Output Prediction Of Solar Thermal Power System Based On Intelligent Algorithm

Solar energy is the most common renewable energy in our life,and it is also a pollution-free clean energy.In view of solar energy,scholars at home and abroad have carried out extensive research.Among them,the photothermal power station as a typical photothermal energy storage system has been widely used.For a photothermal power station,output fluctuation is difficult to avoid due to the uncertainty of solar energy,and its output is directly related to the operation efficiency and economy of the whole system.In order to ensure the safe and stable operation of the photothermal power station,it is necessary to predict its output accurately.In view of the above reasons,various factors restricting the output prediction of photovoltaic thermal power station are summarized,and a output prediction method is proposed for photovoltaic thermal power station.Based on the time series analysis method and the energy flow system model of the thermal power generation system,the solar power generation output prediction model is established,and then the corresponding predicted value is obtained.The correctness and effectiveness of the model are verified by simulation experiments.The research content of this paper includes the following aspects:(1)Through comparative analysis and summary of operation principles of various types of photovoltaic power stations,it is concluded that the most important dependent variable of output of photovoltaic power stations is direct solar radiation.BP neural network is selected as the research method of direct solar radiation prediction,and the prediction model is constructed and analyzed.(2)Model establishment and calculation of solar thermal power system.Mathematical models were established for heliostat field and trough solar mirror field of tower solar power station,energy flow analysis of photovoltaic power station was carried out,mechanism modeling of each subsystem of photovoltaic power station was conducted,and its accuracy was verified by simulation experiment.(3)Combining the mathematical model with BP neural network,the output prediction model of the photothermal energy storage power station is proposed.Time series analysis method is used to predict the direct solar radiation,and simulation calculation is used to verify the prediction model.The predicted value of the direct solar radiation is taken as the input of the mathematical model of the energy flow of the photovoltaic energy storage power station,so as to obtain the predicted value of the output of the photovoltaic thermal power station.In order to verify the feasibility of the proposed method,the simulation results are used to verify it.