Pattern Recognition and Ultra-Short-Term Probabilistic Forecasting of Power Fluctuating in Aggregated Distributed Photovoltaics Clusters

doi:10.16183/j.cnki.jsjtu.2023.048

Abstract

Abstract:

The quantitative evaluation of the uncertainty in distributed photovoltaic power is significant for the safe and stable operation of distribution network. Considering the significant differences in power characteristics of different output fluctuation patterns, in order to obtain a prediction model suitable for different fluctuation patterns and to perform a refined assessment of power uncertainty, this paper proposes a method for pattern recognition and ultra-short-term probabilistic forecasting of power fluctuating in aggregated distributed photovoltaic clusters. First, the satellite cloud images and photovoltaic power data are integrated, and the pattern recognition model of fluctuation is constructed via the feature extraction of power fluctuation, realizing the mining of fluctuation rules. On this basis, the difference in predictability of different fluctuation patterns and the correlation between fluctuation patterns and prediction errors are considered via classification modeling, so that the width of prediction interval can better adapt to the characteristics of prediction error distribution. Thus, refined consideration of power uncertainty of different fluctuation patterns is realized to improve the precision of probabilistic prediction, provide more references for power grid dispatching, and weaken the influence of the strong volatility in distributed photovoltaic power on the power system.

Key words: distributed photovoltaic, power forecasting, deep learning, pattern recognition, probabilistic forecasting

CLC Number:

TM732

WANG Yubo, HAO Ling, XU Fei, CHEN Wenbin, ZHENG Libin, CHEN Lei, MIN Yong. Pattern Recognition and Ultra-Short-Term Probabilistic Forecasting of Power Fluctuating in Aggregated Distributed Photovoltaics Clusters[J]. Journal of Shanghai Jiao Tong University, 2024, 58(9): 1334-1343.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Tab.1

Tab.2

Tab.3

References 26

[1]	WANG F, ZHEN Z, LIU C, et al. Image phase shift invariance based cloud motion displacement vector calculation method for ultra-short-term solar PV power forecasting[J]. Energy Conversion & Management, 2018, 157: 123-135.
[2]	WANG F, ZHANG Z Y, LIU C, et al. Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting[J]. Energy Conversion & Management, 2019, 181: 443-462.
[3]	王洪坤, 葛磊蛟, 李宏伟, 等. 分布式光伏发电的特性分析与预测方法综述[J]. 电力建设, 2017, 38(7): 1-9. doi: 10.3969/j.issn.1000-7229.2017.07.001
	WANG Hongkun, GE Leijiao, LI Hongwei, et al. A review on characteristic analysis and prediction method of distributed PV[J]. Electric Power Construction, 2017, 38(7): 1-9. doi: 10.3969/j.issn.1000-7229.2017.07.001
[4]	王春平. 基于光伏功率预测的分布式能源系统优化[D]. 上海: 上海交通大学, 2020.
	WANG Chunping. Distributed energy system optimization based on photovoltaic power prediction[D]. Shanghai: Shanghai Jiao Tong University, 2020.
[5]	廖启术, 胡维昊, 曹迪, 等. 新能源电力系统中的分布式光伏净负荷预测[J]. 上海交通大学学报, 2021, 55(12): 1520-1531. doi: 10.16183/j.cnki.jsjtu.2021.244
	LIAO Qishu, HU Weihao, CAO Di, et al. Distributed photovoltaic net load forecasting in new energy power systems[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1520-1531.
[6]	SAINT-DRENAN Y M, GOOD G H, BRAUN M, et al. Analysis of the uncertainty in the estimates of regional PV power generation evaluated with the upscaling method[J]. Solar Energy, 2016, 135: 536-550.
[7]	KUSHWAHA V, PINDORIYA N M. A SARIMA-RVFL hybrid model assisted by wavelet decomposition for very short-term solar PV power generation forecast[J]. Renewable Energy, 2019, 140: 124-139.
[8]	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.
[9]	王彪, 吕洋, 陈中, 等. 考虑信息时移的分布式光伏机理-数据混合驱动短期功率预测[J]. 电力系统自动化, 2022, 46(11): 67-74.
	WANG Biao, LYU Yang, CHEN Zhong, et al. Hybrid mechanism-data-driven short-term power forecasting of distributed photovoltaic considering information time shift[J]. Automation of Electric Power Systems, 2022, 46(11): 67-74.
[10]	WANG K J, QI X X, LIU H D. Photovoltaic power forecasting based LSTM-convolutional network[J]. Energy, 2019, 189: 116225.
[11]	ALMONACID F, RUS C, PÉREZ-HIGUERAS P, et al. Calculation of the energy provided by a PV generator. Comparative study: Conventional methods vs. artificial neural networks[J]. Energy, 2011, 36(1): 375-384.
[12]	李丰君, 王磊, 赵健, 等. 基于天气融合和LSTM网络的分布式光伏短期功率预测方法[J]. 中国电力, 2022, 55(11): 149-154.
	LI Fengjun, WANG Lei, ZHAO Jian, et al. Research on distributed photovoltaic short-term power prediction method based on weather fusion and LSTM-net[J]. Electric Power, 2022, 55(11): 149-154.
[13]	郑若楠, 李国杰, 韩蓓, 等. 基于加权扩展日特征矩阵的分布式光伏发电日前功率预测[J]. 电力自动化设备, 2022, 42(2): 99-105.
	ZHENG Ruonan, LI Guojie, HAN Bei, et al. Day-ahead power forecasting of distributed photovoltaic generation based on weighted expanded daily feature matrix[J]. Electric Power Automation Equipment, 2022, 42(2): 99-105.
[14]	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 Kaiyan, DU Haodong, JIA Rong, 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.
[15]	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.
	XU Biao, XU Qingshan, HUANG Yu, et al. Day-ahead probabilistic forecasting of photovoltaic power based on vine copula quantile regression[J]. Power System Technology, 2021, 45(11): 4426-4435.
[16]	赵康宁, 蒲天骄, 王新迎, 等. 基于改进贝叶斯神经网络的光伏出力概率预测[J]. 电网技术, 2019, 43(12): 4377-4386.
	ZHAO Kangning, PU Tianjiao, WANG Xinying. et al. Probabilistic forecasting for photovoltaic power based on improved Bayesian neural network[J]. Power System Technology, 2019, 43(12): 4377-4386.
[17]	王继东, 冉冉, 宋智林. 基于改进深度受限玻尔兹曼机算法的光伏发电短期功率概率预测[J]. 电力自动化设备, 2018, 38(5): 43-49.
	WANG Jidong, RAN Ran, SONG Zhilin. Probability forecast of short-term photovoltaic power generation based on improved depth restricted Boltzmann machine algorithm[J]. Electric Power Automation Equipment, 2018, 38(5): 43-49.
[18]	程泽, 刘冲, 刘力. 基于相似时刻的光伏出力概率分布估计方法[J]. 电网技术, 2017, 41(2): 448-455.
	CHENG Ze, LIU Chong, LIU Li. A method of probabilistic distribution estimation of PV generation based on similar time of day[J]. Power System Technology, 2017, 41(2): 448-455.
[19]	李芬, 周尔畅, 孙改平, 等. 一种新型天气分型方法及其在光伏功率预测中的应用[J]. 上海交通大学学报, 2021, 55(12): 1510-1519. doi: 10.16183/j.cnki.jsjtu.2021.264
	LI Fen, ZHOU Erchang, SUN Gaiping, et al. A novel weather classification method and its application in photovoltaic power prediction[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1510-1519.
[20]	吉锌格, 李慧, 叶林, 等. 基于波动特性挖掘的短期光伏功率预测[J]. 太阳能学报, 2022, 43(5): 146-155. doi: 10.19912/j.0254-0096.tynxb.2020-0961
	JI Xinge, LI Hui, YE Lin, et al. Short-term photovoltaic power forecasting based on fluctuation characteristics mining[J]. Acta Energiae Solaris Sinica, 2022, 43(5): 146-155. doi: 10.19912/j.0254-0096.tynxb.2020-0961
[21]	何之倬, 张颖, 郑刚, 等. 基于极限学习机模型参数优化的光伏功率区间预测技术[J]. 上海交通大学学报, 2024, 58(3): 285-294. doi: 10.16183/j.cnki.jsjtu.2022.338
	HE Zhizhuo, ZHANG Ying, ZHENG Gang, et al. Interval prediction technology of photovoltaic power based on parameter optimization of extreme learning machine[J]. Journal of Shanghai Jiao Tong University, 2024, 58(3): 285-294.
[22]	WANG F, MI Z Q, SU S, et al. Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters[J]. Energies, 2012, 5(5): 1355-1370.
[23]	吕伟杰, 方一帆, 程泽. 基于模糊C均值聚类和样本加权卷积神经网络的日前光伏出力预测研究[J]. 电网技术, 2022, 46(1): 231-238.
	LÜ Weijie, FANG Yifan, CHENG Ze, et al. Prediction of day-ahead photovoltaic output based on FCM-WS-CNN[J]. Power System Technology, 2022, 46(1): 231-238.
[24]	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 Zhibao, DING Jie, ZHOU Hai, 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.
[25]	纪德洋, 金锋, 冬雷, 等. 基于皮尔逊相关系数的光伏电站数据修复[J]. 中国电机工程学报, 2022, 42(4): 1514-1523.
	JI Deyang, JIN Feng, DONG Lei, et al. Data repairing of photovoltaic power plant based on pearson correlation coefficient[J]. Proceedings of the CSEE, 2022, 42(4): 1514-1523.
[26]	王蔚卿. 基于波动过程模式识别的风速超短期预测模型[D]. 保定: 华北电力大学, 2020.
	WANG Weiqing. An ultra-short-term wind speed forecasting model based on fluctuation process pattern recognition[D]. Baoding: North China Electric Power University, 2020.

时间尺度	模型	e_ACE/%	δ_mean/MW	S/MW
15 min	原始模型	2.91	125.60	-31.29
15 min	所提模型	5.18	103.47	-12.04
1 h	原始模型	-2.42	147.33	-48.49
1 h	所提模型	1.35	120.94	-29.26
2 h	原始模型	-6.37	174.61	-74.86
2 h	所提模型	-2.38	139.78	-56.25
4 h	原始模型	-12.41	191.38	-162.94
4 h	所提模型	-7.96	154.72	-128.18

置信度/%	模型	e_ACE/%	δ_mean/MW	S/MW
99	原始模型	-5.46	367.37	-41.11
99	所提模型	-5.06	275.59	-24.20
95	原始模型	-8.28	241.42	-112.88
95	所提模型	-7.11	183.08	-83.96
90	原始模型	-12.41	191.38	-162.94
90	所提模型	-7.96	154.72	-128.18
85	原始模型	-16.50	124.22	-192.93
85	所提模型	-11.03	93.85	-149.71

模型	e_ACE/%	δ_mean/ MW	S/MW
LSTM	-12.41	191.38	-162.94
LSTM+DWT	-9.56	167.94	-139.90
LSTM+WPD	-9.10	166.58	-137.73
LSTM+EMD	-9.33	165.81	-136.78
LSTM+VMD	-8.91	160.42	-131.77
LSTM+PR	-7.96	154.72	-128.18