基于K-I-ELM多模型集成的分布式光伏出力短期预测方法  

Short-term prediction method of distributed PV output power based on K-I-ELM multi-model integration

作　　者：江卓翰 周胜瑜 何禹清 周任军[3] 孙辰昊 JIANG Zhuohan;ZHOU Shengyu;HE Yuqing;ZHOU Renjun;SUN Chenhao(Economic&Technical Research Institute,State Grid Hunan Electric Power Co.,Ltd.,Changsha 410004,China;Hunan Key Laboratory of Energy Internet Supply-demand and Operation,Changsha 410004,China;School of Electrical&Information Engineering,Changsha University of Science&Technology,Changsha 410114,China)

机构地区：[1]国网湖南省电力有限公司经济技术研究院,湖南长沙410004 [2]能源互联网供需运营湖南省重点实验室,湖南长沙410004 [3]长沙理工大学电气与信息工程学院,湖南长沙410114

出　　处：《电力科学与技术学报》2024年第4期146-152,共7页Journal of Electric Power Science And Technology

基　　金：国家自然科学基金(52207074);国网湖南省电力有限公司科技项目(5216A22001J);湖南省科技创新平台与人才计划(2019TP1053)。

摘　　要：为响应“双碳”目标,高比例新能源接入的新型电力系统已成为下一个发展目标。光伏作为当前电力系统能源发电主体形式之一,其出力特性数据尚存在多源、异构及高维等分布特点,导致不同特征作用机理、机制较为复杂,继而加大分布式光伏系统出力的预测难度。为此,首先构建核主成分分析(kernel principle component analysis,KPCA)模型,通过核函数在特征空间中依据不同特征的有效信息蕴含度提取主成分;然后采用信息熵(information entropy,IE)模型,根据各主成分信息负载度量加权系数,综合求解相应作用权重;最后依据特征评估结果,针对性设置极限学习机(extreme learning machine,ELM)网络参数,降低预测不确定度。最终整合多类别数据挖掘模型,构建K-I-ELM预测方法,在复杂数据环境下实施光伏出力短期预测。基于某实际台区光伏发电数据进行案例分析,论证所提方法针对不同数据环境的适应性及较高的预测精度。In response to the"dual carbon"strategy,a new type of power system with a high proportion of renewable energy access has become the next development goal.As one of the main forms of current energy generation,photovoltaic(PV)power generation has characteristics such as multi-source,heterogeneous,and high-dimensional data distribution,which makes the mechanisms and effects of different features relatively complex and subsequently increases the difficulty of predicting the output of distributed PV systems.To address this,multiple categories of data mining models are integrated to construct an K-I-ELM prediction method for short-term PV output prediction in complex data environments.First,a kernel principal component analysis(KPCA)model is constructed to extract principal components based on the effective information contained in different features in the feature space through a kernel function.An information entropy(IE)model is employed to measure the weighting coefficients based on the information load of each principal component and comprehensively solve the corresponding effect weights.Finally,based on the feature evaluation results,the network parameters of the extreme learning machine(ELM)are set specifically to reduce prediction uncertainty.A case study based on actual PV power generation data from a certain substation demonstrates the adaptability and high prediction accuracy of the proposed method in different data environments.

关 键 词：信息熵 核主成分分析 极限学习机 短期预测 光伏出力 

分 类 号：TM615[电气工程—电力系统及自动化]