Paper detail

Age-of-Information in Clocked Networks

We derive key features of the Age-of-Information distribution in a system whose activities are strictly limited to periodic instances on a global time grid. In particular, one agent periodically generates updates while the other agent periodically uses the most recently received of those updates. Likewise, transmission of those updates over a network can only occur periodically. All periods may differ. We derive results for two different models: a basic one in which the mathematical problems can be handled directly and an extended model which, among others, can also account for stochastic transmission failure, making the results applicable to instances with wireless communication. For both models, a suitable approximation for the expected Age-of-Information and an upper bound for its largest occurring value are developed. For the extended model (which is the more relevant one from a practical standpoint) we also present numerical results for the distribution of the approximation error for numerous parameter choices.