A method for real-time optimal heliostat aiming strategy generation via deep learning

被引:4
作者
Wu, Sipei [1 ]
Ni, Dong [1 ]
机构
[1] Zhejiang Univ, Coll Control Sci & Engn, Hangzhou 310027, Peoples R China
关键词
Solar thermal power; Solar tower plant; Heliostat field; Combinatorial optimization problem; Deep neural network; SOLAR POWER TOWER; ALLOWABLE FLUX-DENSITY; RECEIVER; OPTIMIZATION; HEAT; PERFORMANCE; DESIGN; PLANTS; MODEL;
D O I
10.1016/j.engappai.2023.107279
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Optimal aiming strategies are essential for efficient solar power tower technology operation. However, the high calculation complexity makes it difficult for existing optimization methods to solve the optimization problem in real-time directly. This work proposes a real-time optimal heliostat aiming strategy generation method via deep learning. First, a two-stage learning scheme where the neural network models are trained by genetic algorithm (GA) benchmark solutions to produce an optimal aiming strategy is presented. Then, an end-to-end model without needing GA solutions for training is developed and discussed. Furthermore, a robust end-to end training method using randomly sampled flux maps is also proposed. The proposed models demonstrated comparable performance as GA with two orders of magnitude less computation time through case studies. Among the proposed models, the end-to-end model shows significantly better generalization ability than the pure data-driven two-stage model on the test set. A robust end-to-end model with data enhancement has better robustness on unseen flux maps.
引用
收藏
页数:12
相关论文
共 45 条
  • [31] Raza K., 2021, Health Inform.: A Comput. Perspective Healthcare, V932, P77, DOI DOI 10.1007/978-981-15-9735-05
  • [32] State-of-the-art of solar thermal power plants-A review
    Reddy, V. Siva
    Kaushik, S. C.
    Ranjan, K. R.
    Tyagi, S. K.
    [J]. RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2013, 27 : 258 - 273
  • [33] Accelerated Aiming Strategy in Central Receiver Systems Using Integer Linear Programming
    Richter, Pascal
    Speetzen, Nils
    [J]. SOLARPACES 2020 - 26TH INTERNATIONAL CONFERENCE ON CONCENTRATING SOLAR POWER AND CHEMICAL ENERGY SYSTEMS, 2022, 2445
  • [34] Control of the flux distribution on a solar tower receiver using an optimized aiming point strategy: Application to THEMIS solar tower
    Salome, Adrien
    Chhel, Fabien
    Flamant, Gilles
    Ferriere, Alain
    Thiery, Frederik
    [J]. SOLAR ENERGY, 2013, 94 : 352 - 366
  • [35] Aiming strategy model based on allowable flux densities for molten salt central receivers
    Sanchez-Gonzalez, Alberto
    Reyes Rodriguez-Sanchez, Maria
    Santana, Domingo
    [J]. SOLAR ENERGY, 2017, 157 : 1130 - 1144
  • [36] Solar flux distribution on central receivers: A projection method from analytic function
    Sanchez-Gonzalez, Alberto
    Santana, Domingo
    [J]. RENEWABLE ENERGY, 2015, 74 : 576 - 587
  • [37] Dynamic aiming strategy for central receiver systems
    Speetzen, N.
    Richter, P.
    [J]. RENEWABLE ENERGY, 2021, 180 : 55 - 67
  • [38] The role of "Allowable flux density" in the design and operation of molten-salt solar central receivers
    Vant-Hull, LL
    [J]. JOURNAL OF SOLAR ENERGY ENGINEERING-TRANSACTIONS OF THE ASME, 2002, 124 (02): : 165 - 169
  • [39] Multi-objective optimization of the aiming strategy for the solar power tower with a cavity receiver by using the non-dominated sorting genetic algorithm
    Wang, Kun
    He, Ya-Ling
    Xue, Xiao-Dai
    Du, Bao-Cun
    [J]. APPLIED ENERGY, 2017, 205 : 399 - 416
  • [40] Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction
    Wang, Wei
    Huang, Yan
    Wang, Yizhou
    Wang, Liang
    [J]. 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2014, : 496 - +