检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:汪颖[1] 李龙[1] 陈韵竹 肖先勇[1] 胡存刚[2] 郭祺[3] WANG Ying;LI Long;CHEN Yunzhu;XIAO Xianyong;HU Cungang;GUO Qi(College of Electrical Engineering,Sichuan University,Chengdu 610065,China;School of Electrical Engineering and Automation,Anhui University,Hefei 230000,China;National Electric Power Conversion and Control Engineering Technology Research Center(Hunan University),Changsha 410082,China)
机构地区:[1]四川大学电气工程学院,四川省成都市610065 [2]安徽大学电气工程与自动化学院,安徽省合肥市230000 [3]国家电能变换与控制工程技术研究中心(湖南大学),湖南省长沙市410082
出 处:《电力系统自动化》2024年第23期121-135,共15页Automation of Electric Power Systems
基 金:国家自然科学基金资助项目(52077145)。
摘 要:为提升传统线损计算方法的适用性和准确性,解决基于神经网络的线损计算方法的可解释性问题,提出了基于核心关联指标和虚拟等值电阻的台区理论线损计算模型。首先,提出了线损核心关联指标筛选方法,引用灰色关联度算法,计算线损关联指标与线损的相关性,筛选出核心线损关联指标,提高了模型的可解释性。其次,提出了物理-数据双驱动的理论线损计算模型,该模型考虑核心关联指标,以虚拟等值电阻替代传统等值电阻实现线损计算,提升了模型的适用性和准确性。然后,提出了基于二阶锥算法的参数估计方法,构建以理论线损改进值与实际值的方差最小的目标函数,以各类关联指标的临界值为约束条件,求解模型的参数。最后,应用实际监测数据和仿真模型数据,验证了文中所提方法的有效性和适用性。In order to improve the applicability and accuracy of traditional line loss calculation methods,and solve the interpretability problem of neural network based line loss calculation methods,the theoretical calculation model of line loss in distribution station areas based on core correlation indicators and virtual equivalent resistance is proposed.Firstly,a screening method for core correlation indicators of line loss is proposed.The grey relation algorithm is used to calculate the correlation between line loss correlation indicators and line loss,and to screen out core correlation indicators,thereby improving the interpretability of the model.Secondly,a physics-data driven theoretical calculation model of line loss is proposed.The model considers core correlation indicators and replaces traditional equivalent resistance with virtual equivalent resistance to achieve line loss calculation,thus improving the applicability and accuracy of the model.Then,a parameter estimation method based on the second-order cone algorithm is proposed,and an objective function is constructed to minimize the residual equation between the improvement value of theoretical line loss and the actual value.The critical values of various related indicators are used as constraints to solve the model parameters.Finally,the effectiveness and applicability of the proposed method are verified by applying actual monitoring data and simulation model data.
分 类 号:TM744[电气工程—电力系统及自动化]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.137.177.255