基于波动特征提取下云层分型的短期光伏发电功率预测方法

张蕊; 李安燚; 刘世岩; 薛世伟; 贾清泉; 巩秦海

doi:10.19912/j.0254-0096.tynxb.2023-1169

PDF(2402 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (11) : 330-342. DOI: 10.19912/j.0254-0096.tynxb.2023-1169

基于波动特征提取下云层分型的短期光伏发电功率预测方法

张蕊^1,2, 李安燚^1,2, 刘世岩^1,2, 薛世伟^1,2, 贾清泉³, 巩秦海³

作者信息 +

A SHORT-TERM PHOTOVOLTAIC POWER GENERATION POWER PREDICTION METHOD BASED ON CLOUD CLASSIFICATION USING WAVE FEATURE EXTRACTION

Zhang Rui^1,2, Li Anyi^1,2, Liu Shiyan^1,2, Xue Shiwei^1,2, Jia Qingquan³, Gong Qinhai³

Author information +

文章历史 +

摘要

短期光伏发电功率的预测精度与天气类型紧密相关,云层的无规则运动导致光伏发电功率波动。因此该文通过监测不同天气类型下云层的运动形态提高预测精度。首先,基于NWP因子将天气划分为5种类型,并通过变分模态分解将光伏发电功率分为平滑过程与波动过程数据。其次,采用云层灰度值判断云层厚度,由加速鲁棒特征（SURF）监测得到云层特征点,跟踪特征点的移动得到云层的运动速度和方向。然后,提出波动特征参数,结合云层运动状态分析波动形态,从而将云层运动状态与波动形态相关联实现“云层分型”。最后,针对平滑数据和波动过程的数据特征,结合机器学习算法自身的适应性条件,提出基于CNN-LSTM的组合预测算法。该算法实现了基于NWP相关因子,以光伏功率历史平滑数据和历史波动数据为输入、以光伏功率预测值为输出的预测方法,显著提高了光伏发电功率的预测精度。

Abstract

The fluctuation of PV power is caused by the irregular movement of cloud, and its fluctuation is closely related to the weather type, which affects the prediction accuracy of short term PV power forecast, the cloud motion pattern improves the prediction accuracy. Firstly, the weather types are divided into 5 types based on NWP factor, and the PV power is divided unsmooth data and fluctuating data by variational mode decomposition. Secondly, the cloud thickness is judged by the cloud gray level, and the use of SURF is to detect the cloud feature points,and the velocity and direction of the cloud are obtained by tracking the movement of the feature points. Then, the wave shape is analyzed by the wave characteristic parameters and the wave data, so that the cloud motion state is related to the wave shape to realize the“cloud classification”. Finally, a combined forecasting algorithm based on CNN-LSTM is proposed according to the characteristics of smooth data and fluctuating pro-cess and the adaptability of machine learning algorithm. Based on the NWP correlation factor,the daily fluctuation process of PV power is taken as input and the daily fluctuation process of PV power is taken as output.

导出引用

张蕊, 李安燚, 刘世岩, 薛世伟, 贾清泉, 巩秦海. 基于波动特征提取下云层分型的短期光伏发电功率预测方法[J]. 太阳能学报. 2024, 45(11): 330-342 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1169

Zhang Rui, Li Anyi, Liu Shiyan, Xue Shiwei, Jia Qingquan, Gong Qinhai. A SHORT-TERM PHOTOVOLTAIC POWER GENERATION POWER PREDICTION METHOD BASED ON CLOUD CLASSIFICATION USING WAVE FEATURE EXTRACTION[J]. Acta Energiae Solaris Sinica. 2024, 45(11): 330-342 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1169

中图分类号： TK514

参考文献

[1] SHENG H M, XIAO J, CHENG Y H, et al.Short-term solar power forecasting based on weighted Gaussian process regression[J]. IEEE transactions on industrial electronics, 2018, 65(1): 300-308.
[2] SANJARI M J, GOOI H B.Probabilistic forecast of PV power generation based on higher order Markov chain[J]. IEEE transactions on power systems, 2017, 32(4): 2942-2952.
[3] 张娜, 葛磊蛟. 基于SOA优化的光伏短期出力区间组合预测[J]. 太阳能学报, 2021, 42(5): 252-259.
ZHANG N, GE L J.Photovoltaic system short-term power interval hybrid forecasting method based on seeker optimization algorithm[J]. Acta energiae solaris sinica, 2021, 42(5): 252-259.
[4] 赵书强, 张婷婷, 李志伟, 等. 基于数值特性聚类的日前光伏出力预测误差分布模型[J]. 电力系统自动化, 2019, 43(13): 36-45.
ZHAO S Q, ZHANG T T, LI Z W, et al.Distribution model of day-ahead photovoltaic power forecasting error based on numerical characteristic clustering[J]. Automation of electric power systems, 2019, 43(13): 36-45.
[5] 李烁, 陈新度, 尹玲, 等. 考虑气象变化的光伏发电模型评估及研究[J]. 太阳能学报, 2022, 43(6): 79-84.
LI S, CHEN X D, YIN L, et al.Evaluation and research of photovoltaic power generation model considering climate change[J]. Acta energiae solaris sinica, 2022, 43(6): 79-84.
[6] FENG Y, HAO W P, LI H R, et al.Machine learning models to quantify and map daily global solar radiation and photovoltaic power[J]. Renewable and sustainable energy reviews, 2020, 118: 109393.
[7] 赵智立. 光伏电站短期功率预测及并网优化技术研究[D]. 天津: 天津理工大学, 2021.
ZHAO Z L.Research on short-term power and forecast grid-connected optimal configuration of photovoltaic power station[D]. Tianjin: Tianjin University of Technology, 2021.
[8] 王育飞, 付玉超, 薛花. 计及太阳辐射和混沌特征提取的光伏发电功率DMCS-WNN预测法[J]. 中国电机工程学报, 2019, 39(增刊1): 63-71.
WANG Y F, FU Y C, XUE H.DMCS-WNN prediction method of photovoltaic power generation by considering solar radiation and chaotic feature extraction[J]. Proceedings of the CSEE, 2019, 39(S1): 63-71.
[9] 谭海旺, 杨启亮, 邢建春, 等. 基于XGBoost-LSTM组合模型的光伏发电功率预测[J]. 太阳能学报, 2022, 43(8): 75-81.
TAN H W, YANG Q L, XING J C, et al.Photovoltaic power predictionP based on combined XGBoost-LSTM model[J]. Acta energiae solaris sinica, 2022, 43(8): 75-81.
[10] YU Y J, CAO J F, ZHU J Y.An LSTM short-term solar irradiance forecasting under complicated weather conditions[J]. IEEE access, 2019, 7: 145651-145666.
[11] YU Y J, CAO J F, WAN X F, et al.Comparison of short-term solar irradiance forecasting methods when weather conditions are complicated[J]. Journal of renewable and sustainable energy, 2018, 10(5): 053501.
[12] 陈志宝, 丁杰, 周海, 等. 地基云图结合径向基函数人工神经网络的光伏功率超短期预测模型[J]. 中国电机工程学报, 2015, 35(3): 561-567.
CHEN Z B, DING J, ZHOU H, et al.A model of very short-term photovoltaic power forecasting based on ground-based cloud images and RBF neural network[J]. Proceedings of the CSEE, 2015, 35(3): 561-567.
[13] WANG F, ZHEN Z, WANG B, et al.Comparative study on KNN and SVM based weather classification models for day ahead short term solar PV power forecasting[J].Applied sciences, 2017, 8(1): 28.
[14] 李燕青, 杜莹莹. 基于最优相似度与IMEA-RBFNN的短期光伏发电功率预测[J]. 华北电力大学学报(自然科学版), 2018, 45(5): 29-35, 61.
LI Y Q, DU Y Y.Short-term photovoltaic power forecasting based on optimal similarity and radial basis function neural networks optimized by improved mind evolutionary algorithm[J]. Journal of North China Electric Power University (natural science edition), 2018, 45(5): 29-35, 61.
[15] ZHEN Z, LIU J M, ZHANG Z Y, et al.Deep learning based surface irradiance mapping model for solar PV power forecasting using sky image[J]. IEEE transactions on industry applications, 2020, 56(4): 3385-3396.
[16] 柴闵康, 夏飞, 张浩, 等. 基于云图特征自识别的光伏超短期预测模型[J]. 电网技术, 2021, 45(3): 1023-1035.
CHAI M K, XIA F, ZHANG H, et al.Ultra-short-term prediction of self-identifying photovoltaic based on sky cloud chart[J]. Power system technology, 2021, 45(3): 1023-1035.
[17] 张琦. 短期光伏发电出力预测方法研究[D]. 广州: 广东工业大学, 2018.
ZHANG Q.Studies on short-term photovoltaic power output prediction method[D]. Guangzhou: Guangdong University of Technology, 2018.
[18] ZHANG J L, TAN Z F, WEI Y M.An adaptive hybrid model for day-ahead photovoltaic output power prediction[J]. Journal of cleaner production, 2020, 244: 118858.
[19] 叶林, 裴铭, 路朋, 等. 基于天气分型的短期光伏功率组合预测方法[J]. 电力系统自动化, 2021, 45(1): 44-54.
YE L, PEI M, LU P, et al.Combination forecasting method of short-term photovoltaic power based on weather classification[J]. Automation of electric power systems, 2021, 45(1): 44-54.
[20] 杨晶显, 张帅, 刘继春, 等. 基于VMD和双重注意力机制LSTM的短期光伏功率预测[J]. 电力系统自动化, 2021, 45(3): 174-182.
YANG J X, ZHANG S, LIU J C, et al.Short-term photovoltaic power prediction based on variational mode decomposition and long shortterm memory with dual-stage attention mechanism[J]. Automation of electric power systems, 2021, 45(3): 174-182.
[21] BEDI J, TOSHNIWAL D.Empirical mode decomposition based deep learning for electricity demand forecasting[J]. IEEE access, 2018, 6: 49144-49156.
[22] JAMAL T, CARTER C, SCHMIDT T, et al.An energy flow simulation tool for incorporating short-term PV forecasting in a diesel-PV-battery off-grid power supply system[J]. Applied energy, 2019, 254: 113718.
[23] 王粟, 江鑫, 曾亮, 等. 基于VMD-DESN-MSGP模型的超短期光伏功率预测[J]. 电网技术, 2020, 44(3): 917-926.
WANG S, JIANG X, ZENG L, et al.Ultra-short-term photovoltaic power prediction based on VMD-DESN-MSGP model[J]. Power system technology, 2020, 44(3): 917-926.
[24] ZHEN Z, PANG S J, WANG F, et al.Pattern classification and PSO optimal weights based sky images cloud motion speed calculation method for solar PV power forecasting[J]. IEEE transactions on industry applications, 2019, 55(4): 3331-3342.
[25] 余光正, 陆柳, 汤波, 等. 基于云图特征提取的改进混合神经网络超短期光伏功率预测方法[J]. 中国电机工程学报, 2021, 41(20): 6989-7003.
YU G Z, LU L, TANG B, et al.An improved hybrid neural network ultra-short-term photovoltaic power forecasting method based on cloud image feature extraction[J]. Proceedings of the CSEE, 2021, 41(20): 6989-7003.
[26] ABDEL-NASSER M, MAHMOUD K.Accurate photovoltaic power forecasting models using deep LSTM-RNN[J]. Neural computing and applications, 2019, 31(7): 2727-2740.
[27] BEHERA M K, NAYAK N.A comparative study on short-term PV power forecasting using decomposition based optimized extreme learning machine algorithm[J]. Engineering science and technology, an international journal, 2020, 23(1): 156-167.
[28] HAN L, ZHANG R C, WANG X S, et al.Multi-step wind power forecast based on VMD-LSTM[J]. IET renewable power generation, 2019, 13(10): 1690-1700.
[29] 纪棋彬. 光伏并网系统短期功率预测方法研究[D]. 镇江: 江苏大学, 2019.
JI Q B.Research on short-term power prediction method for photovoltaic grid-connected system[D]. Zhenjiang: Jiangsu University, 2019.
[30] 朱想, 居蓉蓉, 程序, 等. 组合数值天气预报与地基云图的光伏超短期功率预测模型[J]. 电力系统自动化, 2015, 39(6): 4-10, 74.
ZHU X, JU R R, CHENG X, et al.A very short-term prediction model for photovoltaic power based on numerical weather prediction and ground-based cloud images[J]. Automation of electric power systems, 2015, 39(6): 4-10, 74.