考虑不同太阳辐射对光伏功率的影响,提出一种基于二次分解和改进粒子群算法的光伏功率预测模型。通过Spearman和Kendall对影响光伏功率的各气象因素进行相关性分析,发现总倾斜辐射、总水平辐射、漫射倾斜辐射、漫射水平辐射与光伏功率的相关系数较大。然后利用CLARANS将样本数据按太阳辐射强度分为强辐射、中辐射和弱辐射,针对3类数据采用自适应噪声完备集合经验模态分解（CEEMDAN）对关键气象因素和功率进行二次分解,充分挖掘时序信息并降低数据的不稳定性。提出一种改进粒子群算法（GWCPSO）用于优化卷积神经网络和双向长短期记忆网络的超参数,提高调参效率,最后构建预测模型进行光伏功率预测。分析3种太阳辐射类型下不同分解方法与网络模型的预测误差,结果表明,所的预测模型可有效提高不同太阳辐射下光伏功率的预测精度。
Abstract
A photovoltaic power prediction model based on quadratic decomposition and improved particle swarm optimization algorithm is proposed considering the impact of different solar radiation on photovoltaic power. Through Spearman and Kendall's correlation analysis of various meteorological factors affecting photovoltaic power, it was found that the correlation coefficients between total tilt radiation, total horizontal radiation, diffuse tilt radiation, diffuse horizontal radiation, and photovoltaic power are relatively large. Then we use CLARANS to divide the sample data into strong radiation, medium radiation and weak radiation according to the solar radiant intensity. For the three types of data, we use CEEMDAN to decompose the key meteorological factors and power twice, fully mining time series information and reducing data instability. The GWCPSO is proposed to optimize the hyperparameter of the convolutional neural network and the bidirectional long short-term memory network, improve the efficiency of parameter adjustment, and finally build a prediction model for photovoltaic power prediction. Analyzing the prediction errors of different decomposition methods and network models under three types of solar radiation, the results show that the proposed prediction model can effectively improve the prediction accuracy of photovoltaic power under different solar radiation conditions.
关键词
光伏功率预测 /
二次分解 /
粒子群算法 /
卷积神经网络 /
双向长短期记忆网络
Key words
photovoltaic power prediction /
secondary decomposition /
particle swarm optimization /
convolutional neural network /
bidirectional long short-term memory
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 国家能源局. 新型电力系统发展蓝皮书(征求意见稿)[EB/OL].http://www.nea.gov.cn/2023-01/06/c_1310688702.htm.
National Energy Administration.Blue book on the development of new power systems(draft for comments)[EB/OL]. http://www.nea.gov.cn/2023-01/06/c_1310688702.htm.
[2] 张臻, 陈天鹏, 王磊, 等. 基于地基云图的超短期太阳辐照预测方法与装置研究[J]. 太阳能学报, 2023, 44(1): 133-140.
ZHANG Z, CHEN T P, WANG L, et al.Research on ultra-short-term solar irradiance prediction method and devicebased on ground-based cloud images[J]. Acta energiae solaris sinica, 2023, 44(1): 133-140.
[3] ZHENG J Q, ZHANG H R, DAI Y H, et al.Time series prediction for output of multi-region solar power plants[J]. Applied energy, 2020, 257: 114001.
[4] KORKMAZ D.SolarNet: a hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting[J]. Applied energy, 2021, 300: 117410.
[5] ELIZABETH MICHAEL N, HASAN S, AL-DURRA A, et al.Short-term solar irradiance forecasting based on a novel Bayesian optimized deep long short-term memory neural network[J]. Applied energy, 2022, 324: 119727.
[6] 向玲, 刘佳宁, 苏浩, 等. 基于CEEMDAN二次分解和LSTM的风速多步预测研究[J]. 太阳能学报, 2022, 43(8): 334-339.
XIANG L, LIU J N, SU H, et al.Research on multi-step wind speed forecast based on ceemdan secondary decomposition and lstm[J]. Acta energiae solaris sinica, 2022, 43(8): 334-339.
[7] 董雪, 赵宏伟, 赵生校, 等. 基于SOM聚类和二次分解的BiGRU超短期光伏功率预测[J]. 太阳能学报, 2022, 43(11): 85-93.
DONG X, ZHAO H W, ZHAO S X, et al.Ultra-short-term forecasting method of photovoltaic power based on SOM clustering, secondary decomposition and BiGRU[J]. Acta energiae solaris sinica, 2022, 43(11): 85-93.
[8] 孟安波, 陈嘉铭, 黎湛联, 等. 基于相似日理论和CSO-WGPR的短期光伏发电功率预测[J]. 高电压技术, 2021, 47(4): 1176-1184.
MENG A B, CHEN J M, LI Z L, et al.Short-term photovoltaic power generation prediction based on similar day theory and CSO-WGPR[J]. High voltage engineering, 2021, 47(4): 1176-1184.
[9] YANG M, ZHAO M, HUANG D W, et al.A composite framework for photovoltaic day-ahead power prediction based on dual clustering of dynamic time warping distance and deep autoencoder[J]. Renewable energy, 2022, 194: 659-673.
[10] ZHOU Y, ZHOU N R, GONG L H, et al.Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine[J]. Energy, 2020, 204: 117894.
[11] 王开艳, 杜浩东, 贾嵘, 等. 基于相似日聚类和QR-CNN-BiLSTM模型的光伏功率短期区间概率预测[J]. 高电压技术, 2022, 48(11): 4372-4388.
WANG K Y, DU H D, JIA R, et al.Short-term interval probability prediction of photovoltaic power based on similar daily clustering and QR-CNN-BiLSTM model[J]. High voltage engineering, 2022, 48(11): 4372-4388.
[12] NG R T, HAN J W.CLARANS: a method for clustering objects for spatial data mining[J]. IEEE transactions on knowledge and data engineering, 2002, 14(5): 1003-1016.
[13] HE D Q, LIU C Y, JIN Z Z, et al.Fault diagnosis of flywheel bearing based on parameter optimization variational mode decomposition energy entropy and deep learning[J]. Energy, 2022, 239(PB): 122108.
[14] DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J]. IEEE transactions on signal processing, 2014, 62(3): 531-544.
[15] TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP). Prague, Czech Republic, 2011, 4144-4147.
[16] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[17] 谢小瑜, 周俊煌, 张勇军, 等. 基于W-BiLSTM的可再生能源超短期发电功率预测方法[J]. 电力系统自动化, 2021, 45(8): 175-184.
XIE X Y, ZHOU J H, ZHANG Y J, et al.W-BiLSTM based ultra-short-term generation power prediction method of renewable energy[J]. Automation of electric power systems, 2021, 45(8): 175-184.
[18] 吴小刚, 刘宗歧, 田立亭, 等. 基于改进多目标粒子群算法的配电网储能选址定容[J]. 电网技术, 2014, 38(12): 3405-3411.
WU X G, LIU Z Q, TIAN L T, et al.Energy storage device locating and sizing for distribution network based on improved multi-objective particle swarm optimizer[J]. Power system technology, 2014, 38(12): 3405-3411.
[19] VAZIRI J, FARID D, NAZEMI ARDAKANI M, et al.A time-varying stock portfolio selection model based on optimized PSO- BiLSTM and multi-objective mathematical programming under budget constraints[J]. Neural computing and applications, 2023, 35(25): 18445-18470.
基金
河北省自然科学基金（F2021502013）
PDF(2409 KB)
