Managing information constraints over networks through the lens of configuration functions

This work deals with networks of agents that exchange information under communication constraints. As a first contribution, the theory of configuration functions is exploited to obtain a general abstract formulation of the network information as a function of the network constraints. As a second contribution, two classic network paradigms are examined: i) a decentralized architecture with remote fusion center; and ii) a fully-flat decentralized architecture with local data exchange between neighboring agents. It is shown how these paradigms match well with the general formulation in terms of configuration functions. Finally, the statistical concentration properties of configuration functions are exploited to characterize the information growth rate under both the aforementioned network paradigms, revealing the thermodynamic deterministic behavior that emerges with high probability as the network size scales to infinity.