Network identification via node knock-out

Marzieh Nabi-Abdolyousefi, Mehran Mesbahi

Abstract: This paper examines the problem of identifying the interaction geometry among a known number of the agents, adopting a (weighted) consensus-type algorithm for their coordination. Inspired by how biologists utilize gene knock-outs for experimentally identifying genetic interaction networks in biological organisms, we propose a node-knockout procedure for the complete characterization of the interaction geometry in such consensus-type networks. In our context, the node knockout is essentially a grounding procedure-where the node broadcasts a zero state to its neighbors in the network without removing itself from it. The proposed identification process is also facilitated by introducing “ports” for stimulating a subset of network vertices via an appropriately defined interface and observing the network's response at another set of vertices. We then provide an example for the utility of such a network identification process in the context of fault detection for networked systems.