployed distributed hosting infrastructures and path diversity, as well as the ISP detailed view of the network status without revealing sensitive operational information. By relying on tier-1 ISP traces, we show that CaTE allows CDNs to enhance the end-user experience while enabling an ISP to achieve several traffic engineering goals.

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved