Research on distributed photovoltaic power prediction method based on combination of spatiotemporal information

YANG Xiyun; ZHAO Zeyu; YANG Yan; ZHANG Yanfeng

doi:10.19666/j.rlfd.202204071

English

您当前的位置：

首页 >

文章列表页 >

Research on distributed photovoltaic power prediction method based on combination of spatiotemporal information

Thermal Power Generation Vol. 51, Issue 8, Pages: 64-72(2022)

更新时间：2025-09-28

- Research on distributed photovoltaic power prediction method based on combination of spatiotemporal information
- 作者机构：
  
  华北电力大学控制与计算机工程学院
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202204071
  CLC： TM615
- Published：2022
- 稿件说明：
移动端阅览
YANG Xiyun, ZHAO Zeyu, YANG Yan, et al. Research on distributed photovoltaic power prediction method based on combination of spatiotemporal information[J]. Thermal Power Generation, 2022, 51(8): 64-72.
DOI：

YANG Xiyun, ZHAO Zeyu, YANG Yan, et al. Research on distributed photovoltaic power prediction method based on combination of spatiotemporal information[J]. Thermal Power Generation, 2022, 51(8): 64-72. DOI： 10.19666/j.rlfd.202204071.

摘要

为保障电网安全稳定运行，提高光伏电站经济效益，需要进一步提升光伏功率预测的准确性。为此提出一种基于时空信息组合的分布式光伏功率预测方法。首先，基于极度梯度提升-长短时记忆神经网络（XGBoost-LSTM）集成模型，利用光伏历史数据时间序列进行预测；然后，基于最小二乘支持向量机（LSSVM）模型，利用光伏电站间的空间相关性进行预测；最后，基于信息熵的基本原理，结合多误差评价角度改进的信息熵确定2种单一预测方法的权值，构建时空信息组合预测模型。研究结果表明：基于多误差评价标准的信息熵权的XGBoost-LSTM+LSSVM模型的平均绝对误差与基于交叉熵的组合模型和基于信息熵的组合模型相比，分别下降1.6%、8.3%；结合单一预测模型的优势，组合模型可降低预测误差，基于多误差评价标准的信息熵组合模型具有更高的鲁棒性与综合性能，可提升分布式光伏功率预测的准确性。

Abstract

To ensure the stability of power grid operation and improve the economic benefits of photovoltaic power plants

the forecast accuracy of distributed photovoltaic power output needs to be further improved. Thus

a distributed photovoltaic power prediction method based on the combination of spatiotemporal information is proposed. Firstly

on the basis of XGBoost-LSTM integrated model

the time series of photovoltaic historical data are used to carry out the prediction. Then

by using the LSSVM model

the spatial correlation between photovoltaic power plants is used to conduct the prediction. Finally

according to the basisc principle of information entropy

and combing with the information entropy improved by multi-error evaluation criteria

the weight of the two prediction methods is determined

and the combined prediction model is constructed to realize spatiotemporal information combination prediction. The research result shows that

the mean absolute error of the XGBoost-LSTM + LSSVM model based on the information entropy improved by multi-error evaluation criteria decreases by 1.6% and 8.3%respectively

compared with the combined model based on cross entropy and the model based on information entropy. Combining with the advantages of a single forecasting model

the combined models can reduce the forecasting error. The information entropy combination model based on multi-error evaluation criteria has higher robustness and comprehensive performance

and can improve the accuracy of distributed photovoltaic power prediction.

关键词

Keywords

references

Views

192

下载量

CSCD

Alert me when the article has been cited

提交

Publicity Resources

Prediction model for NO_x emissions from thermal power plants based on long-short-term memory neural network

Comprehensive evaluation of gas power plant based on entropy weight grey relevance degree fused with principal component analysis

Soft measurement model of primary air flow of coal mill based on self-adaptive recursive LSSVM

Prediction model of SO₂ concentration in desulfurization system based on improved particle swarm optimization LSTM

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

Related Author

LIU He

LI Xinli

WANG Yingnan

ZHANG Tao

YANG Guotian

LIU Binghan

YANG Yunxi

FU Zhongguang

Related Institution

Key Laboratory of Power Station Equipment Status Monitoring and Control, Ministry of Education, North China Electric Power University

China Judicial Big Data Research Institute Co., Ltd

Zhejiang Zheneng Leqing Power Generation Co., Ltd

State Grid Zhejiang Electric Power Company Electric Power Science Research Institute

School of Automation Engineering, Shanghai Electric Power University

AI问答

⁰