Availability and Reliability of Service Function Chain: A Quantitative Evaluation View

Abstract

Service function chain (SFC) based on network function virtualization (NFV) technology can handle network traffic flexibly and efficiently. The virtual network function (VNF), as the core function unit of SFC, can experience software aging, which reduces the availability and reliability of SFC and even leads to service interruption, after it runs continuously for a long time. Software rejuvenation technique can effectively combat software aging. However, its effectiveness in improving the availability and reliability of SFC needs to be evaluated. Compared with existing models, this paper proposes a semi-Markov model to capture the behaviors of each VNF in a SFC from the occurrence of software aging to recovery by software rejuvenation technique under the condition that the failure times and recovery times follow general distribution, while considering trigger intervals of software rejuvenation technique. We then derive the calculation formulas of the steady-state availability, transient availability, and reliability, which are applied to evaluate the effectiveness of software rejuvenation technique. Finally, we conduct sensitivity analysis and numerical experiments to analyze the effects of system parameters, the number of VNFs and trigger interval of software rejuvenation technique on availability and reliability of SFC, and the effects of time-varying parameters on transient availability of SFC.