一种基于配电网的拓扑实时辨识方法及系统

By constructing a smart distribution network topology identification method based on the CNN-LSTM-Attention model, the problems of insufficient accuracy and timeliness of distribution network topology identification in existing technologies are solved, and high-precision and efficient topology identification results are achieved in complex distribution networks.

CN117421571BActive Publication Date: 2026-07-17STATE GRID JIANGSU ELECTRIC POWER CO ZHENJIANG POWER SUPPLY CO
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
STATE GRID JIANGSU ELECTRIC POWER CO ZHENJIANG POWER SUPPLY CO
Filing Date
2023-10-16
Publication Date
2026-07-17

Smart Images

  • Figure CN117421571B_ABST
    Figure CN117421571B_ABST
Patent Text Reader

Abstract

本发明公开了一种基于配电网的拓扑实时辨识方法及系统，该方法针对实际配电网拓扑结构因运维频繁变动的情况，搭建了可智能辨识配电网拓扑结构的深度学习模型。首先，根据配电网系统得到整体拓扑结构，并根据得到的配电网拓扑结构从各类型拓扑结构取若干个时间断面生成节点量测数据，并进行预处理；其次，构建了融合CNN(卷积神经网络)、LSTM(长短期记忆网络)和Attention(注意力机制)的拓扑结构智能辨识模型，并结合历史量测数据对模型训练并测试；最后，在IEEE33节点配电网系统仿真算例中，验证了本发明相较于传统辨识方法在辨识精度上的优越性，实现了该模型的在线应用。
Need to check novelty before this filing date? Find Prior Art