EPIC: Traffic Engineering-Centric Path Programmability Recovery Under Controller Failures in SD-WANs | IEEE Journals & Magazine | IEEE Xplore

EPIC: Traffic Engineering-Centric Path Programmability Recovery Under Controller Failures in SD-WANs


Abstract:

Software-Defined Wide Area Networks (SD-WANs) offer a promising opportunity to enhance the performance of Traffic Engineering (TE). With the help of Software-Defined Netw...Show More

Abstract:

Software-Defined Wide Area Networks (SD-WANs) offer a promising opportunity to enhance the performance of Traffic Engineering (TE). With the help of Software-Defined Networking (SDN), TE can promptly respond to traffic changes and maintain network performance by leveraging a global network view. One of the key benefits of SDN for TE is path programmability, which is empowered by SDN controllers to enable dynamic adjustments of flows’ forwarding paths. However, controller failures pose new challenges for SD-WANs since path programmability could be decreased due to the increasing number of offline flows, leading to potential TE performance degradation. Existing recovery solutions mainly focus on recovering path programmability for improving unpredictable network performance but cannot guarantee consistently satisfactory TE performance as expected, since path programmability can only indirectly evaluate network performance. In this paper, we propose EPIC to ensure robust TE performance under controller failures. We observe that frequently rerouted flows could greatly influence TE performance. Enlightened by this, EPIC introduces a novel metric called the TE performance-centric ratio to assess the relevance of different path programmability values for TE performance. The key idea of EPIC lies in identifying frequently rerouted flows during TE operations and prioritizing recovery of the path programmability of these flows under controller failures. We formulate an optimization problem to maximize TE performance-centric path programmability and propose an efficient heuristic algorithm to solve this problem. Evaluation results demonstrate that EPIC can improve average load balancing performance by up to 55.6% compared with baselines.
Published in: IEEE/ACM Transactions on Networking ( Volume: 32, Issue: 6, December 2024)
Page(s): 4871 - 4884
Date of Publication: 24 October 2024

ISSN Information:

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.