基于灰色关联分析和GeoMAN模型的光伏发电功率短期预测

doi:10.19595/j.cnki.1000-6753.tces.200538

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1082 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要

准确预测光伏发电功率对电网调度具有十分重要的意义。该文提出一种基于灰色关联分析和GeoMAN模型的光伏发电功率短期预测方法。首先,利用灰色关联分析对某地区多光伏电站进行空间相关性分析,选取与待预测光伏电站高度相关的周边电站;然后,基于GeoMAN模型动态提取待预测光伏电站的时空特征和外部气象因素,GeoMAN模型采用编解码结构,利用编码器动态提取待预测光伏电站的站内特征和与周边相关电站的站间空间特征,利用解码器提取输入变量的时间特性,并融合晴空指数和数值天气预报动态输出光伏发电预测功率;最后,采用实际光伏电站进行案例分析,结果表明该文所提出的预测方法与传统LSTM模型相比,实现了更高精度的光伏发电功率短期预测。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：光伏功率短期预测, 灰色关联分析, GeoMAN, 模型, 时空相关性, 注意力机制

Abstract：

Accurateforecast of photovoltaic (PV) power is important for power system dispatch. A new short-term PV power forecastingmethod is proposed based on grey relational analysis andGeoMAN model. Firstly, grey relational analysis is utilized to analyze spatial correlation among multiple PV stations. And several surrounding PV stations highly related with the target PV station are selected. Then, GeoMAN model is established for dynamically extracting the spatiotemporal feature and external meteorological factors. GeoMAN model adopts encoder and decoder structure. The encoderis utilized to dynamically extract the intra-station feature of the target station and the inter-station spatial feature with the related stations. The decoder is utilized to extract the time feature of input variables. Clearness index and numerical weather prediction (NWP) are finally integrated for short-term PV power forecast. A case study is conducted using data collected from practical PV stations. Study results indicate that the proposed method can achieve higher accuracy compared with long short-term memory (LSTM) model.

Key words： Short-term PV power forecast grey relational analysis GeoMANmodel spatiotemporal correlation attentional mechanism

收稿日期: 2020-05-25

PACS:

TM615

基金资助:

国家电网河北电力有限公司科技项目资助（kj2019-077）

通讯作者: 王珏,男,1981年生,博士,研究生导师,研究方向为人工智能算法与应用软件、高性能计算。E-mail：wangjue@cnic.cn

作者简介: 时珉,男,1976年生,本科,高级工程师,研究方向为电力系统运行与控制、可再生能源发电系统。E-mail：shimin9999@126.com

引用本文:

时珉, 许可, 王珏, 尹瑞, 张沛. 基于灰色关联分析和GeoMAN模型的光伏发电功率短期预测[J]. 电工技术学报, 2021, 36(11): 2298-2305. Shi Min, Wang Jue, Yin Rui, Zhang Pei. Short-Term Photovoltaic Power Forecast Basedon Grey Relational Analysis and GeoMANModel. Transactions of China Electrotechnical Society, 2021, 36(11): 2298-2305.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.200538 https://dgjsxb.ces-transaction.com/CN/Y2021/V36/I11/2298

[1] 赖昌伟, 黎静华, 陈博, 等. 光伏发电出力预测技术研究综述[J]. 电工技术学报, 2019, 34(6): 1201-1217.
Lai Changwei, Li Jinghua, Chen Bo, et al.Review of photovoltaic power output prediction technology[J]. Transactions of China Electrotechnical Society, 2019, 34(6): 1201-1217.
[2] 张雨曼, 刘学智, 严正, 等. 光伏-储能-热电联产综合能源系统分解协调优化运行研究[J]. 电工技术学报, 2020, 35(11): 2372-2386.
Zhang Yuman, Liu Xuezhi, Yan Zheng, et al.Decomposition-coordination based optimization for PV-BESS-CHP integrated energy systems[J]. Transactions of China Electrotechnical Society, 2020, 35(11): 2372-2386.
[3] He Hui, Hu Ran, Zhang Yaning, et al.A power forecasting approach for PV plant based on irradiance index and LSTM[C]//Proceedings of the 37th Chinese Control Conference, Wuhan, China, 2018: 9404-9409.
[4] 黄磊, 舒杰, 姜桂秀, 等. 基于多维时间序列局部支持向量回归的微网光伏发电预测[J]. 电力系统自动化, 2014, 38(5): 19-24.
Huang Lei, ShuJie, Jiang Guixiu, et al. Photovoltaic generation forecast based on multidimensional time-series and local support vector regression in microgrids[J]. Automation of Electric Power Systems, 2014, 38(5): 19-24.
[5] 赵滨滨, 王莹, 王彬, 等. 基于ARIMA时间序列的分布式光伏系统输出功率预测方法研究[J]. 可再生能源, 2019, 37(6): 820-823.
Zhao Binbin, Wang Ying, Wang Bin, et al.Research on output power forecast method of distributed photovoltaic system based on ARIMA time series[J]. Renewable Energy, 2019, 37(6): 820-823.
[6] 焦田利, 章坚民, 李熊,等. 基于空间相关性的大规模分布式用户光伏空间分群方法[J]. 电力系统自动化, 2019, 43(21): 97-105, 162.
Jiao Tianli, Zhang Jianmin, Li Xiong, et al.Spatial clustering method for large-scale distributed user photovoltaics based on spatial correlation[J]. Automation of Electric Power Systems, 2019, 43(21): 97-105, 162.
[7] 于若英, 陈宁, 苗淼, 等. 考虑天气和空间相关性的光伏电站输出功率修复方法[J]. 电网技术, 2017, 41(7): 2229-2236.
Yu Reying, Chen Ning, Miao Miao, et al.A repair method for PV power station output data considering weather and spatial correlations[J]. Power System Technology, 2017, 41(7): 2229-2236.
[8] 阚博文, 刘广一, Khodayar Mahdi, 等. 基于图机器学习的分布式光伏发电预测[J]. 供用电, 2019, 36(11): 20-27.
Kan Bowen, Liu Guangyi, KhodayarM, et al. Distributed photovoltaic generation prediction based on graph machine learning[J]. Distribution &Utilization, 2019, 36(11): 20-27.
[9] 王晶, 黄越辉, 李驰, 等. 考虑空间相关性和天气类型划分的多光伏电站时间序列建模方法[J]. 电网技术, 2020, 44(4): 1376-1384.
Wang Jing, HuangYuehui, Li Chi, et al. Time series modeling method for multi-photovoltaic power stations considering spatial correlation and weather type classification[J]. Power System Technology,2020, 44(4): 1376-1384.
[10] 焦田利. 基于时空关系的广域分布式光伏发电群出力预测关键模型研究[D]. 杭州: 杭州电子科技大学, 2019.
[11] 路宽, 赵岩, 王昕, 等. 一种基于编码解码长短期记忆网络的短期风电功率预测方法: 中国, CN108711847B[P].2019-06-04.
[12] 钟建林, 何友, 王红星. 基于多频小波分析和D-S推理的电路故障诊断[J]. 电工技术学报, 2010, 25(8): 180-184, 192.
ZhongJianlin, HeYou, Wang Hongxing. Circuit fault diagnosis based on multi-frequency wavelet analysis and D-S reasoning[J]. Transactions of China Electrotechnical Society, 2010, 25(8): 180-184, 192.
[13] Liang Yuxuan, KeSongyu, ZhangJunbo, et al. GeoMAN: multi-level attention networks for Geo-sensory time series prediction[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, 2018: 3428-3434.
[14] 李冬辉, 尹海燕, 郑博文, 等. 改进的LSTM方法在冷水机组传感器故障检测中的应用[J]. 电工技术学报, 2019, 34(11): 2324-2332.
Li Donghui, Yin Haiyan, Zheng Bowen, et al.Application of improved LSTM method in sensor fault detection of the chiller[J]. Transactions of China Electrotechnical Society, 2019, 34(11): 2324-2332.
[15] 朱文立, 张利, 杨明, 等. 考虑日周期性影响的光伏功率爬坡事件非精确概率预测[J]. 电力系统自动化, 2019, 43(20): 31-40.
Zhu Wenli, Zhang Li, Yang Ming, et al.Imprecise probabilistic prediction of photovoltaic power ramp event considering daily periodic effect[J]. Automation of Electric Power Systems, 2019, 43(20): 31-40.
[16] 谢恩哲. 考虑气象要素的光伏预测模型研究[D]. 哈尔滨: 哈尔滨理工大学, 2015.
[17] 吉锌格, 李慧, 刘思嘉, 等. 基于MIE-LSTM的短期光伏功率预测[J]. 电力系统保护与控制, 2020, 48(7): 50-57.
JiXinge, Li Hui, Liu Sijia, et al. Short-term photovoltaic power forecasting based on MIE-LSTM[J]. Power System Protection and Control,2020, 48(7): 50-57.
[18] 王晨, 寇鹏. 基于卷积神经网络和简单循环单元集成模型的风电场内多风机风速预测[J]. 电工技术学报, 2020, 35(13): 2723-2735.
Wang Chen, Kou Peng.Wind speed forecasts of multiple wind turbines in a wind farm based on integration model built by convolutional neural network and simple recurrent unit[J]. Transactions of China Electrotechnical Society, 2020, 35(13): 2723-2735.