Real-time heliostat field aiming strategy optimization based on reinforcement learning

Zhichen Zeng, Dong Ni and Gang Xiao

Applied Energy, 2022, vol. 307, issue C, No S0306261921014896

Abstract: The heliostat field aiming strategy optimization is a crucial topic in solar power tower (SPT) plants. The optimal aiming strategy attempts to maximize the thermal power output while preserving certain operational limits. While existing methods could produce high-optimality results, they cannot be applied to real-time optimization for ultra large scale problems due to high computational complexity. In this work, an effective and scalable optimization method is proposed to achieve real-time optimization for ultra large scale problems, enabling efficient and robust SPT plant operations under varying solar conditions (i.e., cloud shadowing variations). The real-time optimization problem is reformulated as a reinforcement learning problem, capturing the learning from the intrinsic sequential decision-making process, to minimize unnecessary repetitions of computations. A Crescent Dunes-like SPT plant is studied, with the allowable flux density as the optimization constraint, and the results show that the proposed method provides better or comparable performance compared to heuristic optimization methods with an order of magnitude less computation time.

Keywords: Solar thermal power; Heliostat aiming strategy; Real-time optimization; Combinatorial optimization problem; Reinforcement learning (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261921014896
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:307:y:2022:i:c:s0306261921014896

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2021.118224

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().