Thermal power forecasting of solar power tower system by combining mechanism modeling and deep learning method

Abstract Concentrating solar power systems are proliferating around the world. However, the non-schedulable characteristic of thermal output presents considerable challenges to safe utilization of solar heat. So, seasonable forecasting of thermal output is going to be essential to both power grid and plant. In this paper, a hybrid forecasting method based on mechanism modeling and deep learning method is proposed. By mechanism modeling, the major meteorological factors used for forecasting are identified accurately, avoiding the subjectivity of chosen of model input features. By convolutional neural network and long short-term memory network, the input features are reconstructed, and the spatial-temporal coupling characteristics between meteorological factors are fully explored. Finally, the thermal power is output by fully connected layers. As a case study, the thermal power of a Solar Two-like concentrating solar power plant based on meteorological conditions of Zhangbei is forecasted, and the mean values of root mean square error and mean absolute error are 5.061 MWt and 2.871 MWt on the whole year, respectively. The results show that the methods proposed in paper can be effectively used for thermal power forecasting of concentrating solar power system.

[1]  Gregory J. Kolb,et al.  Final Test and Evaluation Results from the Solar Two Project , 2002 .

[2]  Stefan Lessmann,et al.  A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data , 2018 .

[3]  Yongping Yang,et al.  Multi‐objective optimization of solar‐aided coal‐fired power generation system under off‐design work conditions , 2019, Energy Science & Engineering.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Omar I. Awad,et al.  NOx emissions prediction based on mutual information and back propagation neural network using correlation quantitative analysis , 2020 .

[6]  Francisco J. Collado,et al.  Quick design of regular heliostat fields for commercial solar tower power plants , 2019, Energy.

[7]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[8]  F. Hocaoglu,et al.  A novel method based on similarity for hourly solar irradiance forecasting , 2017 .

[9]  Yong Chen,et al.  Multifactor spatio-temporal correlation model based on a combination of convolutional neural network and long short-term memory neural network for wind speed forecasting , 2019, Energy Conversion and Management.

[10]  Mehrdad Boroushaki,et al.  A computational method for optimal design of the multi-tower heliostat field considering heliostats interactions , 2016 .

[11]  Jianchun Peng,et al.  A review of deep learning for renewable energy forecasting , 2019, Energy Conversion and Management.

[12]  Kody M. Powell,et al.  Hybrid Concentrated Solar Thermal Power Systems: A Review , 2017 .

[13]  Fahad A. Al-Sulaiman,et al.  Development of a mathematical model for optimizing a heliostat field layout using differential evolution method , 2015 .

[14]  Jan Kleissl,et al.  A high-resolution, cloud-assimilating numerical weather prediction model for solar irradiance forecasting , 2013 .

[15]  Hongli Gao,et al.  A new bearing fault diagnosis method based on modified convolutional neural networks , 2020, Chinese Journal of Aeronautics.

[16]  Francisco J. Collado,et al.  A review of optimized design layouts for solar power tower plants with campo code , 2013 .

[17]  Kejun Wang,et al.  Photovoltaic power forecasting based LSTM-Convolutional Network , 2019 .

[18]  D L Siebers,et al.  Estimating convective energy losses from solar central receivers , 1984 .

[19]  Daren Yu,et al.  Short-term average wind speed and turbulent standard deviation forecasts based on one-dimensional convolutional neural network and the integrate method for probabilistic framework , 2020 .

[20]  He Jiang,et al.  Forecast of hourly global horizontal irradiance based on structured Kernel Support Vector Machine: A case study of Tibet area in China , 2017 .

[21]  Dazhi Yang,et al.  Satellite image analysis and a hybrid ESSS/ANN model to forecast solar irradiance in the tropics , 2014 .

[22]  Eric Hu,et al.  The performance of a Solar Aided Power Generation plant with diverse “configuration-operation” combinations , 2016 .

[23]  Thomas Reindl,et al.  Short term solar irradiance forecasting using a mixed wavelet neural network , 2016 .

[24]  M. Thring.  World Energy Outlook , 1977 .

[25]  Fatih Onur Hocaoglu,et al.  A novel hybrid (Mycielski-Markov) model for hourly solar radiation forecasting , 2017 .

[26]  Yongping Yang,et al.  An improvement crossover operation method in genetic algorithm and spatial optimization of heliostat field , 2018, Energy.

[27]  Fei Wang,et al.  Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting , 2019, Energy Conversion and Management.

[28]  Francisco J. Collado,et al.  Campo: Generation of regular heliostat fields , 2012 .

[29]  José R. Dorronsoro,et al.  Deep Neural Networks for Wind and Solar Energy Prediction , 2017, Neural Processing Letters.

[30]  Hongguang Jin,et al.  Off-design thermodynamic performances on typical days of a 330MW solar aided coal-fired power plant in China , 2014 .

[31]  Yongping Yang,et al.  Study on the general system integration optimization method of the solar aided coal-fired power generation system , 2019, Energy.

[32]  Abdallah Khellaf,et al.  A review of studies on central receiver solar thermal power plants , 2013 .

[33]  Glenn Platt,et al.  Machine learning for solar irradiance forecasting of photovoltaic system , 2016 .

[34]  Yongping Yang,et al.  Rapid design of a heliostat field by analytic geometry methods and evaluation of maximum optical efficiency map , 2019, Solar Energy.

[35]  Tara N. Sainath,et al.  Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[36]  Francisco J. Collado,et al.  Two-stages optimised design of the collector field of solar power tower plants , 2016 .

[37]  Robert A. Taylor,et al.  Direct normal irradiance forecasting and its application to concentrated solar thermal output forecasting - A review , 2014 .

[38]  G. Sassi.  Some notes on shadow and blockage effects , 1983 .