局部遮挡下光伏组件功率损失预测模型

刘林君; 李琼; 封力; 饶慧晴; 卢永

doi:10.19912/j.0254-0096.tynxb.2024-1397

PDF(1486 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (12) : 243-253. DOI: 10.19912/j.0254-0096.tynxb.2024-1397

局部遮挡下光伏组件功率损失预测模型

刘林君¹, 李琼¹, 封力¹, 饶慧晴¹, 卢永²

作者信息 +

PREDICTION MODEL OF PHOTOVOLTAIC POWER LOSS UNDER PARTIAL OCCLUSION

Liu Linjun¹, Li Qiong¹, Feng Li¹, Rao Huiqing¹, Lu Yong²

Author information +

文章历史 +

摘要

为研究遮挡条件下的发电效率损失预测以及监测光伏组件遮挡缺陷严重程度,该文提出一种基于Tent-SSA-BP的局部遮挡下光伏组件输出功率损失预测模型。首先通过仿真模拟实验,对光伏组件在局部遮挡条件下的输出特性进行详细分析,在大量仿真数据基础上,建立Tent-SSA-BP预测模型。由于BP神经网络模型在预测时容易陷入局部最优解,预测精度不高,该文建立的Tent-SSA-BP预测模型解决原有网络容易造成的局部最优问题,提高全局搜索能力,快速找到更优的参数组合。通过实验对比分析,Tent-SSA-BP预测模型相比于原有网络MAE降低0.585,MSE降低3.212,RMSE降低0.593,具有更好的模型拟合程度,提升了模型预测精度。

Abstract

The phenomenon of foreign body occlusion often occurs in photovoltaic modules during long-term outdoor operation, which affects photovoltaic power generation. Studying the prediction of power generation efficiency loss under occlusion conditions is very useful for monitoring the severity of photovoltaic module occlusion defects and guiding module cleaning scientifically. In this paper, a forecast model of PV module output power loss under partial occlusion based on Tent-SSA-BP is proposed. Firstly, the output characteristics of PV modules under partial occlusion are analyzed through simulation experiments. On the basis of a large number of simulation data, the Tent-SSA-BP prediction model is established. Because BP neural network model is easy to fall into local optimal solution and the prediction accuracy is not high, the Tent-SSA-BP prediction model established in this paper solves the local optimal problem easily caused by the original network, improves the global search ability, and quickly finds a better parameter combination. Through comparative analysis of experiments, the determination coefficient of Tent-SSA-BP prediction model is improved by 0.04 compared with the original network, which has a better degree of model fitting and improves the prediction accuracy of the model.

导出引用

刘林君, 李琼, 封力, 饶慧晴, 卢永. 局部遮挡下光伏组件功率损失预测模型[J]. 太阳能学报. 2025, 46(12): 243-253 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1397

Liu Linjun, Li Qiong, Feng Li, Rao Huiqing, Lu Yong. PREDICTION MODEL OF PHOTOVOLTAIC POWER LOSS UNDER PARTIAL OCCLUSION[J]. Acta Energiae Solaris Sinica. 2025, 46(12): 243-253 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1397

中图分类号： TM615

参考文献

[1] 戚军, 叶焙佳, 李袁超, 等. 基于阴影识别的光伏阵列输出特性简化仿真方法[J]. 高技术通讯, 2020, 30(2):185-195.
QI J, YE B J, LI Y C, et al.A simplified simulation method for PV array’s output characteristics based on shadow recognition[J]. High-tech communications,2020,30(2):185-195.
[2] 张逴, 李树成, 魏东, 等. 基于GS-SVM的光伏阵列积灰程度评估方法研究[J]. 太阳能学报, 2024, 45(11): 220-226.
ZHANG C, LI S C, WEI D, et al.Evaluation method of ash accumulation degree of photovoltaic array based on GS-SVM[J]. Acta energiae solaris sinica, 2024, 45(11): 220-226.
[3] 王宗满, 李玲, 胡振坤. 光伏组件红外检测故障分级方法[J]. 中国科技信息, 2024(1): 116-118.
WANG Z M, LI L, HU Z K.Classification method for infrared detection fault of photovoltaic module[J]. China science and technology information, 2024(1): 116-118.
[4] 刘恒. 基于I-V曲线的热斑光伏组件故障诊断及状态评估综合研究[D]. 合肥: 合肥工业大学, 2020.
LIU H.Comprehensive research on fault diagnosis and condition assessment of hot spot photovoltaic module based on I-V curve[D]. Hefei: Hefei University of Technology, 2020.
[5] 龚莺飞, 鲁宗相, 乔颖, 等. 光伏功率预测技术[J]. 电力系统自动化, 2016, 40(4): 140-151.
GONG Y F, LU Z X, QIAO Y, et al.An overview of photovoltaic energy system output forecasting technology[J]. Automation of electric power systems, 2016,40(4): 140-151.
[6] 殷豪, 陈云龙, 孟安波, 等. 基于二次自适应支持向量机的光伏输出功率预测[J]. 太阳能学报, 2019, 40(7): 1866-1873.
YIN H, CHEN Y L, MENG A B, et al.Prediction of photovoltaic output power based on quadratic adaptive support vector machine[J]. Acta energiae solaris sinica, 2019, 40(7): 1866-1873.
[7] 方洛迪, 郭倩, 卫东, 等. 遮挡状态下光伏组件多峰输出特性的参数计算与分析[J]. 太阳能学报, 2022, 43(7): 115-121.
FANG L D, GUO Q, WEI D, et al.Parameters calculation and analysis of muti-peak output characteristics of PV module under shading[J]. Acta energiae solaris sinica, 2022, 43(7): 115-121.
[8] 马铭遥, 王海松, 马文婷, 等. 基于S-V特性分析的晶硅光伏组件阴影遮挡故障诊断[J]. 太阳能学报, 2022, 43(9): 64-72.
MA M Y, WANG H S, MA W T, et al.Partial shadow fault diagnosis of crystalline silicon photovoltaic module based on S-V characteristic analysis[J]. Acta energiae solaris sinica,2022,43(9):64-72.
[9] 文爽, 马逸骋, 孙志强. 基于GWO-EEMD-BP神经网络的光伏发电功率短期预测[J]. 中南大学学报(自然科学版), 2022, 53(12): 4799-4808.
WEN S, MA Y C, SUN Z Q.Short-term prediction of photovoltaic power based on GWO-EEMD-BP[J]. Journal of Central South University (science and technology), 2022, 53(12): 4799-4808.
[10] 刘沛汉, 袁铁江, 梅生伟, 等. 基于遗传算法优化神经网络的光伏电站短期功率预测[J]. 水电能源科学, 2016, 34(1): 211-214.
LIU P H, YUAN T J, MEI S W, et al.Short-term power prediction of PV based on combined BP-GA neural network[J]. Water resources and power, 2016, 34(1): 211-214.
[11] 李国进, 黄鹏, 王雪茹. 基于CA-SE-GA-BP的光伏发电功率预测[J]. 水电能源科学, 2020, 38(4): 201-204.
LI G J, HUANG P, WANG X R.Photovoltaic power generation prediction based on CA-SE-GA-BP[J]. Water resources and power, 2020, 38(4): 201-204.
[12] 王云艳, 罗帅, 王子健. 基于改进型BP神经网络的光伏功率预测[J]. 计算机仿真, 2022, 39(11): 153-157.
WANG Y Y, LUO S, WANG Z J.Photovoltaic power prediction combined with popular learning and improved BP neural network[J]. Computer simulation, 2022, 39(11): 153-157.
[13] 杨锡运, 王诗晨, 张艳峰, 等. 基于相似日的Grey-Markov与BP_Adaboost的短期光伏功率预测[J]. 电源技术, 2023, 47(6): 790-794.
YANG X Y, WANG S C, ZHANG Y F, et al.Short-term PV power prediction based on Grey-Markov and BP_Adaboost by similar days[J]. Chinese journal of power sources, 2023, 47(6): 790-794.
[14] 谭建斌, 段春艳, 班群. 基于改进神经网络的光伏发电功率短期预测方法研究[J]. 可再生能源, 2019, 37(8): 1192-1197.
TAN J B, DUAN C Y, BAN Q.Research on short-term prediction method of photovoltaic power based on improved neural network[J]. Renewable energy resources, 2019, 37(8): 1192-1197.
[15] 朱红路, 李旭, 姚建曦, 等. 基于小波分析与神经网络的光伏电站功率预测方法[J]. 太阳能学报, 2015, 36(11): 2725-2730.
ZHU H L, LI X, YAO J X, et al.The power prediction method for photovoltaic power station based on wavelet analysis and neural networks[J]. Acta energiae solaris sinica, 2015, 36(11): 2725-2730.
[16] 张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J] .太阳能学报,2021, 42(9): 62-69.
ZHANG Y Q, CHENG Q Z, JIANG W J, et al.Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta energiae solaris sinica, 2021,42(9):62-69.
[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.
JI X G, LI H, LIU S J, et al.Short-term photovoltaic power forecasting based on MIE-LSTM[J]. Power system protection and control, 2020, 48(7): 50-57.
[18] 裴婷婷, 郝晓弘. 局部阴影条件下光伏阵列的动态建模[J]. 太阳能学报, 2020, 41(2): 268-274.
PEI T T, HAO X H.Dynamic modeling of pv array under partial shading condition[J]. Acta energiae solaris sinica, 2020, 41(2): 268-274.
[19] 林皓, 孙晓寅, 陈昊旻. 局部阴影遮挡下大尺寸光伏组件的输出特性研究[J]. 太阳能, 2023(3): 38-45.
LIN H, SUN X Y, CHEN H M.Output characteristics study of large size PV modules under partial shadow occlusion[J]. Solar energy, 2023(3): 38-45.
[20] MORETÓN R, LORENZO E, NARVARTE L. Experimental observations on hot-spots and derived acceptance/rejection criteria[J]. Solar energy, 2015, 118: 28-40.
[21] 王乃啸, 高海翔, 王希林, 等. 基于BP神经网络的绝缘子污秽成分LIBS在线检测技术[J]. 广东电力, 2020, 33(9): 49-57.
WANG N X, GAO H X, WANG X L, et al.LIBS online detection technique for insulator contamination based on BP neural network[J]. Guangdong electric power, 2020, 33(9): 49-57.
[22] 杨润泽. 基于GA-PSO-BP神经网络的车险欺诈识别研究[D]. 长沙: 湖南大学, 2021.
YANG R Z.The research on auto insurance fraud identification based on GA-PSO-BP neural network[D]. Changsha: Hunan University, 2021.
[23] 张伟康, 刘升, 任春慧. 混合策略改进的麻雀搜索算法[J]. 计算机工程与应用, 2021, 57(24): 74-82.
ZHANG W K, LIU S, REN C H.Mixed strategy improved sparrow search algorithm[J]. Computer engineering and applications, 2021, 57(24): 74-82.
[24] 陈亮, 郝祎纯, 李巧茹, 等. 改进SSA优化的BP神经网络交通量预测模型[J]. 哈尔滨工业大学学报, 2024, 56(7): 94-101.
CHEN L, HAO Y C, LI Q R, et al.Traffic volume forecast model based on BP neural network optimized by improved sparrow search algorithm[J]. Journal of Harbin Institute of Technology, 2024, 56(7): 94-101.
[25] 谭金铃, 赵春华, 林彰稳, 等. 基于GBDT特征提取与Tent-ASO-BP网络的铣刀磨损量预测[J]. 计算机集成制造系统, 2024, 30(4): 1296-1308.
TAN J L, ZHAO C H, LIN Z W, et al.Prediction of milling cutter wear based on GBDT feature extraction and Tent-ASO-BP network[J]. Computer integrated manufacturing systems, 2024, 30(4): 1296-1308.