Achieving Sub-60ms Link Failure Recovery in Software-Defined Networks
JOIV : International Journal on Informatics Visualization · 31.05.2026 · 10 (3) · 1329
DOI: 10.62527/joiv.10.3.5580 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOIV : International Journal on Informatics Visualization, online erschienen am 31.05.2026. Verfasst von Satria Akbar Mugitama und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Software-Defined Networking (SDN) represents a fundamental shift in network architecture, transitioning from hardware-centric configurations to a more flexible, programmable paradigm. At its core, SDN decouples the system's intelligence—the control plane—from the underlying hardware responsible for moving traffic—the data plane. This separation was popularized by the OpenFlow protocol, originally developed at Stanford University, which provides the standardized communication interface between these two layers. However, as networks become increasingly centralized, reliability becomes a critical concern: specifically, how the system maintains connectivity when a physical link fails. To address these reliability gaps, this research developed and evaluated a prototype algorithm designed to manage link failures more efficiently than standard OpenFlow recovery mechanisms. The study focused on two primary metrics: line changeover time (the speed at which the network reroutes traffic) and system overhead. Experimental results revealed that the prototype achieved an average recovery time of 59 ms with a communication overhead of 10.1%. While this performance marks a notable improvement over existing OpenFlow methods, it highlights a persistent challenge in the field: the lack of a "carrier-grade" standard. To be considered truly resilient for mission-critical telecommunications, a network must typically recover from failure in under 50 ms. Although the prototype currently sits 9 ms above this threshold, its superior performance relative to legacy SDN methods suggests that refining the algorithm's logic or reducing its computational footprint could eventually bridge the gap, bringing programmable networks closer to industrial-grade reliability.
Zitieren
APA
Mugitama, S. A., Nuha, H. H., Sailellah, H. R. P., Wen, G. K., & Sukri, K. A. M. (2026). Achieving Sub-60ms Link Failure Recovery in Software-Defined Networks. JOIV : International Journal on Informatics Visualization, 10(3), 1329. https://doi.org/10.62527/joiv.10.3.5580
Vancouver
Mugitama SA, Nuha HH, Sailellah HRP, Wen GK, Sukri KAM. Achieving Sub-60ms Link Failure Recovery in Software-Defined Networks. JOIV : International Journal on Informatics Visualization. 2026;10(3):1329. doi:10.62527/joiv.10.3.5580
BibTeX
@article{Mugitama2026,
author = {Mugitama, Satria Akbar and Nuha, Hilal H. and Sailellah, Hassan Rizky Putra and Wen, Goh Khang and Sukri, Khairul Amin Mohamad},
title = {Achieving Sub-60ms Link Failure Recovery in Software-Defined Networks},
journal = {JOIV : International Journal on Informatics Visualization},
year = {2026},
volume = {10},
number = {3},
pages = {1329},
doi = {10.62527/joiv.10.3.5580}
}
EUVIMED