Combined Plant and Controller Design Using Batch Bayesian Optimization: A Case Study in Airborne Wind Energy Systems Ali Baheri Chris Vermillion University of North Carolina at Charlotte akhayatb@uncc.edu cvermill@uncc.edu Abstract We present a novel data-driven nested optimization framework that addresses the problem of coupling between plant and controller optimization. This optimization strat- egy is tailored towards instances where a closed-form ex- pression for the system dynamic response is unobtainable and simulations or experiments are necessary. Specifically, Bayesian Optimization, which is a data-driven technique for finding the optimum of an unknown and expensive-to- evaluate objective function, is employed to solve a nested optimization problem. The underlying objective function is modeled by a Gaussian Process (GP); then, Bayesian Optimization utilizes the predictive uncertainty information from the GP to determine the best subsequent control or plant parameters. The proposed framework differs from the majority of co-design literature where there exists a closed- form model of the system dynamics. Furthermore, we uti- lize the idea of Batch Bayesian Optimization at the plant optimization level to generate a set of plant designs at each iteration of the overall optimization process, recognizing that there will exist economies of scale in running multiple experiments in each iteration of the plant design process. We validate the proposed framework for Altaeros' Buoyant Airborne Turbine (BAT). We choose the horizontal stabi- lizer area, longitudinal center of mass relative to center of buoyancy (plant parameters), and the pitch angle set-point (controller parameter) as our decision variables. Our results demonstrate that these plant and control parameters con- verge to their respective optimal values within only a few iterations. Figure 1: Altaeros Buoyant Airborne Turbine (BAT), Image Credit: [1] 1 Introduction Airborne Wind Energy (AWE) systems are a new paradigm for wind turbines in which the structural elements of conventional wind turbines are replaced with tethers and a lifting body (a kite, rigid wing, or aerostat) to harvest wind power from significantly increased altitudes (typically up to 600m). At those altitudes, winds are stronger and more con- sistent than ground-level winds. The vast energy resource from high-altitude winds has attracted the attention of numerous research and commer- cial ventures over the past two decades ([1, 2, 3, 4, 5]). To- date, many organizations in the AWE community have fo- cused on optimizing operating altitude ([6, 7]) and cross- wind motion to maximize power output, while a limited number of studies have focused on combined plant and con- trol system designs, which have been shown in [8] to be coupled. Combined plant and controller problems consist of those arXiv:1901.07521v1 [cs.SY] 22 Jan 2019