Photovoltaic short-term output prediction system and method based on XGBoost algorithm

Abstract

The invention relates to a photovoltaic short-term output prediction system and method based on an XGBoost algorithm, and the system comprises a data mining unit and a secondary deep mining unit, andthe data mining unit comprises: a data preprocessing module which is used for preprocessing input feature data; a data set division modulefor dividing the input feature data preprocessed in the data preprocessing module into a plurality of data sets; and a secondary deep mining unit which comprises: a prediction module for carrying out the model training of a prediction model through the feature data and obtaining a trained prediction model, and a training module for carrying out photovoltaic short-term output prediction by utilizing the trained prediction model and outputting a prediction result including photovoltaic output power, wherein an XGBoost algorithm is adopted in the prediction model, and a CART tree is adopted as a base learner. Compared with the prior art, the method has theadvantages of high prediction algorithm efficiency, accurate prediction result and the like.

Description

technical field [0001] The invention relates to the field of power system new energy power generation, in particular to a photovoltaic short-term output prediction system and method based on an XGBoost algorithm. Background technique [0002] New energy power generation has a high degree of volatility and randomness due to its inherent properties. Insufficient output and energy storage or overload operation will cause a power gap, which will bring many negative impacts or even collapse on the power system. The prediction of new energy power generation can The power generation power at the future time is obtained, and then the power difference is obtained, so as to realize the intelligent dispatching of the microgrid system and improve the power quality and operation stability of the system. [0003] Currently, short-term power generation forecasting refers to forecasting the power generation situation in the next few hours to several days. Short-term photovoltaic output for...

AI Technical Summary

Problems solved by technology

The new photovoltaic output prediction model based on the XGBoost (Extreme Gradient Boosting) algorithm has made great breakthroughs in convergence, calculation speed and data set dependence, and the prediction results are accurate and efficient. There are many advantages in prediction, but the current XGBoost algorithm has not been specifically applied in the field of new energy power generation

Images