No abstract

Solar energy is recognized as an ideal renewable energy. Solar photovoltaic power generation is an important way to use solar energy. Photovoltaic power generation can alleviate the existing energy crisis and alleviate various environmental problems. As a clean and renewable energy, photovoltaic power generation is playing a prominent role in smart micro-grid. The intensity of solar radiation is fluctuating, so the successful grid connection of solar power stations requires accurate power prediction. This paper focuses on the prediction of ultraviolet power index to solve the problem of power prediction of photovoltaic power station. Based on the analysis of cumulative autoregressive moving average model, the stationary of ultraviolet index time series was detected, the order of ultraviolet index model was estimated, and the ARIM A model of ultraviolet index was determined. The prediction accuracy of the model is determined by the root mean square error (RM SE) and mean absolute error (M AE).

With the development of clean energy, wind power generation has become one of the most important power generation methods. However, the output power of wind power generation system is characterized by uncertainty, so the effective interval prediction of wind power is an effective method to reduce the uncertainty.In this article, through multi-channel multi-dimensional meteorological data, visual correlation analysis, and in-depth analysis of the main factors affecting wind power, put forward based on the extreme gradient promotion (XGB) improved LGB model to forecast. In addition, in order to improve the model calculating speed and accuracy, using principal component analysis was carried out on the original data dimension reduction analysis and visualization processing, then predicted the results compared with the actual situation, to verify the validity of the established model, it shows that this method can be applied to the era of big data of wind power prediction in the future.