With the development of information technology, the network consists of various proprietary hardware devices, and the use of these devices brings problems. To solve problems, network function virtualization is proposed, which decouples the software and hardware in the network, and deploys the existing network function devices to a common physical platform. However, network virtualization needs will inevitably face reliability problems during resource virtualization and service function chain deployment. This article proposes a service function chain reliability evaluation method and reliability optimization algorithm. The composition relationship and reliability influencing factors of service function chain were analyzed, including resource preemption, common cause failure, fault recovery and redundant backup. The service function chain was modeled as a Petri net model, and reliability evaluation results related to execution time were obtained. Based on the reliability assessment results, a VNF migration strategy is designed, with reliability as the optimization goal while considering costs. Simulation results show that, compared with the reliability optimization strategy based on backup, our algorithm costs less and reduces the impact of resource preemption on service reliability.

中文翻译：

---

基于Petri网的证监会可靠性评估与迁移优化策略。

随着信息技术的发展，网络由各种专有的硬件设备组成，这些设备的使用带来了问题。为了解决这些问题，提出了网络功能虚拟化技术，它可以将网络中的软件和硬件分离，并将现有的网络功能设备部署到一个通用的物理平台上。但是，在资源虚拟化和服务功能链部署期间，网络虚拟化需求将不可避免地面临可靠性问题。提出了一种服务功能链可靠性评估方法和可靠性优化算法。分析了服务功能链的组成关系和可靠性影响因素，包括资源抢占，共因故障，故障恢复和冗余备份。将服务功能链建模为Petri网模型，并获得与执行时间相关的可靠性评估结果。根据可靠性评估结果，设计了一种VNF迁移策略，将可靠性作为优化目标，同时考虑了成本。仿真结果表明，与基于备份的可靠性优化策略相比，该算法成本更低，减少了资源抢占对服务可靠性的影响。