End-to-end deadlines over dynamic topologies

Despite the creativity of the scientific community and the funding agencies, the underlying model of computation behind IoT, WSN, cloud, edge, fog, and mist is fundamentally the same; Computational nodes which are dynamically interconnected to form a system in where both processing capacity and connectivity may vary over time. On top of such a system, we consider applications that need packets to flow along a path and adhere to end-to-end deadlines. This application model is motivated by both control and automation systems, as well as telecom systems. The challenge is to guarantee end-to-end deadlines when allowing nodes and applications to join or leave.

The mainstream, and to some extent natural, approach to this is to relax the stringency of the constraint (e.g. use probabilistic guarantees, soft deadlines). In this paper we take a different approach and keep the end-to-end deadlines as hard constraints and instead partially limit the freedom of how nodes and applications are allowed to leave and join. We present a theoretical framework for modeling such systems along with proofs that deadlines are always honored.