Sample-Efficient Hyperparameter Optimization of an Aim Point Controller for Solar Tower Power Plants by Bayesian Optimization




Aim Point Control, Solar Tower, Bayesian Optimization


This work introduces a sample-efficient algorithm to optimize the control parameters of an aim point controller for solar power tower plants. Optimizing the control parameters increases the performance of the aim point controller, and thus the efficiency of the plant. However, optimizing the parameters in simulation will not yield the true optimal parameters at the real plant due to mismatches between simulation and reality. Thus, optimization must be done at the real tower to find a true optimum. As this can be time consuming and costly, the optimizer should require a minimum number of steps. Hence, a sample-efficient optimization strategy is needed. This work introduces a new algorithm based on Bayesian Optimization (BO), which leverages multiple sets of simulation data to accelerate the optimization. The algorithm is tested on a six-dimensional test function representing an arbitrary aim point controller. The proposed algorithm outperformed standard Bayesian Optimization by reaching near optimal parameter configurations of 95% accuracy within 33% less optimization steps. In a second test, the proposed algorithm is used to optimize a simulated Vant-Hull aim point controller with two hyperparameters. Here, the algorithm also needs 33% less optimization iterations than the standard BO.


Download data is not yet available.


K. Chatzilygeroudis, V. Vassiliades, F. Stulp, S. Calinon, and J.-B. Mouret, “A survey on policy search algorithms for learning robot controllers in a handful of trials,” Jul. 2018. [Online]. Available:

C. E. Rasmussen and C. K. I. Williams, Gaussian processes for machine learning. Cambridge Mass.: MIT Press, 2006.

G. de Ath, J. E. Fieldsend, and R. M. Everson, “What do you mean?,” 2020. [Online]. Available:

A. Cully, J. Clune, D. Tarapore, and J.-B. Mouret, “Robots that can adapt like animals,” 7553, Jul. 2014. [Online]. Available:

Aaron Wilson, Alan Fern, and Prasad Tadepalli, “Using Trajectory Data to Improve Bayesian Optimization for Reinforcement Learning,” Journal of Machine Learning Research, vol. 15, no. 8, pp. 253–282, 2014.

A. Marco et al., “Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization,” in ICRA2017, Singapore, Singapore, op. 2017, pp. 1557–1563.

R. Antonova, A. Rai, and C. G. Atkeson, “Deep Kernels for Optimizing Locomotion Controllers,” PMLR 78:47-56, 2017.

A. Rai, R. Antonova, F. Meier, and C. G. Atkeson, “Using Simulation to Improve Sample-Efficiency of Bayesian Optimization for Bipedal Robots,” Journal of Machine Learning Research (JMLR).

D. Duvenaud, J. R. Lloyd, R. Grosse, J. B. Tenenbaum, and Z. Ghahramani, “Structure Discovery in Nonparametric Regression through Compositional Kernel Search,” Feb. 2013. [Online]. Available:

R. Pautrat, K. Chatzilygeroudis, and J.-B. Mouret, “Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search,” Sep. 2017. [Online]. Available:

I. Roman, R. Santana, A. Mendiburu, and J. A. Lozano, “An Experimental Study in Adaptive Kernel Selection for Bayesian Optimization,” IEEE Access, vol. 7, pp. 184294–184302, 2019, doi:

E. Fong and C. C. Holmes, “On the marginal likelihood and cross-validation,” Biometrika, vol. 107, no. 2, pp. 489–496, 2020, doi:

D. Duvenaud, “Automatic model construction with Gaussian processes,” Apollo - University of Cambridge Repository, 2014.

F. J. Collado and J. Guallar, “A two-parameter aiming strategy to reduce and flatten the flux map in solar power tower plants,” Solar Energy, vol. 188, pp. 185–189, 2019, doi:




How to Cite

Zanger, D., Lenz, B., Maldonado Quinto, D., & Pitz-Paal, R. (2023). Sample-Efficient Hyperparameter Optimization of an Aim Point Controller for Solar Tower Power Plants by Bayesian Optimization. SolarPACES Conference Proceedings, 1.

Conference Proceedings Volume


Analysis and Simulation of CSP and Hybridized Systems

Funding data