摘要
分布式状态传感器可用来实时监测配电主设备,提高电力系统稳定性和用户体验,其可靠性对电网安全稳定运行至关重要。提出一种配电主设备分布式状态传感器可靠性评估方法,基于自注意力机制的时空图卷积神经网络(Self-attention based spatial-temporal graph convolutional networks,SASTGCN)。首先,从传感器装置形式、信号传输等方面开展可靠性研究,构建了主设备状态传感器可靠性评估指标体系。然后,基于自注意力机制更擅长捕捉数据或特征的内部相关性机制,将自注意力机制融入基于注意力机制的时空图卷积神经网络(Attention based spatial-temporal graph convolutional networks,ASTGCN)中,提出一种新的可靠性评估模型。最后,通过对比实验验证了所提模型的正确性和有效性。
Using distributed state sensor to monitor main equipment of distribution network in real time is beneficial to improve power system stability and user experience.However,once the reliability of sensor device cannot be guaranteed,it may cause serious consequences such as power grid paralysis and economic loss.This paper proposed a reliability evaluation method for distributed state sensor:self-attention-based spatial-temporal graph convolutional networks(SASTGCN).First of all,the reliability of the state sensor was evaluated from its device principle and signal transmission.Then,since the self-attention mechanism is better at capturing internal correlation of data or features,which is conducive to improving the evaluation accuracy,a new reliability evaluation model is proposed by integrating it into the attention-based spatial-temporal graph convolution networks(ASTGCN).Finally,the proposed model is proved to be correct and effectives by comparative experiments.
作者
张世栋
左新斌
孙勇
邵志敏
杨珊珊
李元诚
ZHANG Shidong;ZUO Xinbin;SUN Yong;SHAO Zhimin;YANG Shanshan;LI Yuancheng(State Grid Shandong Electric Power Company Electric Power Science Research College,Jinan 250003,China;State Grid Shandong Electric Power Company,Jinan 250001,China;School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China)
出处
《华北电力大学学报（自然科学版）》
CAS
北大核心
2021年第1期33-41,共9页
Journal of North China Electric Power University：Natural Science Edition
基金
国家电网山东省公司科技项目“智能配电网层间协同关键技术研究与应用”(2020A-010).
关键词
配电主设备
传感器
可靠性
神经网络
评估模型
main equipment of distribution network
sensor
reliability
neural network
evaluation model
