Scholarlink

<p>To address the limitations of conventional methods that depend on oversimplified line-loss analysis or single data sources—particularly their low accuracy in complex grid environments and insufficient disaster recovery capabilities—this paper proposes an intelligent topology identification system for distribution networks based on carrier communication technology. The proposed solution combines machine learning algorithms with advanced communication protocols to achieve comprehensive network modeling. By analyzing multidimensional distribution node characteristics, including transmission energy signatures and expert maintenance records, the system generates accurate topology representations. Adaptive control mechanisms are trained using these models to enable fully distributed inspection workflows. The architecture deploys carrier communication networks with optimized channel equalization, significantly improving packet routing efficiency. The experimental results demonstrate that the proposed method enhances topology coverage and network security, strengthens terminal security and other protection measures, and exhibits robust disaster recovery and backup capabilities. Compared with traditional approaches, it achieves higher recognition accuracy, improves system stability, and delivers significant overall performance advantages.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A carrier communication-based method for distribution network topology identification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月9日

查看全文
  • Hongming Ma,
  • Xin Zhao,
  • Quanfeng Geng,
  • Zihe Duan,
  • Guanglei Feng

摘要

To address the limitations of conventional methods that depend on oversimplified line-loss analysis or single data sources—particularly their low accuracy in complex grid environments and insufficient disaster recovery capabilities—this paper proposes an intelligent topology identification system for distribution networks based on carrier communication technology. The proposed solution combines machine learning algorithms with advanced communication protocols to achieve comprehensive network modeling. By analyzing multidimensional distribution node characteristics, including transmission energy signatures and expert maintenance records, the system generates accurate topology representations. Adaptive control mechanisms are trained using these models to enable fully distributed inspection workflows. The architecture deploys carrier communication networks with optimized channel equalization, significantly improving packet routing efficiency. The experimental results demonstrate that the proposed method enhances topology coverage and network security, strengthens terminal security and other protection measures, and exhibits robust disaster recovery and backup capabilities. Compared with traditional approaches, it achieves higher recognition accuracy, improves system stability, and delivers significant overall performance advantages.