为增强逐日太阳辐照度预测的准确性和普适性,提出一种基于多维特征分析的双层协同预测模型。首先,搭建一种双层协同架构,将整个模型分成基准层和提升层两部分,使用分层预测的方式追踪目标对象的多维特征和变化趋势;其次,以数值天气预报（NWP）为输入,采用LightGBM基于特征学习预测方法构建基准预测模型;然后,在前者的基础上,挖掘目标时刻太阳辐照度与历史时序数据之间的关联性,引入改进AdaBoost算法与多隐层极限学习机（MH-ELM）作为提升层主体,提高时序预测的稳定性;最后,选用中国中部地区某光伏电站实测太阳辐照度数据进行算例分析,验证了该模型的合理性和有效性。
Abstract
In order to enhance the accuracy and universality of daily solar radiation intensity prediction, a bi-layer collaborative prediction model based on multi-feature analysis is proposed. Firstly, a bi-layer collaborative architecture is established, which divides the entire model into two parts, the base layer and the promotion layer. It tracks the multi-feature and changing trends of the target object using a layered prediction method. Secondly, a benchmark prediction model is also established base on the feature learning prediction method, by using LightGBM and numerical weather prediction （NWP） as input. Then, on the basis of the former, the correlation between the solar irradiance at the target moment and the historical time series data is mined. The improved AdaBoost algorithm and the multiple hidden layer extreme learning machine （MH-ELM） are introduced as the main body of the lifting layer to improve the stability of time series prediction. Finally, the actual measured solar irradiance data of a photovoltaic power station in the central region of China is selected to analyze the calculation example. The rationality and validity of the model are verified.
关键词
太阳辐照度 /
预测 /
AdaBoost算法 /
双层协同架构 /
LightGBM /
多隐层极限学习机
Key words
solar irradiance /
prediction /
AdaBoost algorithm /
bi-layer collaborative architecture /
LightGBM /
multiple hidden layer ELM
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 徐政, 刘滨, 熊强, 等. 多地区太阳能资源的监测与分析[J]. 太阳能学报, 2020, 41(10): 174-181.
XU Z, LIU B, XIONG Q, et al.Monitoring and analysis of solar energy resources in different areas[J]. Acta energiae solaris sinica, 2020, 41(10): 174-181.
[2] NAM S, HUR J.A hybrid spatio-temporal forecasting of solar generating resources for grid integration[J]. Energy, 2019, 177: 503-510.
[3] LI Q, WU Z, ZHANG H J.Spatio-temporal modeling with enhanced flexibility and robustness of solar irradiance prediction: a chain-structure echo state network approach[J]. Journal of cleaner production, 2020, 261: 121151.
[4] 贾东于, 李开明, 杨丽薇, 等. CMIP5气候模式对未来30年太阳辐射变化的预估研究[J]. 太阳能学报, 2020, 41(3): 199-205.
JIA D Y, LI K M, YANG L W, et al.Prediction of solar radiation variation in future by CMIP5 climate model[J]. Acta energiae solaris sinica, 2020, 41(3): 199-205.
[5] TASCIKARAOGLU A, SANANDAJI B M, CHICCO G, et al.Compressive spatio-temporal forecasting of meteorological quantities and photovoltaic power[J]. IEEE transactions on sustainable energy, 2016, 7(3): 1295-1305.
[6] LAN H, YIN Y, HONG Y Y, et al.Day-ahead spatio-temporal forecasting of solar irradiation along a navigation route[J]. Applied energy, 2018, 211: 15-27.
[7] MOORE D S.Statistics: concepts and controversies[M]. New York: W. H. Freeman and Company, 2017: 290-296.
[8] 邓威, 郭钇秀, 李勇, 等. 基于特征选择和Stacking集成学习的配电网网损预测[J]. 电力系统保护与控制, 2020, 48(15): 108-115.
DENG W, GUO Y X, LI Y, et al.Power losses prediction based on feature selection and stacking integrated learning[J]. Power system protection and control, 2020, 48(15): 108-115.
[9] HUANG G B, ZHU Q Y, SIEW C K.Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501.
[10] 王琦, 季顺祥, 钱子伟, 等. 基于熵理论和改进ELM的光伏发电功率预测[J]. 太阳能学报, 2020, 41(10): 151-158.
WANG Q, JI S X, QIAN Z W, et al.Photovoltaic power prediction based on entropy theory and improved ELM[J]. Acta energiae solaris sinica, 2020, 41(10): 151-158.
[11] 靳果, 朱清智, 闫奇. 基于PCA和ML-ELM-AE的短期光伏功率预测[J]. 控制工程, 2021(9): 1787-1796.
JIN G, ZHU Q Z, YAN Q.Short-term output power prediction of photovoltaic system based on PCA and ML-ELM-AE[J]. Control engineering of China, 2021(9): 1787-1796.
[12] 周子东, 李东伟, 李国胜, 等. 基于逐步回归的AdaBoost-SVR模型在海上风电项目造价预测中的应用[J]. 太阳能学报, 2020, 41(7): 259-264.
ZHOU Z D, LI D W, LI G S, et al.Application of AdaBoost-SVR model based on stepwise regression in cost forecast of offshore wind power[J]. Acta energiae solaris sinica, 2020, 41(7): 259-264.
[13] 李军, 闫佳佳. 基于KELM-AdaBoost方法的短期风电功率预测[J]. 控制工程, 2019, 26(3): 492-501.
LI J, YAN J J.Short-term wind power forecasting based on KELM-AdaBoost method[J]. Control engineering of China, 2019, 26(3): 492-501.
[14] 唐雅洁, 林达, 倪筹帷, 等. 基于XGBoost的双层协同实时校正超短期光伏预测[J]. 电力系统自动化, 2021, 45(7): 18-27.
TANG Y J, LIN D, NI C W, et al.XGBoost based bi-layer collaborative real-time calibration for ultra-short-term photovoltaic prediction[J]. Automation of electric power systems, 2021, 45(7): 18-27.
基金
国家自然科学基金（61763040）; 宁夏自治区重点研发项目（2018BFH03004）; 宁夏自治区自然科学基金（NZ17022）
PDF(1594 KB)
