Photovoltaic power prediction based on a combined CNN-XGBoost model

LI Jiayi; ZHANG Shengyan; HE Jie

doi:10.3969/j.issn.1672-3643.2024.03.002

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Photovoltaic power prediction based on a combined CNN-XGBoost model

更新时间：2026-07-27

- Photovoltaic power prediction based on a combined CNN-XGBoost model
- Ningxia Electric Power Issue 3, (2024)
- 作者机构：
  
  1. 国网宁夏电力有限公司经济技术研究院,宁夏,银川,750001
  2. 国网宁夏电力有限公司银川供电公司,宁夏,银川,750011
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1672-3643.2024.03.002
  CLC：
- Online First：08 July 2024，
  
  Published：2024
- 稿件说明：
移动端阅览
LI Jiayi, ZHANG Shengyan, HE Jie. Photovoltaic power prediction based on a combined CNN-XGBoost model[J]. Ningxia Electric Power, 2024, (3).
DOI：

LI Jiayi, ZHANG Shengyan, HE Jie. Photovoltaic power prediction based on a combined CNN-XGBoost model[J]. Ningxia Electric Power, 2024, (3). DOI： 10.3969/j.issn.1672-3643.2024.03.002.

摘要

为提升光伏功率的预测精度，首先，对数据预处理，包括缺失值处理及归一化处理；其次，利用皮尔逊相关系数分析出与光伏功率最匹配的气象因素，减少模型的输入维度，降低模型复杂度；最后，基于卷积神经网络-极限梯度提升决策树（convolutional neural network-extreme gradient boosting，CNN-XGBoost）组合预测模型进行测试。测试结果表明本文所提模型可以降低预测值的均方根误差，有效地提升了光伏功率预测的精度。

Abstract

To enhance the accuracy of photovoltaic power forecasts

this study begins with data preprocessing

which involves missing values and normalization.Pearson correlation coefficient is then used to analyze meteorological factors that best correlate with photovoltaic power

thereby reducing the model's input dimensions and complexity.Finally

a combined predictive model is tested using a convolutional neural network and extreme gradient boosting(CNN-XGBoost)model.The test results show that the proposed model successfully enhances the accuracy of photovoltaic power forecasts by significantly reducing the root-mean-square error in predictions.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A two-stage intrusion detection method for smart grid networks based on the XGBoost-TLV model

Single-phase inverter power supply control for chemical instrumentation based on a second-order generalized integrator

Impact of AC cables on impedance measurement and oscillation analysis of renewable energy systems and engineering practice

Fault identification of high-voltage circuit breaker energy storage mechanism based on EEMD and GA-BP neural network

Physical consistency verification of power grid dispatching operations based on multi-task learning

Related Author

No data

Related Institution

No data

AI问答

⁰