Uncertainty Quantification in Photovoltaic Power Output Forecasting Based on Long Short-Term Memory Neural Networks and Kernel Density Estimation

Xue Siya; Xu Yining; Liang Hongxi; LU Ganyun; Yin Yu

doi:10.13882/j.cnki.ncdqh.2603A002

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Uncertainty Quantification in Photovoltaic Power Output Forecasting Based on Long Short-Term Memory Neural Networks and Kernel Density Estimation

更新时间：2026-07-22

- Uncertainty Quantification in Photovoltaic Power Output Forecasting Based on Long Short-Term Memory Neural Networks and Kernel Density Estimation
- Rural Electrification Issue 7, Pages: 16-20, 25(2026)
- 作者机构：
  
  1. 南京工程学院电力工程学院,江苏,南京,211167
  2. 国网江苏省电力有限公司江宁区供电分公司,江苏,南京,211103
- 作者简介：
- 基金信息：
- DOI：10.13882/j.cnki.ncdqh.2603A002
  CLC： TM727
- Published：2026
- 稿件说明：
移动端阅览
薛思雅, 许以宁, 梁宏熙, 吕干云, 殷宇. 基于长短期记忆神经网络和核密度估计的不确定光伏出力预测研究[J]. 农村电气化, 2026, (7): 16-20, 25.

Xue Siya, Xu Yining, Liang Hongxi, et al. Uncertainty Quantification in Photovoltaic Power Output Forecasting Based on Long Short-Term Memory Neural Networks and Kernel Density Estimation[J]. Rural Electrification, 2026, (7): 16-20, 25.
薛思雅, 许以宁, 梁宏熙, 吕干云, 殷宇. 基于长短期记忆神经网络和核密度估计的不确定光伏出力预测研究[J]. 农村电气化, 2026, (7): 16-20, 25. DOI： 10.13882/j.cnki.ncdqh.2603A002.

Xue Siya, Xu Yining, Liang Hongxi, et al. Uncertainty Quantification in Photovoltaic Power Output Forecasting Based on Long Short-Term Memory Neural Networks and Kernel Density Estimation[J]. Rural Electrification, 2026, (7): 16-20, 25. DOI： 10.13882/j.cnki.ncdqh.2603A002.

摘要

为提升光伏出力预测精度及量化预测不确定性，提出一种基于长短期记忆神经网络（long-short term memory，LSTM）和核密度估计（kernel density estimation，KDE）的不确定光伏出力日内预测方法。首先，根据光伏出力主要受天气影响的特点，采用K-means聚类算法划分出3种天气类型；然后，将核密度区间预测和LSTM神经网络模型结合构建光伏出力日内预测模型，以LSTM神经网络点预测结果为基础，用核密度在给定置信区间下生成区间预测结果；最后，利用某真实光伏电站运行数据进行模型有效性验证。实验结果表明，所提方法提高了光伏出力的预测效果。

Abstract

To improve photovoltaic power output forecasting accuracy and quantify forecasting uncertainty

this paper proposes an intraday forecasting method for uncertain photovoltaic power output based on long short term memory (LSTM) neural networks and kernel density estimation (KDE). First

considering that photovoltaic power output is mainly affected by weather conditions

the K means clustering algorithm is used to classify three weather types. Then

an intraday photovoltaic power output forecasting model is constructed by combining interval prediction based on KDE with the LSTM model. Based on the point forecasting results of the LSTM neural network

interval forecasting results are generated using KDE under given confidence levels. Finally

the effectiveness of the model is verified using operating data from an actual photovoltaic power station. Experimental results show that the proposed method improves the forecasting performance of photovoltaic power output.

关键词

Keywords

references

王喜军,王伟,李寅松,等.考虑源-荷-储可调度资源的新能源配电网负荷频率控制策略[J].可再生能源,2025,43(11):1537-1546.

赵帅,郑骁麟,陆涛,等.含大规模分布式新能源电网的运行风险定量评估方法[J].电力工程技术,2025,44(4):147-158.

茅庭瑞,李培强.基于改进VMD和CSABO-TCN-BiGRU的中短期光伏功率预测[J].太阳能学报,2025,46(12):168-177.

张晓辉,刘钰婷,马锴,等.分布式光伏功率预测的时空特征融合方法研究[J].中国电机工程学报,2025,45(S1):231-244.

胡堃,丁磊,郭楠,等.基于深度学习算法的短期光伏功率预测[J].电工电能新技术,2025,44(12):94-106.

毕贵红,李玉洪,杨毅,等.基于DCEC-2D聚类和MB-TSMixer-BiKSA Net模型的超短期光伏功率预测[J].智慧电力,2025,53(11):99-108.

张雯涵,艾欣,王昊洋,等.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.

陈殿昊,臧海祥,刘璟璇,等.基于多模态多尺度特征的超短期光伏功率预测[J].太阳能学报,2025,46(8):472-480.

孟安波,陈嘉铭,黎湛联,等.基于相似日理论和CSO-WGPR的短期光伏发电功率预测[J].高电压技术,2021,47(4):1176-1184.

余飞鸿,陈永强,雷霞,等.基于模糊聚类和组合预测算法的光伏短期预测[J].计算机仿真,2019,36(2):447-451,457.

王涛,王旭,许野,等.计及相似日的LSTM光伏出力预测模型研究[J].太阳能学报,2023,44(8):316-323.

刘昳娟,陈云龙,刘继彦,等.基于集成学习的分布式光伏发电功率日前预测[J].中国电力,2022,55(9):38-45.

王志远,王守相,陈海文,等.考虑空间相关性采用LSTM神经网络的光伏出力短期预测方法[J].电力系统及其自动化学报,2020,32(5):78-85.

赵书强,王明雨,胡永强,等.基于不确定理论的光伏出力预测研究[J].电工技术学报,2015,30(16):213-220.

任宇路,程昱舒,王书姝,等.基于MMD-OHCP数据预处理的光伏出力超短期预测方法[J].电网与清洁能源,2025,41(2):93-99.

熊鹏飞,张赛,王宪军.基于波动特征提取的CNN-BiLSTM光伏功率短期预测[J].热能动力工程,2025,40(7):180-189.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on the Evolutionary Game and Benefit Allocation Mechanism of Source-Grid Load-Storage Entities under High Proportion Renewable Energy Scenarios

Fault Early Warning for Secondary Cabinets Based on Sensor Data and Machine Learning

Research on Adaptive Protection Strategy of Secondary Equipment in Substations Integrating Online Monitoring and Fault Prediction

Theoretical Analysis and Troubleshooting Method for Control Circuit Disconnection Faults in 10 kV Switchgear

Optimization of Site Selection and Land-use Planning Standards for 110 kV Substations Under New Power Systems: A Case Study of the Wuhan Power Grid

Related Author

No data

Related Institution

No data

AI问答

⁰