Distributed photovoltaic ultra-short-term power prediction method based on combined neural network

YANG Xiyun; MA Wenbing; PENG Yan; MENG Lingzhuochao; WANG Chenxu; MA Junchao

doi:10.19666/j.rlfd.202212235

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Distributed photovoltaic ultra-short-term power prediction method based on combined neural network

更新时间：2025-09-28

- Distributed photovoltaic ultra-short-term power prediction method based on combined neural network
- Thermal Power Generation Vol. 52, Issue 8, Pages: 162-171(2023)
- 作者机构：
  
  1. 华北电力大学控制与计算机工程学院
  2. 国网浙江省电力有限公司电力科学研究院
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202212235
  CLC： TM615;TP183
- Published：2023
- 稿件说明：
移动端阅览
YANG Xiyun, MA Wenbing, PENG Yan, et al. Distributed photovoltaic ultra-short-term power prediction method based on combined neural network[J]. Thermal power generation, 2023, 52(8): 162-171.
DOI：

YANG Xiyun, MA Wenbing, PENG Yan, et al. Distributed photovoltaic ultra-short-term power prediction method based on combined neural network[J]. Thermal power generation, 2023, 52(8): 162-171. DOI： 10.19666/j.rlfd.202212235.

摘要

分布式光伏电站在电力系统中的渗透率逐年升高，为保障电网安全稳定运行，提出一种基于组合神经网络的分布式光伏超短期功率预测方法。首先利用一维卷积神经网络（1DCNN）与长短时记忆（LSTM）神经网络构建1DCNN1DCNN-LSTM组合神经网络模型，获取多位置数值天气预报（NWP)信息与历史功率信息；然后利用组合神经网络模型进行空间相关性光伏功率预测与时间序列预测，并在组合神经网络模型中加入全连接神经网络（FCNN），利用全连接神经网络对2种预测结果进行学习与权重分配，实现了分布式光伏发电功率的超短期预测。采用河北某光伏电站实测数据进行验证，验证结果表明，该方法能够有效提高分布式光伏预测精度，具有一定的实用价值。

Abstract

The penetration rate of distributed photovoltaic power stations in the power system is increasing year by year

to ensure the safe and stable operation of the power grid

a distributed photovoltaic ultra-short-term power prediction method based on combined neural networks is proposed. Firstly

a 1DCNN1DCNN-LSTM combined neural network model is constructed by using 1D convolutional neural network(1DCNN) and long short-term memory(LSTM) neural networks

to obtain multi location numerical weather prediction(NWP) information and historical power information

using combined neural network model for spatially correlated photovoltaic power prediction and time series prediction; and a fully connected neural network(FCNN) is added to the combined neural network model

which is used to learn and assign weights to the two prediction results

achieving ultra-short-term prediction of distributed photovoltaic power generation. The validation was conducted using measured data from a photovoltaic power station in Hebei

and the results showed that this method can effectively improve the accuracy of distributed photovoltaic prediction and has certain practical value.

关键词

Keywords

references

Views

513

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of solar irradiation based on interpretable deep learning

Dynamic prediction of pollutants emission from circulating fluidized bed unit based on CNN-GRU-MHA

Application of deep learning algorithm in intelligent operation and maintenance of UAVs in photovoltaic power plants

Application of machine learning in state analysis of power plant equipment

A gas path circuit diagnosis method for gas turbine based on model and data hybrid drive

Related Author

LI Ang

ZHOU Leijin

YAN Qunmin

HE Haiyu

CHENG Yongqiang

ZHANG Pengxin

WANG Weihua

GAO Mingming

Related Institution

School of Electrical Engineering, Shaanxi University of Technology

School of Control and Computer Engineering (North China Electric Power University)

National Key Laboratory of New Energy Power System (North China Electric Power University)

State Power Investment Corporation Zhuhai Hengqin Thermal Power Co., Ltd

Xi'an Thermal Power Research Institute Co., Ltd

AI问答

⁰