当前位置: X-MOL 学术PeerJ Comput. Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Increasing fault tolerance of data plane on the internet of things using the software-defined networks
PeerJ Computer Science ( IF 3.8 ) Pub Date : 2021-05-27 , DOI: 10.7717/peerj-cs.543
Katayoun Bakhshi Kiadehi, Amir Masoud Rahmani, Amir Sabbagh Molahosseini

Considering the Internet of Things (IoT) impact in today’s world, uninterrupted service is essential, and recovery has received more attention than ever before. Fault-tolerance (FT) is an essential aspect of network resilience. Fault-tolerance mechanisms are required to ensure high availability and high reliability in systems. The advent of software-defined networking (SDN) in the IoT plays a significant role in providing a reliable communication platform. This paper proposes a data plane fault-tolerant architecture using the concepts of software-defined networks for IoT environments. In this work, a mathematical model called Shared Risk Link Group (SRLG) calculates redundant paths as the primary and backup non-overlapping paths between network equipment. In addition to the fault tolerance, service quality was considered in the proposed schemes. Putting the percentage of link bandwidth usage and the rate of link delay in calculating link costs makes it possible to calculate two completely non-overlapping paths with the best condition. We compare our two proposed dynamic schemes with the hybrid disjoint paths (Hybrid_DP) method and our previous work. IoT developments, wireless and wired equipment are now used in many industrial and commercial applications, so the proposed hybrid dynamic method supports both wired and wireless devices; furthermore multiple link failures will be supported in the two proposed dynamic schemes. Simulation results indicate that, while reducing the error recovery time, the two proposed dynamic designs lead to improved service quality parameters such as packet loss and delay compared to the Hybrid_DP method. The results show that in case of a link failure in the network, the proposed hybrid dynamic scheme’s recovery time is approximately 12 ms. Furthermore, in the proposed hybrid dynamic scheme, on average, the recovery time, the packet loss, and the delay improved by 22.39%, 8.2%, 5.66%, compared to the Hybrid_DP method, respectively.

中文翻译:

使用软件定义的网络提高物联网上数据平面的容错能力

考虑到物联网(IoT)在当今世界中的影响,不间断的服务至关重要,恢复受到了前所未有的关注。容错(FT)是网络弹性的重要方面。需要使用容错机制来确保系统中的高可用性和高可靠性。物联网中软件定义网络(SDN)的出现在提供可靠的通信平台方面起着重要作用。本文使用面向物联网环境的软件定义网络的概念,提出了一种数据平面容错架构。在这项工作中,称为共享风险链接组(SRLG)的数学模型将冗余路径计算为网络设备之间的主要路径和备用非重叠路径。除了容错能力之外,在提议的方案中还考虑了服务质量。在计算链路成本时,将链路带宽利用率的百分比和链路延迟的比率放在一起,就可以计算出两个完全不重叠且条件最佳的路径。我们将我们提出的两个动态方案与混合不相交路径(Hybrid_DP)方法进行了比较,并比较了先前的工作。物联网的发展,无线和有线设备现在已在许多工业和商业应用中使用,因此,所提出的混合动态方法同时支持有线和无线设备。此外,在两个提议的动态方案中将支持多个链路故障。仿真结果表明,与Hybrid_DP方法相比,这两种提出的动态设计在减少错误恢复时间的同时,还改善了服务质量参数,例如丢包和延迟。结果表明,在网络中出现链路故障的情况下,所提出的混合动态方案的恢复时间约为12 ms。此外,在所提出的混合动态方案中,与Hybrid_DP方法相比,平均恢复时间,数据包丢失和延迟分别提高了22.39%,8.2%,5.66%。
更新日期:2021-05-27
down
wechat
bug