基于相似日聚类和SSA-LSTM的光伏组件积灰损失预测

李新福; 李斌; 王广溢; 吴正人; 张剑; 王鑫

doi:doi:10.19912/j.0254-0096.tynxb.2024-1425

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

基于相似日聚类和SSA-LSTM的光伏组件积灰损失预测

更新时间：2026-01-08

- 基于相似日聚类和SSA-LSTM的光伏组件积灰损失预测
- Vol. 46, Issue 12, Pages: 195-203(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-1425
  CLC： TK519
- Published Online：07 January 2026，
  
  Published：2025
- 稿件说明：
移动端阅览
李新福, 李斌, 王广溢, et al. 基于相似日聚类和SSA-LSTM的光伏组件积灰损失预测[J]. 2025, 46(12): 195-203.
DOI：

李新福, 李斌, 王广溢, et al. 基于相似日聚类和SSA-LSTM的光伏组件积灰损失预测[J]. 2025, 46(12): 195-203. DOI： doi:10.19912/j.0254-0096.tynxb.2024-1425.

摘要

为探究气象因素对光伏组件积灰损失的影响

提出一种相似日聚类、麻雀搜索算法（SSA）和长短期记忆网络（LSTM）相结合的光伏组件积灰损失预测模型。首先

利用皮尔逊系数法选出主要气象因素;其次

利用K-均值算法将历史数据聚类为晴天、多云和阴雨天3种相似日样本集并分别建立预测模型;之后

利用SSA优化LSTM超参数

结果表明相较于其他模型

SSA-LSTM模型的预测效果最佳。最后

提出模型组合预测法

结果表明该方法具有预测精度高、泛化能力强的特点

可为光伏组件积灰损失预测研究提供参考。

Abstract

In order to explore the influence of meteorological factors on the dust deposition loss of photovoltaic modules

a prediction model combining similar day clustering

sparrow search algorithm （SSA） and long short-term memory（LSTM） is proposed. Firstly

the main meteorological factors are selected by the Pearson coefficient method. Secondly

the historical data is clustered into three similar day sample sets of sunny

cloudy and rainy days by using the -means algorithm and prediction models are established respectively. Finally

the LSTM hyperparameters are optimized by SSA. The results show that compared with other models

the SSA-LSTM model has the best prediction effect. And the

a model combination prediction method is proposed. The results show that this method has the characteristics of high prediction accuracy and strong generalization ability

which can provide a reference for the prediction of photovoltaic module dust deposition loss.

关键词

Keywords

references

XU L Y, LI S Y, JIANG J M, et al.The influence of dust deposition on the temperature of soiling photovoltaic glass under lighting and windy conditions[J]. Solar energy, 2020, 199: 491-496.

王道累, 姚从荣, 李超, 等. 光伏组件热斑效应智能化检测的综述及展望[J]. 太阳能学报, 2024, 45(5): 527-536.

张军涛, 朱少康, 王珊, 等. 基于有效介质理论的积灰组件透射特性研究[J]. 太阳能学报, 2022, 43(10): 52-58.

VILLEMIN T, FARGES O, PARENT G, et al.Monte Carlo prediction of the energy performance of a photovoltaic panel using detailed meteorological input data[J]. International journal of thermal sciences, 2024, 195: 108672.

ABDALLAH M, KHAIYAT A, BASAHEEH A, et al.Soiling loss rate measurements of photovoltaic modules in a hot and humid desert environment[J]. Journal of solar energy engineering, 2021, 143(3): 031005.

SAID S A M, WALWIL H M. Fundamental studies on dust fouling effects on PV module performance[J]. Solar energy, 2014, 107: 328-337.

李练兵, 王增喜, 刘斌, 等. 太阳电池积灰对其发电性能影响的研究[J]. 太阳能学报, 2016, 37(6): 1418-1422.

宁会峰, 程荣展, 王伟志, 等. 积灰对光伏发电的影响及除尘效果实验研究[J]. 太阳能学报, 2020, 41(11): 120-125.

QAISIEH A, ABU-NABAH B A, HAMDAN M O, et al. Optical characterization of accumulated dust particles and the sustainability of transmitted solar irradiance to photovoltaic cells[J]. Renewable energy, 2023, 219: 119439.

KALDELLIS J K, FRAGOS P.Ash deposition impact on the energy performance of photovoltaic generators[J]. Journal of cleaner production, 2011, 19(4): 311-317.

王粟, 江鑫, 曾亮, 等. 基于VMD-DESN-MSGP模型的超短期光伏功率预测[J]. 电网技术, 2020, 44(3): 917-925.

JAVED W, GUO B, FIGGIS B.Modeling of photovoltaic soiling loss as a function of environmental variables[J]. Solar energy, 2017, 157: 397-407.

陈金鑫, 潘国兵, 欧阳静, 等. 自然降雨下光伏组件积灰预测方法研究[J]. 太阳能学报, 2021, 42(2): 431-437.

ZITOUNI H, AZOUZOUTE A, HAJJAJ C, et al.Experimental investigation and modeling of photovoltaic soiling loss as a function of environmental variables: a case study of semi-arid climate[J]. Solar energy materials and solar cells, 2021, 221: 110874.

XUE J K, SHEN B.A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems science & control engineering, 2020, 8(1): 22-34.

王福忠, 王帅峰, 张丽. 基于VMD-LSTM与误差补偿的光伏发电超短期功率预测[J]. 太阳能学报, 2022, 43(8): 96-103.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于SSA-VMD-LIESN的短期风电功率预测方法研究

ULTRA-SHORT-TERM WIND SPEED PREDICTION BASED ON SAMPLE ENTROPY-BASED DUAL DECOMPOSITION AND SSA-LSTM

K-ISSA-LSTM PHOTOVOLTAIC POWER PREDICTION BASED ON POWER CHARACTERISTIC

CloudSwinNetLite：轻量级地基云图细粒度分割网络

一种高分辨率的光伏短期功率预测模型

Related Author

杨宁宁

王怡昕

吴朝俊

马芝瑞

Wang Xi

Sun Na

Su Hao

Zhang Nan

Related Institution

Faulty of Automation, Huaiyin Institute of Technology, Huaian

Key Laboratory of Thermo-Fluid Science & Engineering of MOE, Xi’an Jiaotong University

Electrical Engineering College, Zhejiang University

Information Engineering College, Hangzhou Dianzi University

State Grid Wenzhou Electric Power Supply Company

AI问答

⁰