第 51 卷 第 23 期 电力系统保护与控制 Vol.51 No.23
2023 年 12 月 1 日 Power System Protection and Control Dec. 1, 2023
DOI: 10.19783/j.cnki.pspc.230654
基于图卷积神经网络的直流送端系统暂态过电压评估
刘浩宇 1
,刘挺坚 1
,刘友波 1
,丁理杰 2
,史华勃 2
(1.四川大学电气工程学院,四川 成都 610065;2.国网四川省电力科学研究院,四川 成都 610000)
摘要:随着新能源接入电力系统并通过直流送出,送端系统的暂态过电压问题逐渐突出。因此,为快速准确估计
送端系统在直流闭锁、换相失败等预想扰动场景下各直流近区节点暂态过电压严重度,提出一种基于图卷积神经
网络(graph convolutional network, GCN)的直流送端系统暂态过电压评估模型。该模型以电网发生直流故障前的潮
流状态参数与网络拓扑作为输入特征,可以同时预估电网多个关键节点(如风电场汇集节点)的暂态过电压严重度。
利用含跨区直流异步互联的两区域系统进行算例分析,验证该模型可以适应多种网架拓扑结构、不同新能源发电
占比等差异化电网运行方式,具有较强的泛化能力。同时,所提模型揭示了对过电压严重度影响最大的关键因素,
具有一定的可解释性,可为暂态过电压的预防控制提供有效指导。
关键词:直流送端系统;闭锁;换相失败;暂态过电压;深度学习;图卷积神经网络
A method for evaluating transient overvoltage of an HVDC sending-end system
based on a graph convolutional network
LIU Haoyu1
, LIU Tingjian1
, LIU Youbo1
, DING Lijie2
, SHI Huabo2
(1. College of Electrical Engineering, Sichuan University, Chengdu 610065, China; 2. State Grid Sichuan
Electric Power Research Institute, Chengdu 610000, China)
Abstract: As new energy sources are connected to the power system and sent out through DC, the transient overvoltage
problem of the sending-end system is gradually becoming prominent. Therefore, a graph convolutional network (GCN)-based
transient overvoltage evaluation model is proposed to quickly and accurately estimate the transient overvoltage severity at
each DC near-zone node in expected disturbance scenarios such as DC block and commutation failure. This model takes the
state parameters and the network topology before a DC fault occurs in the grid as input features, and can predict the transient
overvoltage severity of multiple critical nodes of the grid (e.g., wind farm aggregation node) simultaneously. A case study
using a two-region system with cross-region DC asynchronous interconnection verifies that the model can be adapted to
different grid operational modes, such as multiple grid topologies and different new energy generation ratios, and has a strong
generalisability. At the same time, the proposed model reveals the key factors that have the greatest impact on overvoltage
severity, and has a certain interpretability, which can provide effective guidance for the prevention and control of transient
overvoltage.
This work is supported by the National Natural Science Foundation of China (No. 51977133).
Key words: HVDC sending-end system; DC block; commutation failure; transient overvoltage; deep learning; graph
convolutional neural network
0 引言
我国风光新能源资源与负荷中心逆向分布,由
于新能源基地近区内负荷需求不足,“三北”风电和
西部光伏迫切需要通过建设特高压直流实现跨区外
基金项目:国家自然科学基金项目资助(51977133)
送与消纳[1-3]。截至 2022 年,我国共投运 18 回特高
压直流,总额定容量达 142.6 GW。然而,特高压直
流输电为新能源外送消纳带来显著效益的同时,亦
面临安全稳定问题[4]。当特高压直流发生换相失败、
直流闭锁等故障时,换流站内盈余无功倒送交流系
统,将引起暂态过电压问题[5-7]。当暂态过电压超过
新能源变流器耐压限值时,将进一步导致新能源