Research On Solar Irradiance Prediction And Advanced Control Strategy In Solar Power Generation Process

Solar energy as a renewable energy is a kind of green energy,almost no carbon emissions.It plays an important role in environmental protection.At the same time,the Organic Rankine Cycle(ORC)system is used for waste heat recovery and utilization in many studies to improve energy efficiency.It is also important for environmental protection.This paper mainly studies the prediction of solar irradiance and the advanced control strategy of solar power generation process.The main work of this paper includes three parts:the prediction of solar irradiance,the modelling of moderate temperature solar thermal power generation system and the study of optimal predictive control for the system.In the first part,the Hierarchical Extreme Learning Machine(H-ELM)algorithm is used for solar irradiance.The current weather information and historical irradiance information are input,and the current irradiance is output.The prediction strategy of solar irradiance is proposed.Compared with other mature algorithms,the merits of the algorithm are judged by comparing root mean square error,mean absolute error and determinant coefficient.The simulation results show that the H-ELM algorithm has smaller simulation error than other algorithms,which shows that the algorithm has more advantages.In addition,an extension of this part is also made,which uses multi-zone sampling method to generate scene of irradiance under different weather conditions.The generated scene can be used for the analysis and research of solar power generation system.In the second part,the whole solar photo thermal power generation system is modeled.For the solar collector stage,the static models of the collector and auxiliary energy system are built respectively.The predicted solar irradiance is transformed into the corresponding heat transfer to the organic Rankine cycle system.For ORC system,the mechanism of evaporator,turbine,condenser and refrigerant pump is analyzed,and the corresponding mathematical model is established.Then the corresponding model of medium temperature solar thermal power generation system is integrated.The last part is to carry on the previous work and adopt the classical optimal predictive control algorithm.The temperature and mass flow of the heat source are taken as the disturbance predictive signals,and the control of the evaporation pressure and superheat of the system is studied.The simulation results show that the control scheme can achieve good control effect.