The large-scale grid connection of photovoltaic power generation has brought great challenges to the stability of power system operation in China.Therefore,the accurate pre-diction of photovoltaic power generation output is very important.This paper systematically summarizes the theories and methods of photovoltaic output prediction.Firstly,the photo-voltaic output prediction is classified,especially divided into point prediction and uncertainty prediction according to the prediction form.Secondly,the photovoltaic output prediction is further elaborated through physical methods,statistical methods,artificial intelligence methods and combination methods.The methods of artificial intelligence are introduced in detail from two aspects:machine learning and deep learning.Then,the evaluation indexes of point prediction and uncertainty prediction are combed,and the optimization techniques of the artificial intelligence prediction model are summarized.Finally,according to the develop-ment status of photovoltaic output prediction in China,the future research trend prospects.
关键词
光伏发电出力/人工智能算法/不确定性预测/评价指标/预测模型优化
Key words
PV power generation/Artificial intelligence algorithm/uncertainty forecast/e-valuation index/optimization of forecast model
维普
万方数据