基于改进时空图卷积网络的综合能源系统超短期联合预测方法

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

基于改进时空图卷积网络的综合能源系统超短期联合预测方法

更新时间：2025-10-29

- 基于改进时空图卷积网络的综合能源系统超短期联合预测方法
- Issue 4, Pages: 1-12+23+13(2025)
- 作者机构：
  
  1. 北京市能源电力信息安全工程技术研究中心(华北电力大学)
  2. 中国电力科学研究院有限公司
- 作者简介：
- 基金信息：
- DOI：
  CLC： TK01;TM715
- Published：2025
- 稿件说明：
移动端阅览
[J]. 2025, (4): 1-12+23+13.
DOI：

[J]. 2025, (4): 1-12+23+13. DOI：

摘要

面向综合能源系统中多元负荷和可再生能源出力以及天气因素之间复杂耦合关系的挖掘需求，本文提出一种基于改进时空图卷积网络的综合能源系统超短期联合预测方法。首先，将综合能源系统中的多元负荷、可再生能源出力、天气因素均映射为图结构数据形式，采用最大信息系数计算各输入变量间的相关性，将其作为节点相连边的加权值构造邻接矩阵；其次，在对时空图卷积运算改进的基础上简化了模型的参数结构；最后，建立基于Seq2Seq架构的改进时空图卷积网络模型，引入自回归层改善了非线性部分对于输入数据的敏感度。仿真结果说明相对于其它模型，本文所提模型在综合能源系统的超短期预测方面具有更佳的预测性能。

Abstract

In order to explore the complex coupling relationship among multiple loads

renewable energy output

and weather factors in integrated energy system

we propose an ultra-short-term collaborative prediction method based on improved spatio-temporal graph convolution network. Firstly

the multivariate load

renewable energy output

and weather factors in the integrated energy system are mapped into graph structured data. We employ the maximum information coefficient to calculate the correlation among input variables

which is used as the weighted value of the connected edges of nodes to construct the adjacency matrix. Secondly

we simplify the parameter structure of the model on the basis of improving the convolution operation of spatio-temporal graph. Finally

we establish an improved spatio-temporal graph convolutional network model based on Seq2Seq architecture

with an autoregressive layer introduced to improve the sensitivity of the nonlinear part to the input data. The simulation results show that

compared with other models

the proposed model exhibits superior prediction performance in the ultra-short-term forecasting for the integrated energy system.

关键词

Keywords

references

姜飞,林政阳,王文烨,王小明,奚振乾,郭祺.考虑最小平均包络熵负荷分解的最优Bagging集成超短期多元负荷预测[J].中国电机工程学报,2024(05).

王晓霞,俞敏,霍泽健,杨迪.基于近邻传播聚类与LSTNet的分布式光伏电站群短期功率预测[J].电力系统自动化,2023(06).

张鹏飞,胡博,何金松,胡展硕,刘桁宇,刘育博.基于时空图卷积网络的短期空间负荷预测方法[J].电力系统自动化,2023(13).

邢晨,张照贝.基于改进时间卷积网络的短期光伏出力概率预测方法[J].太阳能学报,2023(02).

韩富佳,王晓辉,乔骥,史梦洁,蒲天骄.基于人工智能技术的新型电力系统负荷预测研究综述[J].中国电机工程学报,2023(22).

龚钢军,蔡贺,杨佳轩,何建军.基于MIC和MA-LSTNet的超短期电力负荷预测模型[J].华北电力大学学报(自然科学版),2024(06).

冯双,彭祥佳,陈佳宁,陆友文,陈力,洪希,雷家兴,汤奕.基于时空图卷积神经网络的强迫振荡定位与传播预测[J].中国电机工程学报,2024(04).

岳伟民,刘青荣,阮应君,钱凡悦,孟华.基于MTL-GRU-Attention的综合能源系统多元负荷预测[J].电力系统及其自动化学报,2023(06).

陈灏颖,管霖.基于主动迁移学习的电力系统拓扑自适应暂态稳定评估[J].中国电机工程学报,2023(19).

鲁斌,霍泽健,俞敏.基于LSTNet-Skip的综合能源系统多元负荷超短期预测[J].中国电机工程学报,2023(06).

彭秉刚,潘振宁,余涛,邱磊鑫,苏晓,陈镇煌.图数据建模与图表示学习方法及其非侵入式负荷监测问题的应用[J].中国电机工程学报,2022(17).

吕伟杰,方一帆,程泽.基于模糊C均值聚类和样本加权卷积神经网络的日前光伏出力预测研究[J].电网技术,2022(01).

舒印彪,张丽英,张运洲,王耀华,鲁刚,元博,夏鹏.我国电力碳达峰、碳中和路径研究[J].中国工程科学,2021(06).

朱继忠,董瀚江,李盛林,陈梓瑜,骆腾燕.数据驱动的综合能源系统负荷预测综述[J].中国电机工程学报,2021(23).

王渝红,沈靖,曾琦,傅云涛,叶葳.基于谱图论和图卷积神经网络的直流电网节点电压估计研究[J].电网技术,2022(02).

王育飞,付玉超,薛花.计及太阳辐射和混沌特征提取的光伏发电功率DMCS-WNN预测法[J].中国电机工程学报,2019(S1).

史佳琪,张建华.基于多模型融合Stacking集成学习方式的负荷预测方法[J].中国电机工程学报,2019(14).

赖昌伟,黎静华,陈博,黄玉金,韦善阳.光伏发电出力预测技术研究综述[J].电工技术学报,2019(06).

高亚静,孙永健,杨文海,啜斌,梁海峰,李鹏.基于新型人体舒适度的气象敏感负荷短期预测研究[J].中国电机工程学报,2017(07).

North China Electric Power University, Changping District, Beijing, 102206, China,North China Electric Power University, Changping District, Beijing, 102206, China,North China Electric Power University, Changping District, Beijing, 102206, China,North China Electric Power University, Changping District, Beijing, 102206, China,North China Electric Power University, Changping District, Beijing, 102206, China,North China Electric Power University, Changping District, Beijing, 102206, China,Gongjiangzhixin (Beijing) Energy Technology Co., Ltd, Changping District, Beijing, 102206, China,North China Electric Power University, Changping District, Beijing, 102206, China.Economic and efficient multi-objective operation optimization of integrated energy system considering electro-thermal demand response[J].Energy,2020.

Kunjin Chen,Jun Hu,Yu Zhang,Zhanqing Yu,Jinliang He.Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks[J].IEEE Journal on Selected Areas in Communications,2020.

Jianzhnog Wu.Integrated Energy Systems[J].Applied Energy,2016.

David I. Shuman,Sunil K. Narang,Pascal Frossard,Antonio Ortega,Pierre Vandergheynst.The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains.[J].IEEE Signal Process. Mag.,2013.

David N. Reshef,Yakir A. Reshef,Hilary K. Finucane,Sharon R. Grossman,Gilean McVean,Peter J. Turnbaugh,Eric S. Lander,Michael Mitzenmacher,Pardis C. Sabeti.Detecting Novel Associations in Large Data Sets[J].Science,2011.

Scarselli Franco,Gori Marco,Tsoi Ah Chung,Hagenbuchner Markus,Monfardini Gabriele.The graph neural network model.[J].IEEE transactions on neural networks,2009.

Views

669

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Operational Optimization of Regional Integrated Energy System Considering Integrated Demand Side Response

Online Estimation of NOx Emission from Power Plant Boilers Based on Maximum Information Coefficient Variable Selection

Related Author

YI Wenfei

ZHANG Yiwei

HUANG Yongzhang

LIU Cong

WANG Wenguang

WANG Shuo

ZHAO Wenjie

Related Institution

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources,North China Electric Power University

State Grid Tianjin Electric Power Company

School of Control and Computer Engineering,North China Electric Power University

AI问答

⁰