基于TDE-SO-AWM-GRU的光伏发电功率预测模型

doi:10.11930/j.issn.1004-9649.202401015

摘要/Abstract

摘要：

精确预测光伏发电功率对电网的安全与经济运行具有重要的意义，但因光伏发电具有时序性、间歇性、波动性以及高非线性等特征，难以深度挖掘数据隐含信息。针对此类问题，提出了一种基于结合时变数据增强（time-varying data enhancement，TDE）、蛇优化算法（snake optimizer，SO）、自适应权重模块（adaptive weight module，AWM）和门控循环单元（gated-recurrent unit，GRU）的光伏发电功率预测模型，通过强相关TDE提升数据特征的表现力，并构造全新的输入矩阵，然后利用AWM对增强后的输入矩阵进行自动赋权处理进入GRU进行预测，同时考虑到组合模型超参数选择困难的问题，引入SO对模型的最佳阈值进行寻找以发挥模型最大性能。最后，使用某光伏发电站实际数据对模型进行验证，结果表明：所提模型可有效提升光伏发电功率的预测精度。

关键词: 光伏功率预测, 数据增强, 自适应权重模块, 蛇优化算法

Abstract:

Accurate prediction of photovoltaic (PV) power is of great significance for the safe and economic operation of power grids, but PV power generation is characterized by time-varying, intermittent, fluctuating, and high nonlinearity characteristics due to the combined effects of multiple meteorological factors, which makes it difficult to deeply explore the implicit information of the data. To solve such problems, a PV power prediction model based on time-varying data enhancement (TDE), snake optimizer (SO), adaptive weight module (AWM), and gated recurrent unit (GRU) was proposed. The expression of data features was improved by TDE with strong correlation, and a new input matrix was constructed. Then, the enhanced input matrix was automatically weighted by AWM and entered into GRU for prediction. At the same time, by considering the difficulty of hyperparameter selection of the combined model, SO was introduced to find the optimal threshold of the model to maximize the performance of the model. Finally, the model was validated using actual data from a PV power station, and the results show that the proposed model can effectively improve the prediction accuracy of PV power.

Key words: photovoltaic power prediction, data enhancement, adaptive weight module, snake optimizer

李翰章, 冯江涛, 王鹏程, 荣澔洁, 柴宇唤. 基于TDE-SO-AWM-GRU的光伏发电功率预测模型[J]. 中国电力, 2024, 57(12): 41-49.

Hanzhang LI, Jiangtao FENG, Pengcheng WANG, Haojie RONG, Yuhuan CHAI. Photovoltaic Power Prediction Model Based on TDE-SO-AWM-GRU[J]. Electric Power, 2024, 57(12): 41-49.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202401015

https://www.electricpower.com.cn/CN/Y2024/V57/I12/41

图/表 15

图 1 原始输入矩阵处理流程

Fig.1 Processing flowchart of initial input matrix

表 1 各气象因素幅值变化划分标准

Table 1 Classification criteria for change of amplitude of each meteorological factor

幅度	辐照度幅值变化/ (W·m^–2·(15 min)^–1)	湿度幅值变化/ (%·(15 min)^–1)	温度幅值变化/ (℃·(15 min)^–1)
低幅	[0, 80)	[0, 0.8)	[0, 0.3)
中幅	[80, 250)	[0.8, 2.5)	[0.3, 0.8)
高幅	[250, 500)	[2.5, 4)	[0.8, 1.4)
剧幅	≥500	≥4	≥1.4

图 2 各气象因素随季节变化幅值构成

Fig.2 Amplitude of each meteorological factor varying with season

图 3 自适应权重模块

Fig.3 AWM

图 4 门控循环单元

Fig.4 GRU

图 5 AWM-GRU网络整体结构

Fig.5 Overall structure of AWM-GRU network

图 6 SO-AWM-GRU预测模型建立流程

Fig.6 Establishment of SO-AWM-GRU prediction model

图 7 实际数据处理过程

Fig.7 Processing process of actual data

表 2 稳定型天气实验结果对比

Table 2 Comparison of results from stable weather experiments

模型类型	E_MA/MW	E_RMS/MW
LSTM	2.1256	2.4432
GRU	2.0154	2.3839
TDE-LSTM	1.9362	2.3153
TDE-GRU	1.7780	2.0830
CNN-GRU	1.5859	1.7874
Attention-GRU	1.3632	1.5981
TDE-SO-AWM-LSTM	1.4763	1.6992
TDE-SO-AWM-GRU	1.0490	1.1828

表 3 突变型天气实验结果对比

Table 3 Comparison of results from mutant weather experiments

模型类型	E_MA/MW	E_RMS/MW
LSTM	2.8256	3.4832
GRU	2.6994	3.3379
TDE-LSTM	2.3950	3.1100
TDE-GRU	2.2350	2.8890
CNN-GRU	2.1426	2.7364
Attention-GRU	1.9785	2.4658
TDE-SO-AWM-LSTM	2.0060	2.5964
TDE-SO-AWM-GRU	1.7563	2.3147

图 8 LSTM与TDE-LSTM预测误差带对比

Fig.8 Comparison of LSTM and TDE-LSTM prediction error bands

图 9 GRU与TDE-GRU预测误差带对比

Fig.9 Comparison of GRU and TDE-GRU prediction error bands

图 10 蛇优化算法适应度曲线

Fig.10 Fitness curve of SO

图 11 稳定型天气预测结果对比

Fig.11 Comparison of results from stable weather prediction

图 12 突变型天气预测结果对比

Fig.12 Comparison of results from mutant weather prediction

参考文献 27

1	程启明, 徐聪, 程尹曼, 等. 基于混合储能技术的光储式充电站直流微网系统协调控制[J]. 高电压技术, 2016, 42 (7): 2073- 2083.
	CHENG Qiming, XU Cong, CHENG Yinman, et al. Coordination control of PV charging station DC microgrid system based on hybrid energy storage technology[J]. High Voltage Engineering, 2016, 42 (7): 2073- 2083.
2	时珊珊, 魏新迟, 张宇, 等. 考虑多模式融合的光储充电站储能系统优化运行策略[J]. 中国电力, 2023, 56 (3): 144- 153, 161.
	SHI Shanshan, WEI Xinchi, ZHANG Yu, et al. Optimal operation strategy of energy storage system in photovoltaic-storage charging station considering multi-mode integration[J]. Electric Power, 2023, 56 (3): 144- 153, 161.
3	马覃峰, 安甦, 刘明顺, 等. 光储系统电网侧故障下VSC变流器的跟网-构网型控制方法[J]. 广东电力, 2023, 36 (12): 47- 56.
	MA Qinfeng, AN Su, LIU Mingshun, et al. Control methods of VSC converters for frid-following/forming operation under grid-side faults in PV energy storage systems[J]. Guangdong Electric Power, 2023, 36 (12): 47- 56.
4	郭洪武, 车建峰, 闫钇汛, 等. 基于无爬坡事件定义标准晴空集的短期光伏功率预测[J]. 中国电力, 2023, 56 (9): 187- 195.
	GUO Hongwu, CHE Jianfeng , YAN Yixun, et al. Short-term photovoltaic power prediction based on standard clear sky set defined by no climbing event[J]. Electric Power, 2023, 56 (9): 187- 195.
5	刘晓艳, 王珏, 姚铁锤, 等. 基于卫星遥感的超短期分布式光伏功率预测[J]. 电工技术学报, 2022, 37 (7): 1800- 1809.
	LIU Xiaoyan, WANG Jue, YAO Tiechui, et al. Ultra short-term distributed photovoltaic power prediction based on satellite remote sensing[J]. Transactions of China Electrotechnical Society, 2022, 37 (7): 1800- 1809.
6	钱振, 蔡世波, 顾宇庆, 等. 光伏发电功率预测方法研究综述[J]. 机电工程, 2015, 32 (5): 651- 659.
	QIAN Zhen, CAI Shibo, GU Yuqing, et al. Review of PV power generation prediction[J]. Journal of Mechanical & Electrical Engineering, 2015, 32 (5): 651- 659.
7	陈炜, 艾欣, 吴涛, 等. 光伏并网发电系统对电网的影响研究综述[J]. 电力自动化设备, 2013, 33 (2): 26- 32, 39. DOI
	CHEN Wei, AI Xin, WU Tao, et al. Influence of grid-connected photovoltaic system on power network[J]. Electric Power Automation Equipment, 2013, 33 (2): 26- 32, 39. DOI
8	邱建, 张建新, 朱煜昆, 等. 光伏并网稳定控制系统设计方法及其在南方电网的应用与实践[J]. 南方电网技术, 2024, 18 (7): 139- 147.
	QIU Jian, ZHANG Jianxin, ZHUN Yikun, et al. Design method of stability control system for photovoltaic grid-connected station and its application and practice in CSG[J]. Southern Power System Technology, 2024, 18 (7): 139- 147.
9	解振学, 林帆, 王若谷, 等. 基于时序动态回归的超短期光伏发电功率预测方法[J]. 智慧电力, 2022, 50 (7): 45- 51.
	XIE Zhenxue, LIN Fan, WANG Ruogu, et al. Very short-term photovoltaic power forecasting method based on time series dynamic regression[J]. Smart Power, 2022, 50 (7): 45- 51.
10	王鹏翔, 沈娟, 王菁旸, 等. 基于PCA-LMD-WOA-ELM的短期光伏功率预测[J]. 智慧电力, 2022, 50 (6): 72- 78.
	WANG Pengxiang, SHEN Juan, WANG Jiangyang, et al. Short term photovoltaic power prediction based on PCA-LMD-WOA-ELM[J]. Smart Power, 2022, 50 (6): 72- 78.
11	MILAD H S A, FAROOQ U, EL-HAWARY M E, et al. Neo-fuzzy integrated adaptive decayed brain emotional learning network for online time series prediction[J]. IEEE Access, 1037, 5, 1037- 1049.
12	ZHANG W Y, LI Q W, HE Q F. Application of machine learning methods in photovoltaic output power prediction: a review[J]. 2022, 14(2): 022701.
13	DATTA S, BAUL A, SARKER G C, et al. A comprehensive review of the application of machine learning in fabrication and implementation of photovoltaic systems[J]. IEEE Access, 2023, 11, 77750- 77778. DOI
14	吴硕. 光伏发电系统功率预测方法研究综述[J]. 热能动力工程, 2021, 36 (8): 1- 7.
	WU Shuo. Review of power forecasting methods of photovoltaic power generation system[J]. Journal of Engineering for Thermal Energy and Power, 2021, 36 (8): 1- 7.
15	董存, 王铮, 白捷予, 等. 光伏发电功率超短期预测方法综述[J]. 高电压技术, 2023, 49 (7): 2938- 2951.
	DONG Cun, WANG Zheng, BAI Jieyu, et al. Review of ultra-short-term forecasting methods for photovoltaic power generation[J]. High Voltage Engineering, 2023, 49 (7): 2938- 2951.
16	MELLIT A, MASSI PAVAN A, OGLIARI E, et al. Advanced methods for photovoltaic output power forecasting: a review[J]. Applied Sciences, 2020, 10 (2): 487. DOI
17	孟安波, 许炫淙, 陈嘉铭, 等. 基于强化学习和组合式深度学习模型的超短期光伏功率预测[J]. 电网技术, 2021, 45 (12): 4721- 4728.
	MENG Anbo, XU Xuancong, CHEN Jiaming, et al. Ultra short term photovoltaic power prediction based on reinforcement learning and combined deep learning model[J]. Power System Technology, 2021, 45 (12): 4721- 4728.
18	ROSATO A, ALTILIO R, ARANEO R, et al. Prediction in photovoltaic power by neural networks[J]. Energies, 2017, 10 (7): 1003. DOI
19	朱琼锋, 李家腾, 乔骥, 等. 人工智能技术在新能源功率预测的应用及展望[J]. 中国电机工程学报, 2023, 43 (8): 3027- 3048.
	ZHU Qiongfeng, LI Jiateng, QIAO Ji, et al. Application and prospect of artificial intelligence technology in renewable energy forecasting[J]. Proceedings of the CSEE, 2023, 43 (8): 3027- 3048.
20	张佳伟, 张自嘉. 基于PSO-BP神经网络的短期光伏系统发电预测[J]. 可再生能源, 2012, 30 (8): 28- 32.
	ZHANG Jiawei, ZHANG Zijia. Short-term photovoltaic system power forecasting based on PSO-BP neural network[J]. Renewable Energy Resources, 2012, 30 (8): 28- 32.
21	谢少华, 何山, 闫学勤, 等. 基于SSA-BP神经网络的光伏短期功率预测[J]. 浙江工业大学学报, 2022, 50 (6): 628- 633. DOI
	XIE Shaohua, HE Shan, YAN Xueqin, et al. Short term photovoltaic power prediction based on SSA-BP neural network[J]. Journal of Zhejiang University of Technology, 2022, 50 (6): 628- 633. DOI
22	宋绍剑, 李博涵. 基于LSTM网络的光伏发电功率短期预测方法的研究[J]. 可再生能源, 2021, 39 (5): 594- 602. DOI
	SONG Shaojian, LI Bohan. Short-term forecasting method of photovoltaic power based on LSTM[J]. Renewable Energy Resources, 2021, 39 (5): 594- 602. DOI
23	刘国海, 孙文卿, 吴振飞, 等. 基于Attention-GRU的短期光伏发电功率预测[J]. 太阳能学报, 2022, 43 (2): 226- 232.
	LIU Guohai, SUN Wenqing, WU Zhenfei, et al. Short-term photovoltaic power forecasting based on Attention-GRU model[J]. Acta Energiae Solaris Sinica, 2022, 43 (2): 226- 232.
24	靳果, 朱清智, 闫奇. 基于PCA和ML-ELM-AE的短期光伏功率预测[J]. 控制工程, 2021, 28 (9): 1787- 1796.
	JIN Guo, ZHU Qingzhi, YAN Qi. Short-term photovoltaic power prediction based on PCA and ML-ELM-AE[J]. Control Engineering of China, 2021, 28 (9): 1787- 1796.
25	WANG J Z, YU Y, ZENG B, et al. Hybrid ultra-short-term PV power forecasting system for deterministic forecasting and uncertainty analysis[J]. Energy, 2024, 288, 129898. DOI
26	KHAN Z A, HUSSAIN T, BAIK S W. Dual stream network with attention mechanism for photovoltaic power forecasting[J]. Applied Energy, 2023, 338, 120916. DOI
27	HASHIM F A, HUSSIEN A G. Snake optimizer: a novel meta-heuristic optimization algorithm[J]. Knowledge-Based Systems, 2022, 242, 108320. DOI

[1]	战文华, 车建峰, 王勃, 丁禹. 基于网格化数值天气预报的区域光伏发电多输出功率预测方法[J]. 中国电力, 2024, 57(3): 144-151.
[2]	张娜, 任强, 刘广忱, 郭力萍, 李静宇. 基于VMD-GWO-ELMAN的光伏功率短期预测方法[J]. 中国电力, 2022, 55(5): 57-65.
[3]	周艳真, 查显煜, 兰健, 郭庆来, 孙宏斌, 薛峰, 王胜明. 基于数据增强和深度残差网络的电力系统暂态稳定预测[J]. 中国电力, 2020, 53(1): 22-31.
[4]	梁适春, 张晓冬, 林培峰, 牛萌. 一种混合储能光伏发电系统的功率预测算法[J]. 中国电力, 2014, 47(3): 24-27.