Traffic predictive-based flow splitting rerouting scheme for link failures in software-defined networks

Q2 Computer Science

International Journal of Computers and Applications Pub Date : 2023-07-31 DOI:10.1080/1206212X.2023.2241185

Vianney Kengne Tchendji, Joelle Kabdjou, Yannick Florian Yankam

引用次数: 0

Abstract

This paper presents a traffic rerouting approach to keep a satisfactory QoS (Quality of Service) in virtualized network infrastructures (VPN, Cloud, etc.), supervised by an SDN (Software-Defined Networking) controller dealing with high traffic fluctuations. Traffic fluctuations are usually caused by link failures or link congestion and result in high packet loss, long delay times, and high jitter. These metrics are critical in computer network's QoS assessing. In our strategy, we combine traffic prediction in the SDN controller with flow splitting in the data plane. Simulations reveal that this strategy provides more satisfying values of the QoS assessment metrics compared to the literature.

查看原文本刊更多论文

基于流量预测的软件定义网络链路故障分流重路由方案

本文提出了一种在虚拟网络基础设施(VPN, Cloud等)中保持令人满意的QoS(服务质量)的流量重路由方法，该方法由SDN(软件定义网络)控制器监督，处理高流量波动。流量波动通常是由链路故障或链路拥塞引起的，导致丢包率高、时延长、抖动大。这些指标对计算机网络的QoS评价至关重要。在我们的策略中，我们将SDN控制器中的流量预测与数据平面中的流量拆分相结合。仿真结果表明，与文献相比，该策略提供了更令人满意的QoS评估指标值。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Computers and Applications Computer Science-Computer Graphics and Computer-Aided Design

CiteScore

4.70

自引率

0.00%

发文量

期刊介绍： The International Journal of Computers and Applications (IJCA) is a unique platform for publishing novel ideas, research outcomes and fundamental advances in all aspects of Computer Science, Computer Engineering, and Computer Applications. This is a peer-reviewed international journal with a vision to provide the academic and industrial community a platform for presenting original research ideas and applications. IJCA welcomes four special types of papers in addition to the regular research papers within its scope: (a) Papers for which all results could be easily reproducible. For such papers, the authors will be asked to upload "instructions for reproduction'''', possibly with the source codes or stable URLs (from where the codes could be downloaded). (b) Papers with negative results. For such papers, the experimental setting and negative results must be presented in detail. Also, why the negative results are important for the research community must be explained clearly. The rationale behind this kind of paper is that this would help researchers choose the correct approaches to solve problems and avoid the (already worked out) failed approaches. (c) Detailed report, case study and literature review articles about innovative software / hardware, new technology, high impact computer applications and future development with sufficient background and subject coverage. (d) Special issue papers focussing on a particular theme with significant importance or papers selected from a relevant conference with sufficient improvement and new material to differentiate from the papers published in a conference proceedings.