Study of short-term PV power prediction based on ICEEMDAN-LSTM networks under generalized weather classifications

doi:10.3969/j.issn.2097-0706.2024.09.007

Abstract

Abstract:

To alleviate the influence of varied weather and strong randomness on photovoltaic （PV） systems， a short-term PV power prediction method based on improved complete ensemble empirical mode decomposition with adaptive noise （ICEEMDAN） and long short-term memory （LSTM） networks under generalized weather classifications is proposed. Based on the historical irradiance data， different weather conditions are divided into three generalized types by K-means++ clustering algorithm. Then， the PV power data are decomposed into several intrinsic mode functions（IMFs） and residual components of different frequencies by ICEEMDAN， to reduce the non-stationarity of the original sequence. LSTM forecasting models of the modal sequence components under different weather types are established. The trained LSTM models are used to make multi-dimensional prediction on modal components of each decomposed subsequence. The final prediction result is obtained by fusing the results of modal prediction sequences on different layers. The experimental results show that， the PV power prediction of the proposed ICEEMDAN-LSTM hybrid model is more accurate than that of conventional short-term prediction models.

Key words: photovoltaic system, power prediction, generalized weather classification, improved complete ensemble empirical mode decomposition with adaptive noise, long short-term memory network

CLC Number:

TM615：TK519

YUAN Junqiu, WANG Di, XIE Xiaofeng, ZHANG Qianying, CAO Shang, CAO Fei, ZHANG Jingwei. Study of short-term PV power prediction based on ICEEMDAN-LSTM networks under generalized weather classifications[J]. Integrated Intelligent Energy, 2024, 46(9): 53-60.

Figures/Tables 9

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Fig.6

Fig.7

Table 2

References 27

[1]	WEN H R, DU Y, CHEN X Y, et al. A regional solar forecasting approach using generative adversarial networks with solar irradiance maps[J]. Renew Energy, 2023, 216: 119043.
[2]	李军徽, 张嘉辉, 李翠萍, 等. 参与调峰的储能系统配置方案及经济性分析[J]. 电工技术学报, 2021, 36(19): 4148-4160.
	LI Junhui, ZHANG Jiahui, LI Cuiping, et al. Configuration scheme and economic analysis of energy storage system participating in grid peak shaving[J]. Transactions of China Electrotechnical Society, 2021, 36(19): 4148-4160.
[3]	葛俊雄, 蔡国伟, 姜柳, 等. 基于天气变化自适应分型与匹配的分布式光伏短期功率预测方法[J]. 激光与光电子学进展, 2024, 61(15):1-12.
	GE Junxiong, CAI Guowei, JIANG Liu, et al. A method for distributed PV short-term power prediction based onweather change adaptive fractal and matching[J]. Laser Optoelectronics Progress, 2024, 61(15):1-12.
[4]	高寒旭, 袁祖晴, 张淑婷, 等. 基于LSTM模型的短期光伏功率预测[J]. 太阳能学报, 2024, 45(6): 376-381.
	GAO Hanxu, YUAN Zuqing, ZHANG Shuting, et al. Short-term photovoltaic power prediction based on LSTM model[J]. Acta Energiae Solaris Sinica, 2024, 45(6): 376-381.
[5]	杨锡运, 马文兵, 彭琰, 等. 基于组合神经网络的分布式光伏超短期功率预测方法[J]. 热力发电, 2023, 52(8): 162-171.
	YANG Xiyun, MA Wenbing, PENG Yan, et al. Distributed photovoltaic ultra-short-term power prediction method based on combined neural network[J]. Thermal Power Generation, 2023, 52 (8): 162-171.
[6]	CHU Y H, URQUHART B, GOHARI S M I, et al. Short-term reforecasting of power output from a 48 MWe solar PV plant[J]. Solar Energy, 2015, 112: 68-77.
[7]	BOUZERDOUM M, MELLIT A, MASSI PAVAN A. A hybrid model(SARIMA-SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant[J]. Solar Energy, 2013, 98: 226-235.
[8]	LI F Y, ZHENG H F, LI X M, et al. Day-ahead city natural gas load forecasting based on decomposition-fusion technique and diversified ensemble learning model[J]. Applied Energy, 2021, 303: 117623.
[9]	LI Z, YE L, ZHAO Y N, et al. A spatiotemporal directed graph convolution network for ultra-short-term wind power prediction[J]. IEEE Transactions on Sustainable Energy, 2023, 14(1): 39-54.
[10]	FU W L, WANG K, TAN J W, et al. A composite framework coupling multiple feature selection, compound prediction models and novel hybrid swarm optimizer-based synchronization optimization strategy for multi-step ahead short-term wind speed forecasting[J]. Energy Convers Manage, 2020, 205: 112461.
[11]	KAZEM H A, YOUSIF J H. Comparison of prediction methods of photovoltaic power system production using a measured dataset[J]. Energy Convers Manage, 2017, 148: 1070-1081.
[12]	蔡源, 吴浩, 唐丹. 光伏发电功率预测方法综述[J]. 四川电力技术, 2024, 47(2): 25-31.
	CAI Yuan, WU Hao, TANG Dan. Reviews of photovoltaic power prediction methods[J]. Sichuan Electric Power Technology, 2024, 47(2): 25-31.
[13]	刘源延, 孔小兵, 马乐乐, 等. 基于小波包变换与深度学习的超短期光伏功率预测[J]. 太阳能学报, 2024, 45(5): 537-546.
	LIU Yuanyan, KONG Xiaobing, MA Lele, et al. Ultra-short-term photovoltaic power forecasting based on wavelet packet transform and deep learning[J]. Acta Energiae Solaris Sinica, 2024, 45(5): 537-546.
[14]	张永宁, 任晓颖, 张飞, 等. 基于深度学习的光伏功率预测技术[J/OL]. 综合智慧能源, (2024-04-01) [2024-07-23]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240328.2244.002.html.
	ZHANG Yongning, REN Xiaoying, ZHANG Fei, et al. Deep learning based photovoltaic power prediction technology[J/OL]. Integrated Intelligent Energy,(2024-04-01) [2024-07-23]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240328.2244.002.html.
[15]	郑真, 朱峰, 马小丽, 等. 基于TL-LSTM的新能源功率短期预测[J]. 综合智慧能源, 2023, 45(1): 41-48. doi: 10.3969/j.issn.2097-0706.2023.01.005
	ZHENG Zhen, ZHU Feng, MA Xiaoli, et al. Short-term new energy power prediction based on TL-LSTM[J]. Integrated Intelligent Energy, 2023, 45(1): 41-48. doi: 10.3969/j.issn.2097-0706.2023.01.005
[16]	李博涵. 基于相似时和LSTM神经网络的短期光伏功率预测[D]. 南宁: 广西大学, 2020.
	LI Bohan. Short-term photovoltaic power prediction based on similar time and LSTM neural network[D]. Nanning: Guangxi University, 2020.
[17]	王守相, 张娜. 基于灰色神经网络组合模型的光伏短期出力预测[J]. 电力系统自动化, 2012, 36(19): 37-41.
	WANG Shouxiang, ZHANG Na. Short-term output power forecast of photovoltaic based on a grey and neural network hybrid model[J]. Automation of Electric Power Systems, 2012, 36(19): 37-41.
[18]	朱玥, 顾洁, 孟璐. 基于EMD-LSTM的光伏发电预测模型[J]. 电力工程技术, 2020, 39(2): 51-58.
	ZHU Yue, GU Jie, MENG Lu. Photovoltaic power generation prediction model based on EMD-LSTM[J]. Electric Power Engineering Technology, 2020, 39(2): 51-58.
[19]	王鑫, 李慧, 叶林, 等. 考虑风速波动特性的VMD-GRU 短期风电功率预测[J]. 电力科学与技术学报, 2021, 36(4): 20-28.
	WANG Xin, LI Hui, YE Lin, et al. VMD-GRU based short-term wind power forecast considering wind speed fluctuation characteristics[J]. Journal of Electric Power Science and Technology, 2021, 36(4): 20-28.
[20]	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.
[21]	金吉, 王斌, 喻敏, 等. 基于分形特征的自适应EEMD 及其在风功率预测中的应用[J]. 太阳能学报, 2023, 44(5): 416-424. doi: 10.19912/j.0254-0096.tynxb.2022-0039
	JIN Ji, WANG Bin, YU Min, et al. Adaptive eemd on basis of fraction characteristics and its application on wind power forecasting[J]. Acta Energiae Solaris Sinica, 2023, 44(5): 416-424. doi: 10.19912/j.0254-0096.tynxb.2022-0039
[22]	LI P T, ZHOU K K, LU X H, et al. A hybrid deep learning model for short-term PV power forecasting[J]. Applied Energy, 2020, 259: 114216.
[23]	王晓东, 苗宜之, 刘颖明, 等. 基于多分解策略和误差校正的超短期风电功率混合智能预测算法[J]. 太阳能学报, 2021, 42(6): 312-320.
	WANG Xiaodong, MIAO Yizhi, LIU Yingming, et al. Hybrid intelligent prediction algorithm of ultra-short-term wind power based on multi-decomposition strategy and error correction[J]. Acta Energiae Solaris Sinica, 2021, 42(6): 312-320.
[24]	GAO M M, LI J J, HONG F, et al. Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM[J]. Energy, 2019, 187: 115838.
[25]	卢忠山, 袁建华. 基于EEMD-LSTM方法的光伏发电系统超短期功率预测[J]. 中国测试, 2022, 48(12): 125-132.
	LU Zhongshan, YUAN Jianhua. Ultra-short term power prediction of photovoltaic power generation system based on EEMD-LSTM method[J]. China Measurement and Test, 2022, 48(12): 125-132.
[26]	王飞, 米增强, 甄钊, 等. 基于天气状态模式识别的光伏电站发电功率分类预测方法[J]. 中国电机工程学报, 2013, 33(34): 75-82.
	WANG Fei, MI Zengqiang, ZHEN Zhao, et al. A classified forecasting approach of power generation for photovoltaic plants based on weather condition pattern recognition[J]. Proceedings of the CSEE, 2013, 33(34): 75-82.
[27]	孙辉, 冷建伟. 基于改进的Semi Boost天气聚类的CC-PSO-DBN短期光伏发电预测[J]. 计算机应用与软件, 2020, 37(8): 103-109.
	SUN Hui, LENG Jianwei. CC-PSO-DBN short-term photovoltaic power generation forecasting based on improved Semi Boost weather clustering[J]. Computer Applications and Software, 2020, 37(8): 103-109.

模型	广义天气类型Ⅰ	广义天气类型Ⅱ	广义天气类型Ⅲ
ICEEMDAN-LSTM	0.116	0.324	0.582
BPNN	0.136	0.511	0.684
KELM	0.180	0.556	0.578