Short-term Photovoltaic Power Prediction Based on SMARTS and LK Optical Flow Method

WANG Guang; WANG Xin; WANG Anjie; JIAO Jianfang

doi:10.19805/j.cnki.jcspe.2025.240266

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Short-term Photovoltaic Power Prediction Based on SMARTS and LK Optical Flow Method

更新时间：2026-10-10

- Short-term Photovoltaic Power Prediction Based on SMARTS and LK Optical Flow Method
- Chinese Journal of Power Engineering Vol. 45, Issue 6, Pages: 835-845(2025)
- 作者机构：
  
  华北电力大学自动化系,河北,保定,071003
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2025.240266
  CLC：
- Online First：16 June 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
王光,王欣,王安杰,焦建芳. 基于SMARTS和LK光流法的短期光伏功率预测动力工程学报, 2025, 45(6): 835-845 https://doi.

org/10.19805/j.cnki.jcspe.2025.240266
王光,王欣,王安杰,焦建芳. 基于SMARTS和LK光流法的短期光伏功率预测动力工程学报, 2025, 45(6): 835-845 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.240266.

org/10.19805/j.cnki.jcspe.2025.240266 DOI：

摘要

针对现有光伏功率预测模型精度和稳定性不足等问题

提出了一种以天空图像数据为基础

基于阳光大气辐射传输的简单模型(SMARTS)和LK光流法的光伏功率预测模型。利用SMARTS计算指定时间的晴空辐照度和太阳位置信息

同时通过LK光流法获取云层运动向量

使用云层运动向量推测未来时刻云层对太阳直射光的遮挡情况

再利用晴空辐照度和预测得到的太阳遮挡情况计算最终功率预测结果。采用天空图像数据集SKIPP'D对模型进行验证:在晴天环境下

将所提方法与Bird模型、Ineichen模型进行对比;在阴天环境下

将所提方法与长短期记忆(LSTM)神经网络模型、卷积神经网络(CNN)模型进行了对比。验证了该方法在短期光伏功率预测方面的有效性。结果表明:阴天环境下

所提方法能够准确地捕捉云层变化对光伏发电功率的影响

模型决定系数

大于90%

预测精度和稳定性都明显优于对照模型。

Abstract

To address the problems of insufficient accuracy and stability of the existing photovoltaic (PV) power prediction models

a PV power prediction model was proposed. This model was based on sky image data

the simple model of the atmospheric radiative transfer of sunshine (SMARTS)

and the LK optical flow method. The SMARTS was used to calculate the clear sky irradiance and solar position information at a specified time

and the cloud motion vectors were obtained through the LK optical flow method. The cloud motion vectors were used to infer the shading situation of the cloud to the direct sunlight at future times. Then

the clear sky irradiance and the predicted solar shading situation were use

d to calculate the final power prediction result. The model was validated using the sky image dataset SKIPP'D. In a sunny environment

the proposed method was compared with the Bird model and the Ineichen model. In a cloudy environment

the proposed method was compared with the long short-term memory (LSTM) neural network model and the convolutional neural network (CNN) model. The effectiveness of this method in short-term PV power prediction has been verified. Results show that

the proposed method can accurately capture the effect of cloud changes on the PV power generation in a cloudy environment

the determination coefficient

of the model is greater than 90%

and both the prediction accuracy and stability are significantly better than those of the control models.

关键词

Keywords

references

吴芸芸, 王义函, 陈衡, 等. 太阳能辅助垃圾焚烧发电系统及其性能研究[J]. 动力工程学报, 2023, 43(7): 858-868. WU Yunyun, WANG Yihan, CHEN Heng, et al. Performance analysis of a solar-aided waste-to-energy power generation system[J]. Journal of Chinese Society of Power Engineering, 2023, 43(7): 858-868.

王异林, 苏博生, 黄枝, 等. 太阳能辅助沼气化学回热的新型冷热电联产系统模拟分析[J]. 动力工程学报, 2024, 44(2): 213-220, 231. WANG Yilin, SU Bosheng, HUANG Zhi, et al. Simulation analysis of a new CCHP system based on solar-assisted biogas chemical recuperation[J]. Journal of Chinese Society of Power Engineering, 2024, 44(2): 213-220, 231.

HU Chunchao, CAI Zexiang, ZHANG Yanxu, et al. A soft actor-critic deep reinforcement learning method for multi-timescale coordinated operation of microgrids[J]. Protection and Control of Modern Power Systems, 2022, 7(1): 29.

YENGEJEH H H, SHAHNIA F, ISLAM S M. Impact of distributed rooftop photovoltaic systems on short-circuit faults in the supplying low voltage networks[J]. Electric Power Components and Systems, 2017, 45(20): 2257-2274.

SANSA I, BOUSSAADA Z, BELLAAJ N M. Solar radiation prediction using a novel hybrid model of ARMA and NARX[J]. Energies, 2021, 14(21): 6920.

魏铭琦, 张天瑞, 高秀秀, 等. 基于DA-RKELM算法的光伏发电功率预测方法[J]. 系统仿真学报, 2020, 32(10): 2041-2051. WEI Mingqi, ZHANG Tianrui, GAO Xiuxiu, et al. A photovoltaic power forecasting method based on DA-RKELM algorithm[J]. Journal of System Simulation, 2020, 32(10): 2041-2051.

陈涛, 王艳, 纪志成. 基于经验小波变换的光伏功率组合预测模型[J]. 系统仿真学报, 2021, 33(11): 2627-2635. CHEN Tao, WANG Yan, JI Zhicheng. Combination forecasting model of photovoltaic power based on empirical wavelet transform[J]. Journal of System Simulation, 2021, 33(11): 2627-2635.

WANG Huaizhi, LEI Zhenxing, ZHANG Xian, et al. A review of deep learning for renewable energy forecasting[J]. Energy Conversion and Management, 2019, 198: 111799.

DU Peidong, ZHANG Gang, LI Pingli, et al. The photovoltaic output prediction based on variational mode decomposition and maximum relevance minimum redundancy[J]. Applied Sciences, 2019, 9(17): 3593.

HOSSAIN M S, MAHMOOD H. Short-term photovoltaic power forecasting using an LSTM neural network and synthetic weather forecast[J]. IEEE Access, 2020, 8: 172524-172533.

WU Ze, PAN Feifan, LI Dandan, et al. Prediction of photovoltaic power by the Informer model based on convolutional neural network[J]. Sustainability, 2022, 14(20): 13022.

AGGA A, ABBOU A, LABBADI M, et al. Short-term self consumption PV plant power production forecasts based on hybrid CNN-LSTM, ConvLSTM models[J]. Renewable Energy, 2021, 177: 101-112.

王东风, 刘婧, 黄宇, 等. 结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究[J]. 太阳能学报, 2024, 45(2): 443-450. WANG Dongfeng, LIU Jing, HUANG Yu, et al. Photovoltaic power prediction method combinating solar radiation calculation and CNN-LSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(2): 443-450.

王宇驰, 赵延阳, 张树军. 基于EMD-KPCA-LSTM的光伏功率预测模型分析[J]. 现代工业经济和信息化, 2024, 14(2): 89-91, 94. WANG Yuchi, ZHAO Yanyang, ZHANG Shujun. Photovoltaic power prediction model based on EMD-KPCA-LSTM[J]. Modern Industrial Economy and Informationization, 2024, 14(2): 89-91, 94.

NIU Tong, LI Jinkai, WEI Wei, et al. A hybrid deep learning framework integrating feature selection and transfer learning for multi-step global horizontal irradiation forecasting[J]. Applied Energy, 2022, 326: 119964.

董坤, 冉鹏, 刘旭, 等. 基于权参数优化的并行深度学习光伏功率预测[J]. 动力工程学报, 2024, 44(1): 91-98. DONG Kun, RAN Peng, LIU Xu, et al. Photovoltaic power prediction by weight parameter optimization-based parallel deep learning[J]. Journal of Chinese Society of Power Engineering, 2024, 44(1): 91-98.

RODRGUEZ-BENTEZ F J, LPEZ-CUESTA M, ARBIZU-BARRENA C, et al. Assessment of new solar radiation nowcasting methods based on sky-camera and satellite imagery[J]. Applied Energy, 2021, 292: 116838.

谈玲, 康瑞星, 夏景明, 等. 融合多源异构气象数据的光伏功率预测模型[J]. 电子与信息学报, 2024, 46(2): 503-517. TAN Ling, KANG Ruixing, XIA Jingming, et al. A photovoltaic power prediction model integrating multi-source heterogeneous meteorological data[J]. Journal of Electronics & Information Technology, 2024, 46(2): 503-517.

王飞, 李娜, 苏营, 等. 基于卫星遥感的辐照度时空关联映射与预测建模[J]. 太阳能学报, 2024, 45(3): 1-9. WANG Fei, LI Na, SU Ying, et al. Spatiotemporal correlation mapping and prediction modeling of irradiance based on satellite remote sensing[J]. Acta Energiae Solaris Sinica, 2024, 45(3): 1-9.

叶畅, 柳丹, 曹侃. 基于云图特征的超短期光伏发电功率预测模型[J]. 电网与清洁能源, 2023, 39(10): 70-79. YE Chang, LIU Dan, CAO Kan. An ultra-short-term photovoltaic power forecasting model based on cloud features[J]. Power System and Clean Energy, 2023, 39(10): 70-79.

LIU Jingxuan, ZANG Haixiang, CHENG Lilin, et al. A transformer-based multimodal-learning framework using sky images for ultra-short-term solar irradiance forecasting[J]. Applied Energy, 2023, 342: 121160.

HU Keyong, CAO Shihua, WANG Lidong, et al. A new ultra-short-term photovoltaic power prediction model based on ground-based cloud images[J]. Journal of Cleaner Production, 2018, 200: 731-745.

FU Yuwei, CHAI Hua, ZHEN Zhao, et al. Sky image prediction model based on convolutional auto-encoder for minutely solar PV power forecasting[J]. IEEE Transactions on Industry Applications, 2021, 57(4): 3272-3281.

郁云, 王一海, 曹潇. 结合气象监测与地基云图的地表太阳辐射预测[J]. 电子器件, 2024, 47(1): 134-139. YU Yun, WANG Yihai, CAO Xiao. Surficial solar irradiation prediction based on meteorological monitoring combined with ground-based cloud images[J]. Chinese Journal of Electron Devices, 2024, 47(1): 134-139.

GUEYMARD C A. Parameterized transmittance model for direct beam and circumsolar spectral irradiance[J]. Solar Energy, 2001, 71(5): 325-346.

GUEYMARD C. SMARTS2, a simple model of the atmospheric radiative transfer of sunshine: algorithms and performance assessment[R]. USA: Florida Solar Energy Center, 2021.

BIRD R E. A simple, solar spectral model for direct-normal and diffuse horizontal irradiance[J]. Solar Energy, 1984, 32(4): 461-471.

ZHEN Zhao, WANG Fei, MI Zengqiang, et al. Cloud tracking and forecasting method based on optimization model for PV power forecasting[C]//2015 Australasian Universities Power Engineering Conference (AUPEC). Wollongong, NSW, Australia: IEEE, 2015: 1-4.

NIE Yuhao, LI Xiatong, SCOTT A, et al. SKIPP'D: a sky images and photovoltaic power generation dataset for short-term solar forecasting[J]. Solar Energy, 2023, 255: 171-179.

YANG Dazhi. A guideline to solar forecasting research practice: reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES)[J]. Journal of Renewable and Sustainable Energy, 2019, 11(2): 022701.

YANG Dazhi. Comment: operational aspects of solar forecasting[J]. Solar Energy, 2020, 210: 38-40.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Review of Key Technologies and Research Applications in Wind Power Prediction

Research on Key Technologies of Medium and High Temperature Thermochemical Heat Storage

Multi-objective Optimal Maintenance Decision-making of Gas Turbine Blades Based on WPHM and Non-dominated Genetic Algorithm

Research on Optimal Scheduling Method for Source-Grid- Load-Storage Systems Considering Electro-Thermal Load Demands in Industrial Parks

Modeling of Coal-Ammonia Co-firing Boiler and Multi-modal Validation Optimization Using Affinity Propagation-Least Squares Support Vector Machine

Related Author

LIU Yibing

GAO Qingfeng

WU Xin

TENG Wei

WANG Lei

HUANG Shuo

ZHAO Bingtao

ZHONG Mei

Related Institution

Key Laboratory of Power Station Energy Transfer, Conversion and System, Ministry of Education, North China Electric Power University

School of Energy and Power Engineering, University of Shanghai for Science and Technology

School of Energy, Power and Mechanical Engineering, North China Electric Power University

State Key Laboratory of Clean Energy Utilization, Zhejiang University

School of Mechanical and Power Engineering, North University of China

AI问答

⁰