| 513 | 13 | 38 |
| Downloads | Citas | Reads |
Photovoltaic power generation is affected by the chaotic characteristics of meteorology, and its stochastic, volatile and intermittent characteristics affect the operation of power systems seriously. Aiming at the problem of large dimension of original PV power generation data and the vulnerability of power generation to weather conditions, a data processing method based on Principal Component Analysis(PCA) and BRICH clustering was proposed to reduce the dimensionality of model input variables and facilitate statistical modeling. Secondly, a Copula-Monte Carlo-based probabilistic PV power probabilistic prediction model was constructed to calculate the probabilistic interval prediction of PV power output given the future point prediction values. The model was evaluated based on interval coverage and average width of prediction interval. Finally, the summer data of the actual photovoltaic power station were taken as an example for verification analysis. The results show that the Copula-Monte Carlo method can intuitively show the fluctuation range and expected value of photovoltaic power generation, and is superior to other power prediction models.
[1] 万灿，崔文康，宋永华.新能源电力系统概率预测：基本概念与数学原理[J].中国电机工程学报，2021,41(19):6493-6509.
[2] SONG H,AL KHAFAF N,KAMOONA A,et al.Multitasking recurrent neural network for photovoltaic power generation prediction[J].Energy reports.2023,9(S3):369-376.
[3] TIANZE L,SHUSEN L,SHUNJIANG W,et al.Short-term photovoltaic power prediction based on MDCM-GA-LSTM model[J].The journal of engineering.2022,2022(10):994-1005.
[4] 周帆，郑常宝，胡存刚，等.基于高斯混合模型的光伏发电功率概率区间预测[J].科学技术与工程，2021,21(24):10284-10290.
[5] 刘洁，林舜江，梁炜焜，等.基于高阶马尔可夫链和高斯混合模型的光伏出力短期概率预测[J].电网技术，2023,47(1):266-275.
[6] 许彪，徐青山，黄煜，等.基于藤copula分位数回归的光伏功率日前概率预测[J].电网技术，2021,45(11):4426-4435.
[7] 张虎，陈建斌，魏欢.一种改进的BRICH算法及其应用[J].软件导刊，2015,14(10):45-47.
[8] NELSEN R B.An introduction to copulas[M].New York:Springer,1999.
[9] LANDAU D P,BINDER K.A guide to Monte Carlo simulations in statistical physics(4th ed.)[M].Cambridge:Cambridge University Press,2014.
[10] CHEN Y D,ZHANG Q,XIAO M,et al.Probabilistic forecasting of seasonal droughts in the Pearl River basin,China[J].Stochastic environmental research and risk assessment,2016,30(7):2031-2040.
[11] AGOUA X G,GIRARD R,KARINIOTAKIS G.Probabilistic models for spatio-temporal photovoltaic power forecasting[J].IEEE transactions on sustainable energy,2019,10(2):780-789.
[12] HE Y,QIN Y,WANG S,et al.Electricity consumption probability density forecasting method based on LASSO-Quantile Regression Neural Network[J].Applied energy,2019,233:565-575.
Basic Information:
DOI：10.20040/j.cnki.1000-7709.2023.20230949
China Classification Code:TM615
Citation Information:
[1]HUANG Mu-tao,GAO Su-hua,WANG Yang ,et al.Photovoltaic Power Probabilistic Prediction Based on BRICH Clustering and Copula-Monte Carlo Simulation[J].Water Resources and Power,2023,41(12):220-224.DOI:10.20040/j.cnki.1000-7709.2023.20230949.
Fund Information:
国家电网有限公司科技项目资助(SGHZ0000DKJS2200330)
2023-07-04
2023
2023-07-12
2023
2023-11-02
1
2023-11-30
2023-11-30
2023-11-30