Towards Scalable k-out-of-n Models for Assessing the Reliability of Large-Scale Function-as-a-Service Systems with Bayesian Networks

Typically, Function-as-a-Service (FaaS) involves state-less replication with very large numbers of instances. The reliability of such services can be evaluated using Bayesian Networks and k-out-of-n models. However, existing k-out-of-n models do not scale to the larger number of hosts of FaaS services. Therefore, we propose a scalable k-out-of-n model in this paper with the same semantics as the standard k-out-of-n voting gates in fault trees, enabling the reliability analysis of FaaS services.