A Discrete-Time Decentralized Estimation Scheme

This paper investigates a discrete-time distributed estimation approach for multi-agent systems. A given signal is assumed to be sampled by only a subset of agents, named sources, while the other agents, the users, are required to estimate it in a distributed way. Each agent communicates only with a subset of neighbours and the communication topology is described by a directed graph with relatively weak connectivity properties. The problem is solved by resorting to a bank of discrete-time distributed estimators run by each user agent. Convergence properties are then assessed for two classes of signals characterized, respectively, by a null or a uniformly bounded difference of a given order. Simulations are run to show the effectiveness of the approach and assess its performance.