全文下载： 
202402018.pdf
文章编号： 1672-6987（2024）02-0147-12； DOI： 10.16351/j.1672-6987.2024.02.018
梁宏涛， 王莹*， 刘国柱， 杜军威， 于旭(青岛科技大学 信息科学与技术学院，山东 青岛 266061)
摘要： 大规模光伏发电并网给我国电力系统运行的稳定性带来了巨大挑战，因此，光伏发电出力的精确预测至关重要。论文对光伏出力预测理论与方法进行系统综述。首先，对光伏出力预测进行分类，特别是按预测形式分为点预测和不确定性预测。其次，通过物理方法、统计方法、人工智能方法及组合方法进一步阐述光伏出力预测；其中从机器学习和深度学习两个方面对人工智能方法进行详细介绍。然后，梳理了点预测和不确定性预测的评价指标，归纳了人工智能预测模型的优化技术。最后，根据我国光伏出力预测的发展现状,对未来的研究趋势做出展望。
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
中图分类号： TP 18文献标志码： A
引用格式： 梁宏涛， 王莹， 刘国柱， 等. 光伏出力预测理论与方法综述［J］. 青岛科技大学学报(自然科学版), 2024, 45(2): 147-158.
LIANG Hongtao， WANG Ying， LIU Guozhu， et al. Review on the theory and methods of photovoltaic output forecasting［J］. Journal of Qingdao University of Science and Technology（Natural Science Edition), 2024， 45（2）： 147-158.
Review on the Theory and Methods of Photovoltaic Output Forecasting
LIANG Hongtao， WANG Ying， LIU Guozhu， DU Junwei， YU Xu
(College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China)
Abstract: 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 prediction of photovoltaic power generation output is very important. This paper systematically summarizes the theories and methods of photovoltaic output prediction. Firstly, the photovoltaic 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 development status of photovoltaic output prediction in China, the future research trend prospects.
Key words: PV power generation; Artificial intelligence algorithm; uncertainty forecast; evaluation index; optimization of forecast model
Key words: PV power generation; Artificial intelligence algorithm; uncertainty forecast; evaluation index; optimization of forecast model.
收稿日期： 2023-04-20
基金项目： 国家自然科学基金项目(61973180，62172249)；山东省产教融合研究生联合培养示范基地项目(2020-19).
作者简介： 梁宏涛（1979—），男，副教授.*通信联系人.
