基于导纳回归算法的配电网台区户变关系识别方法
By constructing a linear regression model using the admittance regression algorithm, the problems of low accuracy, high cost, and poor robustness in the identification of household transformer relationships in low-voltage distribution substations are solved. This achieves high-precision identification of household transformer relationships without relying on additional hardware equipment, and is suitable for low-voltage distribution networks with complex loads and distributed energy access.
CN121959514BActive Publication Date: 2026-07-17LINXIA COUNTY ELECTRIC POWER CO
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- LINXIA COUNTY ELECTRIC POWER CO
- Filing Date
- 2026-04-01
- Publication Date
- 2026-07-17
Smart Images
Figure CN121959514B_ABST
Abstract
本申请提供了一种基于导纳回归算法的配电网台区户变关系识别方法，属于户变关系识别技术领域；解决了低压配电台区户变关系识别中存在的成本高、精度低、鲁棒性差等问题；该方法包括以下步骤：采集待识别户变关系的低压配电台区中配电变压器的三相电压、三相电流以及每个分支用户的电压、电流；分别计算变压器的总导纳和每个用户的导纳，并将计算得到的导纳进行标准化处理；构建变压器的总导纳与所有用户的导纳之间的回归模型，将回归模型中的回归系数或基于回归系数的决定系数作为台区户变关系识别的依据；采用最小二乘法估计回归系数，设定阈值判别户变关系；本申请应用于低压配电台区。
Need to check novelty before this filing date? Find Prior Art