Automated Generation of Availability Models for SFCs: the Case of Virtualized IP Multimedia Subsystem
NOMS 2020 - PROCEEDINGS OF THE 2020 IEEE/IFIP NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM 2020 MANAGEMENT IN THE AGE OF SOFTWARIZATION AND ARTIFICIAL INTELLIGENCE(2020)
摘要
The reputation of network providers strongly depends on their ability to guarantee high performance levels of virtualized infrastructures, and to maintain strict Quality-of-Service (QoS) requirements, thus, the concept of "five nines" or high availability (HA) is critical. It means that, on average, the continuity of a provided service cannot be violated for more than about five minutes per year. In this direction, we propose a framework useful to design and model, from a HA perspective, the Service Function Chains (SFCs) whose chained software logic is embodied in many softwarized telco infrastructures (e.g. IP Multimedia Subsystem elected here as a representative use case). The proposed framework interacts with TimeNET tool, and offers interesting functionalities such as: i) generating stochastic models of SFCs based on the SRN (Stochastic Reward Nets) formalism; ii) deploying network scenarios via drag-and-drop operations for basic users, or modifying the underlying SRN models for advanced users; iii) setting a variety of parameters (mean-time-to-failure/repair, software/hardware specs, redundancy, etc.); iv) presenting availability results in tabular and/or graphical forms.
更多查看译文
关键词
Availability model generation,Stochastic Reward Nets,Redundancy Optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要