PCC点系统侧戴维南等值电路参数的估计方法研究  

Thevenin equivalent circuit parameter estimation analysis for PCC upstream system

作　　者：张坤[1] 戴传凯 孙媛媛[1] 尹志明[3] 

机构地区：[1]山东大学电气工程学院,山东济南250061 [2]国网潍坊供电公司,山东潍坊261021 [3]国网北京市电力公司培训中心,北京100041

出　　处：《电工电能新技术》2017年第4期7-15,共9页Advanced Technology of Electrical Engineering and Energy

基　　金：国家自然科学基金项目(51577108);山东省优秀中青年科学家科研奖励基金项目(BS2013NJ005)

摘　　要：电力系统中PCC点系统侧戴维南等值电路参数的准确估计对电网的安全稳定分析具有重要意义。本文首先根据系统的戴维南等值电路模型,分析了等值电路参数估计的难点在于克服系统侧和负荷侧参数同时波动的影响。进而提出利用偏最小二乘回归法列写回归方程估计系统侧的等值电源和阻抗参数。为提高准确性,文中基于变电站的电压、电流实测数据,结合电压和负荷的波动概率,提出了数据选择的指标,筛选出系统侧保持恒定而负荷侧有较大波动的数据。同时基于实测数据的分析对数据选择指标的取值规律进行了研究。本文方法可有效估计出正序、负序以及谐波频率下系统侧的戴维南等值电路参数,实际算例分析验证了所提方法的有效性。The accurate estimation of the Thevenin equivalent circuit parameters for the PCC upstream systems is of great importance to the power system security and stability analysis. Based on the Thevenin equivalent circuit mod- el, firstly, the paper pointed out that the main challenge for the system equivalent circuit parameter estimation is to overcome the impact of the synchronous variations of the system side and load side parameters. Then the partial least square method is applied to establish the regression equations in order to acquire the parameters of the system side equivalent source and impedance. Moreover, through the analysis of the fluctuation probability of the PCC volt- ages and the load impedance based on the measured substation data, new data selection indices are proposed in or- der to improve the accuracy of parameter estimation. With the help of the indices, the constant system data and the considerable variation load data can be selected out. Simultaneously the variation laws for the data selection indices are further analyzed. Based on the method proposed, the Thevenin equivalent circuit parameters for the system side under the positive sequence, negative sequence and harmonic conditions can be estimated efficiently. And the practical examples analysis verifies the validity of the method.

关 键 词：戴维南等值参数 偏最小二乘法 数据筛选 基波分量 谐波 

分 类 号：TM74[电气工程—电力系统及自动化]