Learning in Wireless Control Systems Over Nonstationary Channels

Abstract

This paper considers a set of multiple independent control systems that are each connected over a non-stationary wireless channel. The goal is to maximize control performance over all the systems through the allocation of transmitting power within a fixed budget. This can be formulated as a constrained optimization problem examined using Lagrangian duality. By taking samples of the unknown wireless channel at every time instance, the resulting problem takes on the form of empirical risk minimization, a well-studied problem in machine learning. Due to the non-stationarity of wireless channels, optimal allocations must be continuously learned and updated as the channel evolves. The quadratic convergence property of Newton's method motivates its use in learning approximately optimal power allocation policies over the sampled dual function as the channel evolves over time.Conditions are established under which Newton's method learns approximate solutions with a single update, and the subsequent sub-optimality of the control problem is further characterized. Numerical simulations illustrate the near-optimal performance of the method and resulting stability on a wireless control problem.

Learning Optimal Resource Allocations in Wireless Systems

“…In the case in which the weights w i and channel noise power v i may change over time, we may use the existing as a "warm-start" to quickly adapt to the changes in the model. For problem parameters that are changing fast, there have been higher order optimization methods that have been proposed to adapt to changing conditions of the problem [14].…”

Recent advances in data-driven wireless communication using Gaussian processes: A comprehensive survey

“…In addition to stationary patterns, there are also a few complex non-stationary patterns with time-varying characteristics for wireless communication, for instance, mmWave massive MIMO channel modeling [64], 5G wireless channel modeling [65], wireless control systems [66], 3D non-stationary UAV-MIMO channels [67], non-stationary mobile-to-mobile channels allowing for velocity and trajectory variations in mobile stations [68], and non-stationary channel modeling for vehicle-to-vehicle communications [69]. In contrast to the stationary kernel depending only on the distance τ = x−x , the signal characteristics of non-stationary GP, such as frequencies, amplitudes, and spectral densities, have direct dependences on the input locations x.…”

6G: Connecting Everything by 1000 Times Price Reduction

“…With AI-assisted technology, the modeling problem of non-stationary characteristics can be systematically solved via generating sufficient data-sets and machine learning [21]. As an example, it has been reported in [22] that the non-stationary channel statistics among different types of base stations can be exploited using deep learning. Although the AI-assisted physical transmission is still in its infancy, a promising throughput gain can be expected by a deep understanding of non-stationary properties of 6G networks.…”