Application of selective ensemble learning soft sensor modeling based on GPR in the solar thermal power collection system

Yalu  Sun; Kun  Ding; Changhai  Yang; Zhuxiu  Wang

doi:10.6180/jase.202510_28(10).0007

Application of selective ensemble learning soft sensor modeling based on GPR in the solar thermal power collection system

Yalu SunThis email address is being protected from spambots. You need JavaScript enabled to view it., Kun Ding, Changhai Yang, and Zhuxiu Wang

State Grid Gansu Electric Power Company Economic and Technological Research Institute, Lanzhou, 730070, P.R. China

Received: October 30, 2023
Accepted: December 13, 2024
Publication Date: January 23, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202510_28(10).0007

In order to achieve zero carbon emissions, new concepts and algorithms are needed in the control of renewable energy to ensure the safe and reliable operation of the grid under the trend of zero carbonization in the future. In this paper, the ensemble learning soft sensor model is applied to the outlet temperature control of the solar thermal power collection system. Due to the lack of accuracy and diversity of base learners in traditional ensemble methods, ensemble pruning is ignored, and the lack of adaptability. So, the estimated performance falls short of the expected value. Therefore, a novel predictive control method for the outlet temperature of the collector system is proposed based on the Gaussian process regression selective ensemble learning soft sensing model (SESMGPR). Firstly, the collecting heat field temperature values were extracted from the Dunhuang Dacheng solar photothermal power plant as historical data, and the subsets and subspaces of the historical data were obtained by bootstrap and partial least squares regression (PLS), respectively. Secondly, the local domain (LTs) was identified by Gaussian mixture model (GMM) clustering, and the local GPR model was established for each LT to obtain the base model (MGPR). Finally, the set pruning strategy based on a genetic algorithm (GA) was used to select the MGPR model with high estimation performance, and the base models were fused by the Stacking algorithm to obtain the SESMGPR model. Besides, adaptive control is used to alleviate the performance degradation of SESMGPR due to the randomness of solar radiation, ambient temperature, wind speed, etc. Experimental results show that the SESMGPR method can effectively handle time-varying variations of the solar thermal power collection system and maintain high prediction accuracy.

Keywords: Solar thermal power generationEnsemble learning; Gaussian process regressionEnsemble pruningModel adaptation

[1] I. E. Agency. Global Energy Review: CO2 Emissions in 2020. IEA, 2021.
[2] U. N. E. Programme. Emissions Gap Report 2021. UNEP, 2021.
[3] A.Hassan, O. Bass, Y. M. Al-Abdeli, M. Masek, and M. A. Masoum, (2023) “A novel approach for optimal sizing of stand-alone solar PV systems with power quality considerations" International Journal of Electrical Power &Energy Systems 144: 108597. DOI: 10.1016/j.ijepes.2022.108597.
[4] V. Kher, S. Sharma, H. Santhosh, N. Manoj, O. Yo gesh, and N. A. Bhinge. “Scheduled single axis so lar tracker system for improvisation of energy effi ciency”. In: 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE. 2022, 787–791. DOI: 10.1109/ICSSIT53264.2022.9716418.
[5] Z. Wang, X. Lin, N. Tong, Z. Li, S. Sun, and C. Liu, (2020) “Optimal planning of a 100% renewable energy island supply system based on the integration of a concen trating solar power plant and desalination units" Interna tional Journal ofElectrical Power&EnergySystems 117: 105707. DOI: 10.1016/j.ijepes.2019.105707.
[6] S.Zhao,Y.Fang,andZ.Wei,(2019)“Stochastic optimal dispatch of integrating concentrating solar power plants with wind farms" International Journal of Electrical Power&EnergySystems109:575–583. DOI:10.1016/j.ijepes.2019.01.043.
[7] E. G. Cojocaru, M. J. Vasallo, J. M. Bravo, and D. Marin. “Scheduling in Concentrating Solar Power Plants Based on Model Predictive Control and Binary-Regularization Methods”. In: 2018 IEEE Con ference on Control Technology and Applications (CCTA). IEEE. 2018, 1008–1013. DOI: 10.1109/CCTA.2018.8511609.
[8] G. Andonovski, A. Bayas, D. Sáez, S. Blažiˇc, and I. Škrjanc. “Robust evolving cloud-based control for the distributed solar collector field”. In: 2016 IEEE In ternational Conference on Fuzzy Systems (FUZZ-IEEE). IEEE. 2016, 1570–1577. DOI: 10.1109/FUZZ-IEEE.2016.7737877.
[9] D.M.Lima,J. E. Normey-Rico, and T. L. M. Santos, (2016) “Temperature control in a solar collector field using f iltered dynamic matrix control" ISA transactions 62: 39–49. DOI: 10.1016/j.isatra.2015.09.016.
[10] M. Karamali and M. Khodabandeh, (2017) “A dis tributed solar collector field temperature profile control and estimation using inlet oil temperature and radiation estimates based on iterative extended kalman filter" Re newable energy 101: 144–155. DOI: 10.1016/j.renene.2016.08.049.
[11] X. LuandZ.Liang, (2021) “Application of Model Pre dictive Control Based on Kalman Filter in Solar Collector Field of Solar Thermal Power Generation" Energy Engi neering 118(4): 1171–1183. DOI: 10.32604/EE.2021.014724.
[12] P. Gil, J. Henriques, A. Cardoso, P. Carvalho, and A. Dourado, (2013) “Affine neural network-based predictive control applied to a distributed solar collector field" IEEE Transactions on control systems technology 22(2): 585–596. DOI: 10.1109/TCST.2013.2260545.
[13] X. LuandH.Dong, (2017) “Application of multi-model active fault-tolerant sliding mode predictive control in so lar thermal power generation system" Acta Automatica Sinica 43(7): 1241–1247.
[14] M. Naeem, W. K. Mashwani, M. Abiad, H. Shah, Z. Khan, and M. Aamir, (2023) “Soft computing tech niques for forecasting of COVID-19 in Pakistan" Alexan dria Engineering Journal 63: 45–56. DOI: 10.1016/j.aej.2022.07.029.
[15] H.Paggi, J. Soriano, V. Ramperez, R. Gutiérrez, and J. A. Lara, (2022) “A distributed soft sensors model for managing vague and uncertain multimedia communica tions using information fusion techniques" Alexandria Engineering Journal 61(7): 5517–5528. DOI: 10.1016/j.aej.2021.10.060.
[16] L. Fortuna, S. Graziani, A. Rizzo, M. G. Xibilia, et al. Soft sensors for monitoring and control of industrial processes. 22. Springer, 2007.
[17] J. Kortela and S.-L. Jämsä-Jounela, (2012) “Fuel quality soft sensor using the dynamic superheater model for control strategy improvement of the BioPower 5 CHP plant" International Journal of Electrical Power & Energy Systems 42(1): 38–48. DOI: 10.1016/j.ijepes.2012.03.001.
[18] X. Yuan, Z. Ge, B. Huang, Z. Song, and Y. Wang, (2016) “Semisupervised JITL framework for nonlinear industrial soft sensing based on locally semisupervised weighted PCR" IEEE Transactions on Industrial In formatics 13(2): 532–541. DOI: 10.1109/TII.2016.2610839.
[19] W.Shao, X. Tian, and P. Wang, (2015) “Soft sensor de velopment for nonlinear and time-varying processes based on supervised ensemble learning with improved process state partition" Asia-Pacific Journal of Chemical En gineering 10(2): 282–296. DOI: 10.1002/apj.1874.
[20] Y. Wang, D. Wu, and X. Yuan, (2019) “A two-layer ensemble learning framework for data-driven soft sensor of the diesel attributes in an industrial hydrocracking process" Journal of Chemometrics 33(12): e3185. DOI: 10.1002/cem.3185.
[21] J. MA, X. DENG, and L. WANG, (2018) “Industrial process soft sensor method based on deep learning ensem ble support vector machine" CIESC Journal 69(3): 1121. DOI: 10.11949/j.issn.0438-1157.20171050.
[22] H. Jin, L. Shi, X. Chen, B. Qian, B. Yang, and H. Jin, (2021) “Probabilistic wind power forecasting using se lective ensemble of finite mixture Gaussian process re gression models" Renewable Energy 174: 1–18. DOI: 10.1016/j.renene.2021.04.028.
[23] Q. Sun and Z. Ge, (2021) “A survey on deep learning for data-driven soft sensors" IEEE Transactions on In dustrial Informatics 17(9): 5853–5866. DOI: 10.1109/TII.2021.3053128.
[24] H. Jin, B. Pan, X. Chen, and B. Qian, (2019) “Ensem ble just-in-time learning framework through evolutionary multi-objective optimization for soft sensor development of nonlinear industrial processes" Chemometrics and Intelligent Laboratory Systems 184: 153–166. DOI: 10.1016/j.chemolab.2018.12.002.
[25] B. Pan, H. Jin, B. Yang, B. Qian, and Z. Zhao, (2019) “Soft sensor development for nonlinear industrial processes based on ensemble just-in-time extreme learning machine through triple-modal perturbation and evolutionary mul tiobjective optimization" Industrial & Engineering Chemistry Research 58(38): 17991–18006. DOI: 10.1021/acs.iecr.9b03702.
[26] H.Kaneko andK. Funatsu, (2014) “Adaptive soft sen sor based on online support vector regression and Bayesian ensemble learning for various states in chemical plants" Chemometrics and Intelligent Laboratory Systems 137: 57–66. DOI: 10.1016/j.chemolab.2014.06.008.
[27] Z.-H. Zhou, J. Wu, and W. Tang, (2002) “Ensembling neural networks: many could be better than all" Artificial intelligence 137(1-2): 239–263. DOI: 10.1016/S0004-3702(02)00190-X.
[28] T. Liu, S. Chen, S. Liang, and C. J. Harris, (2020) “Se lective ensemble of multiple local model learning for non linear and nonstationary systems" Neurocomputing 378: 98–111. DOI: 10.1016/j.neucom.2019.10.015.
[29] H.Jin, S. Huang, L. Wang, X. Chen, B. Pan, and J. Li, (2019) “Selective ensemble learning based on evolutionary multi-objective optimization for soft sensor development" J. Chem. Eng. Chin. Univ:
[30] R. Grbi´c, D. Sliškovi´c, and P. Kadlec, (2013) “Adap tive soft sensor for online prediction and process moni toring based on a mixture of Gaussian process models" Computers & chemical engineering 58: 84–97. DOI: 10.1016/j.compchemeng.2013.06.014.