Data-driven sensor scheduling for remote estimation in wireless networks

TL;DR

This paper introduces a data-driven sensor scheduling framework for remote estimation in wireless networks that does not require prior probabilistic models, using empirical risk minimization and convex optimization.

Contribution

It develops a novel model-free approach for sensor scheduling based solely on observed data, applicable to unicast and broadcast networks, with efficient local optimization methods.

Findings

Framework is independent of data distribution and sensor correlation.

Empirical risk minimization formulated as a difference-of-convex problem.

Locally optimal solutions obtained efficiently via convex-concave procedure.

Abstract

Sensor scheduling is a well studied problem in signal processing and control with numerous applications. Despite its successful history, most of the related literature assumes the knowledge of the underlying probabilistic model of the sensor measurements such as the correlation structure or the entire joint probability density function. Herein, a framework for sensor scheduling for remote estimation is introduced in which the system design and the scheduling decisions are based solely on observed data. Unicast and broadcast networks and corresponding receivers are considered. In both cases, the empirical risk minimization can be posed as a difference-of-convex optimization problem and locally optimal solutions are obtained efficiently by applying the convex-concave procedure. Our results are independent of the data's probability density function, correlation structure and the number of sensors.