Conjugate gradient MIMO iterative learning control using data-driven stochastic gradients

TL;DR

This paper introduces a stochastic conjugate gradient descent method for data-driven iterative learning control in massive MIMO systems, achieving faster convergence and improved performance over existing methods.

Contribution

It develops a novel stochastic conjugate gradient algorithm tailored for large-scale MIMO systems, enhancing data-driven control efficiency without system modeling.

Findings

The proposed method outperforms stochastic gradient descent in convergence speed.

It surpasses deterministic conjugate gradient methods in control performance.

The approach is validated on a multivariable example demonstrating its effectiveness.

Abstract

Data-driven iterative learning control can achieve high performance for systems performing repeating tasks without the need for modeling. The aim of this paper is to develop a fast data-driven method for iterative learning control that is suitable for massive MIMO systems through the use of efficient unbiased gradient estimates. A stochastic conjugate gradient descent algorithm is developed that uses dedicated experiments to determine the conjugate search direction and optimal step size at each iteration. The approach is illustrated on a multivariable example, and it is shown that the method is superior to both the earlier stochastic gradient descent and deterministic conjugate gradient descent methods.