基于灰色关联理论和BP神经网络的分布式光伏电站运维数据虚拟采集方法

doi:10.12204/j.issn.1000-7229.2021.01.014

电力建设 ›› 2021, Vol. 42 ›› Issue (1): 125-131.doi: 10.12204/j.issn.1000-7229.2021.01.014

基于灰色关联理论和BP神经网络的分布式光伏电站运维数据虚拟采集方法

张凌浩¹, 张明¹, 嵇文路¹, 方磊¹, 秦羽飞², 葛磊蛟²

1.国网江苏省电力有限公司南京供电公司,南京市 210019
2.智能电网教育部重点实验室(天津大学),天津市 300072

收稿日期:2020-03-22 出版日期:2021-01-01 发布日期:2021-01-07
通讯作者: 葛磊蛟
作者简介:张凌浩(1975),男,硕士,高级工程师,主要从事分布式光伏并网、智能用电及电力物联网技术方面的研究工作;|张明(1976), 男,硕士,高级工程师,主要从事配电自动化方面的研究工作;|嵇文路(1974),男,博士,高级工程师,主要从事配电自动化方面的研究工作;|方磊(1991),男, 博士,工程师, 主要从事光伏发电、智能车联网及能源互联网技术方面的研究工作;|秦羽飞(1996)男,硕士研究生,从事分布式光伏数据采集方面的研究工作;
基金资助:
国家重点研发计划项目(2018YFB1500800);国网江苏省电力有限公司科技项目“分布式光伏智能运维支撑关键技术与装置研究”(J2020082)

Virtual Acquisition Method for Operation Data of Distributed PV Applying the Mixture of Grey Relational Theory and BP Neural Work

ZHANG Linghao¹, ZHANG Ming¹, JI Wenlu¹, FANG Lei¹, QIN Yufei², GE Leijiao²

1. State Grid Nanjing Electric Power Supply Company, Nanjing 210019, China
2. Key Laboratory of Smart Grid of Ministry of Education(Tianjin University), Tianjin 300072, China

Received:2020-03-22 Online:2021-01-01 Published:2021-01-07
Contact: GE Leijiao
Supported by:
National Key Research and Development Program of China(2018YFB1500800);State Grid Jiangsu Electric Power Co., Ltd. Science and Technology Project “Research on Key Technologies and Devices of Distributed Photovoltaic Intelligent Operation and Maintenance Support”(J2020082)

摘要/Abstract

摘要：

由于分布式光伏电站的布置点多面广、分散无序,要实现其运维数据的全覆盖采集,最佳方式为每一个分布式光伏电站均配置一套数据采集装置,由此也将面临投资成本巨大、运维任务繁重等难题。为此,提出了一种基于灰色关联度和BP神经网络的分布式光伏电站数据虚拟采集方法,实现了在安装少量数据采集装置条件下完成对全区域内分布式光伏电站运维数据的采集。选取江苏某区域内分布式光伏电站为研究对象,先利用灰色关联理论分析该区域内安装数据采集装置的一个分布式光伏电站的历史运维数据,获知辐照度与分布式光伏出力的特征曲线;然后,将区域范围内待虚拟采集光伏站的日辐照度实时信息与历史辐照度数据进行关联度计算,并选取关联度达到0.9以上的历史日为相似日,然后基于相似日的历史数据建立BP神经网络数据虚拟采集模型,实现区域范围内分布式光伏电站数据的虚拟采集;最后,通过算例验证了该方法采集的光伏输出功率具有较高的精度,能够实现对网格化区域内光伏电站输出功率数据的虚拟采集。

关键词: 分布式光伏电站, 灰色关联理论, 虚拟采集, 神经网络

Abstract:

In order to realize the full coverage collection of operation and maintenance data for the distributed photovoltaic station with the characteristics of many scattered and disordered points in a wide area, the best way is to configure a set of data acquisition devices for each distributed photovoltaic station. Therefore, it will also face the problems such as huge investment cost and heavy operation and maintenance tasks. This paper proposes a virtual acquisition method for distributed photovoltaic data applying the mixture of grey relational degree and BP neural network, and realizes the operation and maintenance data acquisition of the distributed photovoltaic station in the whole region under the condition of installing a small number of data acquisition devices. A distributed photovoltaic power station in a certain region of Jiangsu province is selected as the research object. Firstly, the historical operation and maintenance data of a distributed photovoltaic power station with data acquisition devices installed in the region are analyzed by using the grey relational theory, and the characteristic curves of irradiance and distributed photovoltaic output are obtained. Then, the correlation degree between the real-time daily irradiance information and historical irradiance data of the photovoltaic station to be virtually collected in the region is calculated, and the historical date with correlation degree above 0.9 is selected as the similar date, and then the BP neural network data virtual acquisition model is established according to the historical data of similar days, which is used to realize the virtual collection of distributed photovoltaic data in the region. Finally, the case verifies that the photovoltaic output power collected by this method has high precision and that the method can realize the virtual collection of photovoltaic output power data in the grid area.

Key words: distributed photovoltaic power station, grey relevance theory, virtual acquisition, neural network

中图分类号:

TM711

张凌浩, 张明, 嵇文路, 方磊, 秦羽飞, 葛磊蛟. 基于灰色关联理论和BP神经网络的分布式光伏电站运维数据虚拟采集方法[J]. 电力建设, 2021, 42(1): 125-131.

ZHANG Linghao, ZHANG Ming, JI Wenlu, FANG Lei, QIN Yufei, GE Leijiao. Virtual Acquisition Method for Operation Data of Distributed PV Applying the Mixture of Grey Relational Theory and BP Neural Work[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(1): 125-131.

图/表 15

图1 辐照度与输出功率曲线图

Fig.1 Curves of irradiance and PV output power

图2 BP神经网络结构

Fig.2 Structure of BP neural network

图3 虚拟采集模型示意图

Fig.3 Schematic diagram of virtual acquisition model

图4 1—3月份相似日分析结果示意图

Fig.4 Schematic diagram of the analysis results of similar days in January, February and March

图5 6—8月份相似日分析结果示意图

Fig.5 Schematic diagram of the analysis results of similar days in June, July and August

图6 10—12月份相似日分析结果示意图

Fig.6 Schematic diagram of the analysis results of similar days in October, November and December

图7 1—3月份相似日辐照度曲线

Fig.7 Irradiance curves of similar days in January, February and march

图8 6—8月份相似日辐照度曲线

Fig.8 Irradiance curves of similar days in June, July and August

图9 10—12月份相似日辐照度曲线

Fig.9 Irradiance curves of similar days in October, November and December

图10 BP神经网络训练结果

Fig.10 Training results of BP neural network

图11 1—3月份光伏数据虚拟采集结果

Fig.11 Results of virtual collection of photovoltaic data in January, February and March

图12 6—8月份光伏数据虚拟采集结果

Fig.12 Results of virtual collection of photovoltaic data in June, July and August

图13 10—12月份光伏数据虚拟采集结果

Fig.13 Virtual collection results of photovoltaic data in October, November and December

表1 误差指标分析

Table 1 Error index analysiskW

图14 各电站虚拟采集结果

Fig.14 Virtual acquisition of different PV stations

参考文献 19

[1]	王志峰, 杜凤丽 . 2015 ~2022年中国太阳能热发电发展情景分析及预测[J]. 太阳能, 2019(11):5-10, 69.
[2]	邵汉桥, 张籍, 张维 . 分布式光伏发电经济性及政策分析[J]. 电力建设, 2014,35(7):51-57.
	SHAO Hanqiao, ZHANG Ji, ZHANG Wei . Economy and policy analysis of distributed photovoltaic generation[J]. Electric Power Construction, 2014,35(7):51-57.
[3]	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.
[4]	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.
	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.
[5]	张家安, 王琨玥, 陈建 , 等. 基于空间相关性的分布式光伏出力预测[J]. 电力建设, 2020,41(3):47-53.
	ZHANG Jia’an, WANG Kunyue, CHEN Jian , et al. Research on prediction of distributed photovoltaic output considering spatial relevance[J]. Electric Power Construction, 2020,41(3):47-53.
[6]	丁明, 徐宁舟 . 基于马尔可夫链的光伏发电系统输出功率短期预测方法[J]. 电网技术, 2011,35(1):152-157.
	DING Ming, XU Ningzhou . A method to forecast short-term output power of photovoltaic generation system based on Markov chain[J]. Power System Technology, 2011,35(1):152-157.
[7]	袁晓玲, 施俊华, 徐杰彦 . 计及天气类型指数的光伏发电短期出力预测[J]. 中国电机工程学报, 2013,33(34):57-64.
	YUAN Xiaoling, SHI Junhua, XU Jieyan . Short-term power forecasting for photovoltaic generation considering weather type index[J]. Proceedings of the CSEE, 2013,33(34):57-64.
[8]	祝暄懿, 姚李孝 . 基于相似日和小波神经网络的光伏短期功率预测[J]. 电网与清洁能源, 2019,35(3):75-78.
	ZHU Xuanyi, YAO Lixiao . Solar power plant short-term power forecast based on similar days and WNN[J]. Power System and Clean Energy, 2019,35(3):75-78.
[9]	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 Ruoying, 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.
[10]	程伟 . 基于神经网络的微电网光伏发电及负荷短期预测研究[D]. 济南:山东大学, 2019.
	CHENG Wei . Research on micro-grid photovoltaic power generation and load short-term forecasting based on neural network[D]. Jinan: Shandong University, 2019.
[11]	梁彩霞, 高赵亮 . 基于相似日和GA-DBN神经网络的光伏发电短期功率预测[J]. 电气应用, 2019,38(3):97-102.
[12]	LUO P, ZHU S, HAN L, et al. Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine[C]// 2017 IEEE Power & Energy Society General Meeting. IEEE, 2018.
[13]	吴云, 雷建文, 鲍丽山 , 等. 基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测[J]. 电力系统自动化, 2018,42(20):67-74.
	WU Yun, LEI Jianwen, BAO Lishan , et al. Short-term load forecasting based on improved grey relational analysis and neural network optimized by bat algorithm[J]. Automation of Electric Power Systems, 2018,42(20):67-74.
[14]	CUI Y, ZHANG J, ZHONG W . Short-term photovoltaic output prediction method based on similar day selection with grey relational theory[C]// 2019 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia). IEEE, 2019.
[15]	韦航宇 . 基于GA-BP神经网络的光伏电站短期发电功率预测[D]. 南宁:广西大学, 2019.
	WEI Hangyu . Short-term generation power forecast of photovoltaic power station based on GA-BP neural network[D]. Nanning: Guangxi University, 2019.
[16]	耿博, 高贞彦, 白恒远 , 等. 结合相似日GA-BP神经网络的光伏发电预测[J]. 电力系统及其自动化学报, 2017,29(6):118-123.
	GENG Bo, GAO Zhenyan, BAI Hengyuan , et al. PV generation forecasting combined with similar days and GA-BP neural network[J]. Proceedings of the CSU-EPSA, 2017,29(6):118-123.
[17]	MENG X, XU A, ZHAO W , et al. A new PV generation power prediction model based on GA-BP neural network with artificial classification of history day [C]// International Conference on Power System Technology. 2018.
[18]	张刚, 刘福潮, 王维洲 , 等. 电网短期负荷预测的BP-ANN方法及应用[J]. 电力建设, 2014,35(3):54-58.
	ZHANG Gang, LIU Fuchao, WANG Weizhou , et al. BP-ANN method for power grid short-term load forecasting and its application[J]. Electric Power Construction, 2014,35(3):54-58.
[19]	王小川, 史峰, 郁磊 . MATLAB神经网络30个案例分析[M]. 北京: 北京航空航天大学出版社, 2010.

基于灰色关联理论和BP神经网络的分布式光伏电站运维数据虚拟采集方法

Virtual Acquisition Method for Operation Data of Distributed PV Applying the Mixture of Grey Relational Theory and BP Neural Work

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价

[1]	唐子卓, 刘洋, 许立雄, 郭久亿. 基于负荷数据频域特征和LSTM网络的类别不平衡负荷典型用电模式提取方法[J]. 电力建设, 2020, 41(8): 17-24.
[2]	宋建，束洪春，董俊，梁雨婷，李雨龙，杨博. 基于GM(1，1)与BP神经网络的综合负荷预测[J]. 电力建设, 2020, 41(5): 75-80.
[3]	白浩，袁智勇，孙睿，张强，史训涛. 基于Apriori算法和卷积神经网络的配电设备运行效率主要影响因素挖掘[J]. 电力建设, 2020, 41(3): 31-38.
[4]	史晨豪，唐忠，魏敏捷，李征南，陈寒. 基于数据驱动的配电网光伏双层优化调控策略[J]. 电力建设, 2020, 41(3): 62-70.
[5]	朱刘柱, 王绪利, 马静, 陈庆会, 齐先军. 基于小波包分解与循环神经网络的综合能源系统短期负荷预测[J]. 电力建设, 2020, 41(12): 133-140.
[6]	庄家懿, 杨国华, 郑豪丰, 王煜东, 胡瑞琨, 丁旭. 并行多模型融合的混合神经网络超短期负荷预测[J]. 电力建设, 2020, 41(10): 1-8.
[7]	朱云杰, 秦文萍, 于浩, 姚宏民, 尹琦琳, 韩肖清. 基于神经网络的微电网参与上层电网实时优化调度策略[J]. 电力建设, 2020, 41(10): 9-11.
[8]	韦善阳，黎静华，黄乾. 基于改进权值优化模型的光伏功率区间预测[J]. 电力建设, 2019, 40(7): 26-33.
[9]	肖泽青，华昊辰，曹军威. 人工智能在能源互联网中的应用综述[J]. 电力建设, 2019, 40(5): 63-70.
[10]	杨懿男，齐林海，王红，苏林萍. 基于生成对抗网络的小样本数据生成技术研究[J]. 电力建设, 2019, 40(5): 71-77.
[11]	江文超，张兴，谢东，李明. 基于小波变换与BP神经网络的光伏电站孤岛检测研究[J]. 电力建设, 2019, 40(12): 113-119.
[12]	曹弘飞，朱新坚. BP神经网络在线优化卡尔曼滤波算法在钒电池SOC估算中的应用[J]. 电力建设, 2018, 39(4): 9-.
[13]	梁荣，杨波，马润泽，吴健，吴奎华，林振智，文福拴. 利用多源信息和深度置信神经网络的配电系统空间负荷预测[J]. 电力建设, 2018, 39(10): 12-19.
[14]	牛东晓，马天男，王海潮，刘鸿飞，黄雅莉. 基于KPCA和NSGAII优化CNN参数的电动汽车充电站短期负荷预测[J]. 电力建设, 2017, 38(3): 85-.
[15]	石鑫，朱永利. 深度学习神经网络在电力变压器故障诊断中的应用[J]. 电力建设, 2015, 36(12): 116-122.