English

Waypoint Optimization Using Bayesian Optimization: A Case Study in Airborne Wind Energy Systems

Systems and Control 2020-11-18 v2 Systems and Control

Abstract

We present a data-driven optimization framework that aims to address online adaptation of the flight path shape for an airborne wind energy system (AWE) that follows a repetitive path to generate power. Specifically, Bayesian optimization, which is a data-driven algorithm for finding the optimum of an unknown objective function, is utilized to solve the waypoint adaptation. To form a computationally efficient optimization framework, we describe each figure-88 flight via a compact set of parameters, termed as basis parameters. We model the underlying objective function by a Gaussian Process (GP). Bayesian optimization utilizes the predictive uncertainty information from the GP to determine the best subsequent basis parameters. Once a path is generated using Bayesian optimization, a path following mechanism is used to track the generated figure-88 flight. The proposed framework is validated on a simplified 22-dimensional model that mimics the key behaviors of a 33-dimensional AWE system. We demonstrate the capability of the proposed framework in a simulation environment for a simplified 22-dimensional AWE system model.

Keywords

Cite

@article{arxiv.1910.12901,
  title  = {Waypoint Optimization Using Bayesian Optimization: A Case Study in Airborne Wind Energy Systems},
  author = {Ali Baheri and Chris Vermillion},
  journal= {arXiv preprint arXiv:1910.12901},
  year   = {2020}
}
R2 v1 2026-06-23T11:57:37.041Z