考虑非均匀分布特性的电压暂降数据生成方法  

Voltage Sag Data Generation Considering Non-uniformed Distribution Characteristics

作　　者：汪颖[1] 蒋欣燎 陈韵竹 肖先勇[1] 胡文曦 WANG Ying;JIANG Xinliao;CHEN Yunzhu;XIAO Xianyong;HU Wenxi(College of Electrical Engineering,Sichuan University,Chengdu 610065,Sichuan Province,China)

机构地区：[1]四川大学电气工程学院,四川省成都市610065

出　　处：《电网技术》2023年第7期2936-2946,共11页Power System Technology

基　　金：国家自然科学基金项目(52077145);中央高校基本科研业务费专项资金资助。

摘　　要：电压暂降监测数据具有非均匀分布特性,影响敏感设备评估及治理决策。该文提出一种电压暂降数据生成方法,实现了考虑暂降类型非均匀以及特征非均匀分布的暂降数据生成,解决了敏感设备评估等研究中电压暂降数据不足的问题。首先,提出了基于融合判据系数的电压暂降分类方法,定义电压暂降恢复系数等特征及其计算方法,构建奇异特征直线距离系数等分类评价指标,通过融合判据对假设暂降类型进行直观评价,解决了暂降类型非均匀的问题。其次,建立电压暂降概率密度能量因子,刻画幅值、持续时间的概率密度分布特征,提出一种基于改进Star GAN(generative adversarial networks)网络的电压暂降数据生成方法,实现了按特征分布的暂降数据生成。最后,应用仿真数据和实测数据,验证所提方法的准确性、适用性和低数据依赖性。The voltage sag monitoring data,with the characteristics of non-uniformed distribution,affects the sensitive equipment evaluation and the governance decisions against the voltage sag.This paper presents a method of voltage sag data generation,which realizes the generations of the voltage sag data considering the non-uniformed distribution of the voltage sag types and characteristics.It solves the problem,at the same time,of the insufficient voltage sag data in the researches of the sensitive equipment evaluation.Firstly,this paper proposes a method for voltage sag classification based on the fusion criterion coefficient.The features of the voltage sag recovery coeeficients are defined and their calculation methods are presented.The classification evaluation indexes are constructed,such as the linear distance coefficient of the singular features and so on.The hypothetical type of the voltage sag is evaluated through the fusion criterion,overcoming the nonuniform of the voltage sag types.Secondly,this paper establishes the voltage sag probability density energy factor to describe the probability density distribution characteristics of the residual voltage and the duration.Furthermore,it proposes a voltage sag data generation method based on the improved Star GAN network to generate the voltage sag data according to the distribution of the single-event characteristics of the voltage sag.Finally,the simulation data and measured data are used to verify the accuracy,applicability and low data dependence of the proposed method.

关 键 词：电压暂降 非均匀分布特性 融合判据系数 概率密度分布 改进Star GAN网络 

分 类 号：TM721[电气工程—电力系统及自动化]