The self-learning AI controller for adaptive power beaming with fiber-array laser transmitter system

TL;DR

This paper presents a novel AI-based control system using deep neural networks for adaptive power beaming with fiber-array lasers, which improves upon traditional stochastic methods by utilizing real-time sensor data for optimized atmospheric transmission.

Contribution

The study introduces an online-trained deep neural network control system that eliminates the need for pre-training and enhances power beaming efficiency under atmospheric turbulence.

Findings

DNN-based control outperforms traditional SPGD algorithms in simulations.

The approach guarantees continuous optimization without pre-training.

Numerical experiments confirm improved power transfer efficiency.

Abstract

In this study we consider adaptive power beaming with fiber-array laser transmitter system in presence of atmospheric turbulence. For optimization of power transition through the atmosphere fiber-array is traditionally controlled by stochastic parallel gradient descent (SPGD) algorithm where control feedback is provided via radio frequency link by an optical-to-electrical power conversion sensor, attached to a cooperative target. The SPGD algorithm continuously and randomly perturbs voltages applied to fiber-array phase shifters and fiber tip positioners in order to maximize sensor signal, i.e. uses, so-called, "blind" optimization principle. In opposite to this approach a perspective artificially intelligent (AI) control systems for synthesis of optimal control can utilize various pupil- or target-plane data available for the analysis including wavefront sensor data, photo-voltaic array (PVA) data, other optical or atmospheric parameters, and potentially can eliminate well-known drawbacks of SPGD-based controllers. In this study an optimal control is synthesized by a deep neural network (DNN) using target-plane PVA sensor data as its input. A DNN training is occurred online in sync with control system operation and is performed by applying of small perturbations to DNN's outputs. This approach does not require initial DNN's pre-training as well as guarantees optimization of system performance in time. All theoretical results are verified by numerical experiments.