基于相似日聚类和时序图像特征提取的光伏功率预测方法

郭威; 徐立; 汤旭晶; 赵丹阳; 陈昉林; 汪恬

doi:10.19912/j.0254-0096.tynxb.2024-2355

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于相似日聚类和时序图像特征提取的光伏功率预测方法

更新时间：2026-07-21

- 基于相似日聚类和时序图像特征提取的光伏功率预测方法
- Vol. 47, Issue 5, Pages: 650-659(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19912/j.0254-0096.tynxb.2024-2355
  CLC： TM615
- Online First：04 June 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
郭威, 徐立, 汤旭晶, et al. 基于相似日聚类和时序图像特征提取的光伏功率预测方法[J]. 2026, 47(5): 650-659.
DOI：

郭威, 徐立, 汤旭晶, et al. 基于相似日聚类和时序图像特征提取的光伏功率预测方法[J]. 2026, 47(5): 650-659. DOI： 10.19912/j.0254-0096.tynxb.2024-2355.

摘要

提出一种融合时序图像特征提取的混合深度学习光伏功率预测模型。首先

基于综合相关系数法构建多维气象特征筛选机制

实现关键影响因子的优化选择。其次

提出融合LB_Keogh距离的动态时间规整（DTW）度量方法

对K-中心点聚类算法进行改进

增强了算法的鲁棒性和聚类效率

实现了晴天、多云和阴雨天气模式的准确划分。最后

将选定的高相关性气象特征变量和历史光伏功率数据转换为二维格拉姆角场图像

输入到CSWin-Transformer模型进行功率预测。与对比模型相比

所提模型在3种典型天气工况下均表现出更高的预测精度。

Abstract

This paper introduces a hybrid deep learning PV power prediction model that leverages feature extraction from time-series images. Firstly

a multi-dimensional meteorological feature screening mechanism was developed using the comprehensive correlation coefficient method to optimize the selection of key influencing factors. Secondly

an enhanced -Medoids clustering algorithm was proposed by incorporating a dynamic time warping （DTW） distance measure based on LB_Keogh distance

which improves the robustness and clustering efficiency of the algorithm and enables precise classification of sunny

cloudy

and rainy weather patterns. Finally

the selected high-correlation meteorological variables and historical PV power data were transformed into two-dimensional Gramian angular field images and fed into the CSWin-Transformer model for power prediction. Compared with other models

the proposed approach demonstrates superior prediction accuracy under three typical weather conditions

offering a novel methodology for PV power generation prediction.

关键词

Keywords

references

STRAUB N, HERZBERG W, DITTMANN A, et al.Blending of a novel all sky imager model with persistence and a satellite based model for high-resolution irradiance nowcasting[J]. Solar energy, 2024, 269: 112319.

王迎春, 王志硕, 刘洋, 等. 基于联邦学习的海上分布式光伏超短期功率预测[J]. 控制与决策, 2025, 40(2): 441-450.

王超, 蔺红, 庞晓虹. 基于HPO-VMD和MISMA-DHKELM的短期光伏功率组合预测[J]. 太阳能学报, 2023, 44(12): 65-73.

刘源延, 孔小兵, 马乐乐, 等. 基于小波包变换与深度学习的超短期光伏功率预测[J]. 太阳能学报, 2024, 45(5): 537-546.

龙小慧, 秦际赟, 张青雷, 等. 基于相似日聚类及模态分解的短期光伏发电功率组合预测研究[J]. 电网技术, 2024, 48(7): 2948-2957.

黄泽, 毕贵红, 谢旭, 等. 基于MBI-PBI-ResNet的超短期光伏功率预测[J]. 电力系统保护与控制, 2024, 52(2): 165-176.

WU X, ZHEN Z, ZHANG J, et al.Multidimensional feature extraction based minutely solar irradiance forecasting method using all-sky images[J]. IEEE transactions on industry applications, 2024, 60(3): 4494-4504.

ZHANG X, GAO R, ZHU C, et al.Ultra-short-term prediction of regional photovoltaic power based on dynamic graph convolutional neural network[J]. Electric power systems research, 2024, 226: 109965.

路志英, 周庆霞, 李鑫, 等. 基于地基云图图像特征的光伏功率预测[J]. 电力系统及其自动化学报, 2020, 32(8): 70-76.

司志远, 杨明, 于一潇, 等. 基于卫星云图特征区域定位的超短期光伏功率预测方法[J]. 高电压技术, 2021, 47(4): 1214-1223.

杨国华, 张鸿皓, 郑豪丰, 等. 基于相似日聚类和IHGWO-WNN-AdaBoost模型的短期光伏功率预测[J]. 高电压技术, 2021, 47(4): 1185-1194.

CHEN Y, LIU X, LI X, et al.Delineating urban functional areas with building-level social media data: a dynamic time warping (DTW) distance based k-medoids method[J]. Landscape and urban planning, 2017, 160: 48-60.

KEOGH E, RATANAMAHATANA C A.Exact indexing of dynamic time warping[J]. Knowledge and information systems, 2005, 7(3): 358-386.

李莹, 涂志德, 刘艳芳, 等. 基于时间序列相似度的城市功能区识别研究[J]. 地理空间信息, 2021, 19(1): 22-29,47,4.

TIAN W, WU J, CUI H, et al.Drought prediction based on feature-based transfer learning and time series imaging[J]. IEEE access, 2021, 9: 101454-101468.

DONG X, BAO J, CHEN D, et al.CSWin Transformer: a general vision transformer backbone with cross-shaped windows[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, IEEE, 2022.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

SHORT-TERM PHOTOVOLTAIC POWER PREDICTION METHOD BASED ON MIXED GRAPH NEURAL NETWORK AND GATED RECURRENT UNIT NETWORK

基于GSS的RIME-CNN-LSTM-Attention光伏出力组合预测模型

局部遮挡下光伏组件功率损失预测模型

基于FOX-VMD联合小波阈值去噪的短期光伏功率预测研究

SHORT-TERM PHOTOVOLTAIC POWER FORECASTING BASED ON ATTENTION-GRU MODEL

Related Author

Yin Hao

Li Yidian

Xie Zhifeng

Yu Hui

Zhang Zhan

Wang Yihua

黄毅

马一力

Related Institution

School of Automation, Guangdong University of Technology

Jiangxi Vocational & Technical College of Electricity

School of Electrical and Information Engineering, Jiangsu University

Jiangsu Zhen An Power Equipment Co., Ltd.

College of Automation, Beijing Information Science and Technology University

AI问答

⁰