| Summary: | 碩士 === 吳鳳科技大學 === 光機電暨材料研究所 === 105 === In this study, taking the Min-Ho Elementary School in Chia-Yi County as an example, the records of solar power generation system were captured, and the monitoring value of power generation was set as Dependent variable. The main meteorological parameters such as wind direction, wind speed, temperature, (Pearson Correlation Coefficient) method and P value test method were used to calculate the correlation strength between the independent variable and the dependent variable, and then the independent variables with the highest correlation degree were calculated by using Pearson Correlation Coefficient (Pearson Correlation Coefficient) The applicability of solar power generation forecasting model based on Artificial Neural Networks (ANN) method is discussed. The results show that solar energy is correlated with the temperature and humidity of meteorological parameters and the neural network analysis (ANN) is used to analyze the temperature and humidity parameters with the solar power generation. It is applied to the monthly and monthly data of February to May, Solar power generation training forecast, to confirm the forecast value of the month close to the actual value, showing the weather parameters and solar power generation are interrelated. In the follow-up training parameters used from June of 2015 to January of 2016 solar power generation prediction modeling, both in simulation and prediction results, are close to the actual value, verify the solar power generation and meteorological parameters have a certain correlation; The future can be based on meteorological parameters to predict solar power generation, as the current solar power generation system design and application.
|
|---|
