Reconstruction of joint covariances in networked linear systems

We propose a sample representation of estimation errors that is utilized to reconstruct the joint covariance in distributed estimation systems. The key idea is to sample uncorrelated and fully correlated noise according to different techniques at local estimators without knowledge about the processing of other nodes in the network. In this way, the correlation between estimates is inherently linked to the representation of the corresponding sample sets. We discuss the noise processing, derive key attributes, and evaluate the precision of the covariance estimates.