Data-Driven Power Control for State Estimation: A Bayesian Inference Approach

TL;DR

This paper introduces a Bayesian inference-based power control method for sensor transmission in wireless state estimation, improving estimation accuracy by adaptively adjusting power based on estimate importance.

Contribution

It presents a novel power control strategy that preserves Gaussianity and provides a closed-form solution for estimation error, outperforming non data-driven controllers.

Findings

Improved state estimation accuracy with the proposed power control.

Closed-form solution for expected estimation error covariance.

Performance gains over traditional non data-driven controllers.

Abstract

We consider sensor transmission power control for state estimation, using a Bayesian inference approach. A sensor node sends its local state estimate to a remote estimator over an unreliable wireless communication channel with random data packet drops. As related to packet dropout rate, transmission power is chosen by the sensor based on the relative importance of the local state estimate. The proposed power controller is proved to preserve Gaussianity of local estimate innovation, which enables us to obtain a closed-form solution of the expected state estimation error covariance. Comparisons with alternative non data-driven controllers demonstrate performance improvement using our approach.