Research on Photovoltaic Power Prediction Based on Similar-Day Clustering and Ivy Algorithm with CNN-BiGRU-Attention Hybrid Model

张雯涵; 艾欣; 王昊洋; 徐衍会

您当前的位置：

首页 >

文章列表页 >

Research on Photovoltaic Power Prediction Based on Similar-Day Clustering and Ivy Algorithm with CNN-BiGRU-Attention Hybrid Model

更新时间：2026-03-13

- Research on Photovoltaic Power Prediction Based on Similar-Day Clustering and Ivy Algorithm with CNN-BiGRU-Attention Hybrid Model
- Vol. 41, Issue 10, (2025)
- 作者机构：
  
  新能源电力系统全国重点实验室（华北电力大学）
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
张雯涵,艾欣,王昊洋,徐衍会.基于相似日划分与常春藤优化的CNN-BiGRU-Attention光伏功率预测研究[J].电网与清洁能源,2025,41(10):119~127

张雯涵, 艾欣, 王昊洋, et al. Research on Photovoltaic Power Prediction Based on Similar-Day Clustering and Ivy Algorithm with CNN-BiGRU-Attention Hybrid Model[J]. 2025, 41(10).
张雯涵,艾欣,王昊洋,徐衍会.基于相似日划分与常春藤优化的CNN-BiGRU-Attention光伏功率预测研究[J].电网与清洁能源,2025,41(10):119~127 DOI：

张雯涵, 艾欣, 王昊洋, et al. Research on Photovoltaic Power Prediction Based on Similar-Day Clustering and Ivy Algorithm with CNN-BiGRU-Attention Hybrid Model[J]. 2025, 41(10). DOI：

摘要

为提高光伏发电功率预测的准确度与效率，提出一种基于相似日划分和常春藤算法（ivy algorithm，IA）优化的卷积神经网络（convolutional neural network，CNN）-双向门控循环单元（bidirectional gated recurrent unit，BiGRU）-注意力机制的光伏功率预测模型。首先，构建基于动态时间规整的K中心点相似日选取方法，采用动态时间规整（dynamic time warping，DTW）距离替代传统聚类方法的欧氏距离，实现对历史数据的非线性时间序列聚类，并将其划分为晴天、阴天和雨/雪天3种类型；其次，提出基于IA优化的CNN-BiGRU-注意力机制组合预测模型，利用IA自动优化超参数，并结合CNN的空间特征提取、BiGRU的时序建模能力以及注意力机制的关键信息聚焦功能，提升模型预测性能；最后，采用新疆某光伏电站的实测数据进行算例分析。实验结果表明，所提模型在长、短期预测中均表现出更高的准确性和时效性，同时验证了改进聚类方法的有效性。

Abstract

To enhance photovoltaic power forecasting performance，a novel prediction model is developed by integrating similarity day classification with an Ivy algorithm-optimized convolutional neural network （CNN）-bidirectional gated recurrent unit （BiGRU）-attention mechanism. First，a dynamic time warping （DTW）-based k-medoids method for selecting similar days is proposed. This approach replaces the Euclidean distance in traditional clustering with DTW distance to achieve nonlinear time series clustering of the historical data，which is classified into three categories：sunny，cloudy，and rainy/snowy. Second，a combined forecasting model based on an Ivy Algorithm-optimized Convolutional Neural Network-Bidirectional Gated Recurrent Unit-Attention Mechanism is introduced.The Ivy Algorithm automatically tunes the hyperparameters，while the CNN extracts spatial features，the BiGRU captures temporal dependencies，and the attention mechanism focuses on key information，thereby collectively improving prediction performance. Finally，a case study is conducted using real operational data from a PV plant in Xinjiang. Results demonstrate the proposed model delivers significantly higher accuracy and faster prediction speed for both long-term and short-term forecasting，while also confirming the effectiveness of the enhanced clustering method.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hydraulic Turbines Vibration Fault Diagnosis by Neural Network Based on Particle Swarm Optimization

Application of Neural Network Based on Particle Swarm Optimization in Mechanical Fault Diagnosis of High-Voltage Circuit Breaker

Load Model Based on Transient Characteristics of Load in the Distribution Network

Short-Term Electricity Price Forecasting Based on Period-Decoupled Price Sequence with Grid-Connected Wind Power

Power System Operating Point State Assessment Based on Rough Set and Neural Network

Related Author

JIA Rong1

CHEN Xiao-yun1

CUI Jian-wu2

HUANG Ge1

HONG Gang2

XUE Jian-hui1

ZENG Xiao-lin1

ZI Shu-wei1

Related Institution

Northwest Hydro Consulting Engineers, CHECC

College of Electrical Engineering, Xi’an University of Technology

Department of Electrical Engineering, Xi’an University of Technology

Cangzhou Power Supply Company

College of Electrical and Electronic Engineering,Chengde Petroleum College

AI问答

⁰