Modular population protocols

Abstract: Population protocols are a model of distributed computation intended for the study of networks of independent computing agents with dynamic communication structure. Each agent has a finite number of states, and communication opportunities occur nondeterministically, allowing the agents involved to change their states based on each other's states. Population protocols are often studied in terms of reaching a consensus on whether the input configuration satisfied some predicate. A desirable property of a computation model is modularity, the ability to combine existing simpler computations in a straightforward way. In the present paper we present a more general notion of functionality implemented by a population protocol in terms of multisets of inputs and outputs. This notion allows to design multiphase protocols as combinations of independently defined phases. The additional generality also increases the range of behaviours that can be captured in applications (e.g. maintaining the role distribution in a fleet of servers). We show that composition of protocols can be performed in a uniform mechanical way, and that the expressive power is essentially semilinear, similar to the predicate expressive power in the original population protocol setting.