Ultra-short-term Photovoltaic Power Forecasting Based on Multi-level Sky Image Features and Broad Learning

CHEN Dianhao; ZANG Haixiang; JIANG Yunan; LIU Jingxuan; SUN Guoqiang; WEI Zhinong

doi:10.7500/AEPS20240416009

您当前的位置：

首页 >

文章列表页 >

Ultra-short-term Photovoltaic Power Forecasting Based on Multi-level Sky Image Features and Broad Learning

Basic Research | 更新时间：2025-06-16

- Ultra-short-term Photovoltaic Power Forecasting Based on Multi-level Sky Image Features and Broad Learning
- Automation of Electric Power Systems Vol. 48, Issue 22, Pages: 131-139(2024)
- 作者机构：
  
  河海大学电气与动力工程学院，江苏省南京市 211100
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(52077062)
- DOI：10.7500/AEPS20240416009
  CLC：
- Received：16 April 2024，
  
  Revised：2024-08-04，
  
  Published Online：05 September 2024，
  
  Published：25 November 2024
- 稿件说明：
移动端阅览
陈殿昊,臧海祥,蒋雨楠等.基于多层次云图特征与宽度学习的超短期光伏功率预测[J].电力系统自动化,2024,48(22):131-139.

CHEN Dianhao,ZANG Haixiang,JIANG Yunan,et al.Ultra-short-term Photovoltaic Power Forecasting Based on Multi-level Sky Image Features and Broad Learning[J].Automation of Electric Power Systems,2024,48(22):131-139.
陈殿昊,臧海祥,蒋雨楠等.基于多层次云图特征与宽度学习的超短期光伏功率预测[J].电力系统自动化,2024,48(22):131-139. DOI： 10.7500/AEPS20240416009.

CHEN Dianhao,ZANG Haixiang,JIANG Yunan,et al.Ultra-short-term Photovoltaic Power Forecasting Based on Multi-level Sky Image Features and Broad Learning[J].Automation of Electric Power Systems,2024,48(22):131-139. DOI： 10.7500/AEPS20240416009.

摘要

针对现有研究云图信息利用不充分、爬坡功率预测误差较大而导致超短期光伏功率预测性能提升受限的问题，提出一种基于多层次云图特征与宽度学习的超短期光伏功率预测方法。首先，提取地基云图的多层次特征作为功率预测模型的图像特征量；同时，引入云层覆盖率与云层变化率作为爬坡识别模型的图像特征量。其次，结合历史功率数据，构建基于宽度学习的光伏功率预测模型与爬坡识别模型。最后，若爬坡识别结果为非爬坡事件，则直接应用功率预测模型得到预测结果；反之，则使用与爬坡事件相关的历史数据对功率预测模型进行增量更新，并基于更新后的功率预测模型得到预测结果。实验结果表明，所提出的方法能够有效提高超短期光伏功率的预测精度。

Abstract

Aiming at the problems of insufficient use of sky image information and large errors in ramp power forecasting

which lead to the limited predictive performance improvement

an ultra-short-term photovoltaic power forecasting method based on multi-level sky image features and broad learning is proposed. Firstly

the multi-level features of the ground-based sky image are extracted as the image features of the power forecasting model. At the same time

the cloud coverage and cloud change rate are introduced as image features of the ramp recognition model. Secondly

combined with the historical power data

the photovoltaic power forecasting model and the ramp recognition model based on the broad learning are developed. Finally

if the ramp recognition result is a non-ramp event

the forecasting results are obtained according to the power forecasting model. However

if the ramp recognition result is a ramp event

the power forecasting model is incrementally updated using the historical data related to the ramp event

and the forecasting results are obtained based on the updated power forecasting model. The experimental results show that the proposed method can effectively improve the forecasting accuracy of ultra-short-term photovoltaic power.

关键词

Keywords

references

叶林，裴铭，路朋，等 . 基于天气分型的短期光伏功率组合预测方法［J］. 电力系统自动化， 2021 ， 45 （ 1 ）： 44 - 54 .

YE Lin ， PEI Ming ， LU Peng ， et al . Combination forecasting method of short-term photovoltaic power based on weather classification ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 1 ）： 44 - 54 .

王玉庆，徐飞，刘志坚，等 . 基于动态关联表征与图网络建模的分布式光伏超短期功率预测［J］. 电力系统自动化， 2023 ， 47 （ 20 ）： 72 - 82 .

WANG Yuqing ， XU Fei ， LIU Zhijian ， et al . Ultra-short-term power forecasting of distributed photovoltaic based on dynamic correlation characterization and graph network modeling ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 20 ）： 72 - 82 .

赵耀，高少炜，李东东，等 . 基于天气相似聚类与QRNN的短期光伏功率区间概率预测［J］. 电力系统自动化， 2023 ， 47 （ 23 ）： 152 - 161 .

ZHAO Yao ， GAO Shaowei ， LI Dongdong ， et al . Short-term interval probability prediction of photovoltaic power based on weather similarity clustering and quantile regression neural network ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 23 ）： 152 - 161 .

杨明，李梦林，王勃，等 . 面向新型电力系统发展需求的数值天气预报技术及应用综述［J/OL］. 电力系统自动化［ 2024-08-22 ］. http：//kns.cnki.net/kcms/detail/32.1180.TP.20240619.1053.002.html http://kns.cnki.net/kcms/detail/32.1180.TP.20240619.1053.002.html .

YANG Ming ， LI Menglin ， WANG Bo ， et al . Review on technologies and applications of numerical weather prediction for development needs of new power system ［J/OL］. Automation of Electric Power Systems ［ 2024-08-22 ］. http：//kns.cnki.net/kcms/detail/32.1180.TP.20240619.1053.002. html http://kns.cnki.net/kcms/detail/32.1180.TP.20240619.1053.002.html .

孟祥剑，石欣羽，张承慧，等 . 基于pix2pixHD图像修复的光伏电站秒级功率预测方法［J/OL］. 高电压技术［ 2024-08-22 ］. https：//doi.org/10.13336/j.1003-6520.hve.20232181 https://doi.org/10.13336/j.1003-6520.hve.20232181 .

MENG Xiangjian ， SHI Xinyu ， ZHANG Chenghui ， et al . Second level photovoltaic power forecasting method based on pix2pixHD image restoration ［J/OL］. High Voltage Engineering ［ 2024-08-22 ］. https：//doi.org/10.13336/j.1003-6520.hve.20232181 https://doi.org/10.13336/j.1003-6520.hve.20232181 .

PALETTA Q ， HU A ， ARBOD G ， et al . ECLIPSE： envisioning cloud induced perturbations in solar energy ［J］. Applied Energy ， 2022 ， 326 ： 119924 .

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 .

张青山，王丽婕，郝颖，等 . 基于卫星云图和晴空模型的分布式光伏电站太阳辐照度超短期预测［J］. 高电压技术， 2022 ， 48 （ 8 ）： 3271 - 3281 .

ZHANG Qingshan ， WANG Lijie ， HAO Ying ， et al . Ultra-short-term solar irradiance prediction of distributed photovoltaic power stations based on satellite cloud images and clear sky model ［J］. High Voltage Engineering ， 2022 ， 48 （ 8 ）： 3271 - 3281 .

MACIELC J ， GIMENEZ-LEDESMA J ， ANDO-JUNIOR O ， et al . Hybrid prediction method of solar irradiance applied to short-term photovoltaic energy generation ［J］. Renewable and Sustainable Energy Reviews ， 2023 ， 342 ： 121160 .

CHEN C LP ， LIU Zhulin . Broad learning system： an effective and efficient incremental learning system without the need for deep architecture ［J］. IEEE Transactions on Neural Networks and Learning Systems ， 2018 ， 29 （ 1 ）： 10 - 24 .

ZHOU Nan ， XU Xiaoyuan ， YAN Zheng ， et al . Spatio-temporal probabilistic forecasting of photovoltaic power based on monotone broad learning system and copula theory ［J］. IEEE Transactions on Sustainable Energy ， 2022 ， 13 （ 4 ）： 1874 - 1885 .

周楠，徐潇源，严正，等 . 基于宽度学习系统的光伏发电功率超短期预测［J］. 电力系统自动化， 2021 ， 45 （ 1 ）： 55 - 64 .

ZHOU Nan ， XU Xiaoyuan ， YAN Zheng ， et al . Ultra-short-term forecasting of photovoltaic power generation based on broad learning system ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 1 ）： 55 - 64 .

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 - 38 .

ZHU Wenli ， ZAHNG Li ， YANG Ming ， et al . Imprecise probabilistic forecasting of photovoltaic power ramp event considering daily periodic effect ［J］. Automation of Electric Power Systems ， 2019 ， 43 （ 20 ）： 31 - 38 .

LAPPALAINEN K ， WANG G ， KLEISSL J ， et al . Estimation of the largest expected photovoltaic power ramp rates ［J］. Applied Energy ， 2020 ， 278 ： 115636 .

CHENG Lilin ， ZANG Haixiang ， TRIVEDI A ， et al . Mitigating the impact of photovoltaic power ramps on intraday economic dispatch using reinforcement forecasting ［J］. IEEE Transactions on Sustainable Energy ， 2024 ， 15 （ 1 ）： 3 - 12 .

Stanford . About persistent URLs （PURLs）［EB/OL］. ［ 2024-02-05 ］. https：//purl.stanford.edu/ https://purl.stanford.edu/ .

魏利胜，周圣文，张平改，等 . 基于双经度模型的鱼眼图像畸变矫正方法［J］. 仪器仪表学报， 2015 ， 36 （ 2 ）： 377 - 385 .

WEI Lisheng ， ZHOU Shengwen ， ZHANG Pinggai ， et al . Double Longitude model based correction method for fish-eye image distortion ［J］. Chinese Journal of Scientific Instrument ， 2015 ， 36 （ 2 ）： 377 - 385 .

GUO Zhaoyang ， YU Xiantao ， DU Qinglei . Infrared and visible image fusion based on saliency and fast guided filtering ［J］. Infrared Physics & Technology ， 2022 ， 123 ： 104178 .

臧海祥，许瑞琦，刘璟璇，等 . 基于多维融合特征和卷积神经网络的多任务用户短期负荷预测［J］. 电力系统自动化， 2023 ， 47 （ 13 ）： 69 - 77 .

ZANG Haixiang ， XU Ruiqi ， LIU Jingxuan ， et al . Short-term load forecasting for multi-task consumers based on multi-dimensional fusion feature and convolutional neural network ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 13 ）： 69 - 77 .

张毅斌，李梦诗，徐子弘，等 . 基于轨迹图像与卷积神经网络的电缆早期故障识别［J］. 广东电力， 2022 ， 35 （ 8 ）： 86 - 94 .

ZHANG Yibin ， LI Mengshi ， XU Zihong ， et al . Cable incipient fault identification based on trajectory image and convolutional neural network ［J］. Guangdong Electric Power ， 2022 ， 35 （ 8 ）： 86 - 94 .

XIE Jiale ， WANG Guang ， LIU Jun ， et al . Faults diagnosis for large-scale battery packs via texture analysis on spatial-temporal images converted from electrical behaviors ［J］. IEEE Transactions on Transportation Electrification ， 2023 ， 9 （ 4 ）： 4876 - 4887 .

白晓阳 . 基于改进Markov和地基云图的光伏超短期预测研究［D］. 哈尔滨：哈尔滨工业大学， 2022 .

BAI Xiaoyang . Research on ultra-short-term forecasting of photovoltaic power based on improved Markov model and ground-based cloud images ［D］. Harbin ： Harbin Institute of Technology ， 2022 .

FENG Cong ， ZHANG Jie ， ZHANG Wenqi ， et al . Convolutional neural networks for intra-hour solar forecasting based on sky image sequences ［J］. Applied Energy ， 2022 ， 310 ： 118438 .

AJITH M ， MARTINEZ-RAMON M . Deep learning based solar radiation micro forecast by fusion of infrared cloud images and radiation data ［J］. Applied Energy ， 2021 ， 294 ： 117014 .

QIN Jun ， JIANG Hou ， LU Ning ， et al . Enhancing solar PV output forecast by integrating ground and satellite observations with deep learning ［J］. Renewable and Sustainable Energy Reviews ， 2022 ， 167 ： 112680 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Value-oriented Photovoltaic Power Forecasting Method for Operation Revenue Improvement of Photovoltaic-Energy Storage Plants

Graded Rolling Early Warning of Dynamic Security for Large-scale AC/DC Power Grid Considering Uncertainties on Source and Load Sides

Construction and Online Fast Update Method for Transient Stability Boundary in Parameter Space of Power System

Non-intrusive Charging Identification Method for Electric Bicycles Based on Feature Selection and Incremental Learning

Related Author

QIN Fang

XU Xiaoyuan

XU Duo

WANG Mengyuan

YAN Zheng

LU Jianyu

YAO Hongchun

YAN Jiongcheng

Related Institution

East China Branch of State Grid Corporation of China

China Electric Power Research Institute

Shanghai Non-carbon Energy Conversion and Utilization Institute

Key Laboratory of Control of Power Transmission and Conversion, Ministry of Education (Shanghai Jiao Tong University)

Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education (Shandong University)

⁰