Scholarlink

With the low-carbon transformation of energy and the increasing proportion of new energy connected to the power grid, the short-circuit ratio of the power grid has decreased, and the voltage support capacity of the power grid has weakened. The voltage support strength urgently needs more theoretically scientific and engineering practical quantitative evaluation indicators and calculation methods. This paper first analyzes the definition and related derivation formula of MRSCR that can take into account the mutual influence between stations. Secondly, it introduces the relevant definition of graph convolutional neural network, and constructs a model for calculating MRSCR using graph convolutional neural network according to the topological structure of the power grid. This model can quantitatively analyze the critical short-circuit ratio of multiple renewable energy stations. Finally, the GCN based method is verified on the improved Nordic system based on BPA software.

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

SCR Calculation Based on Graph Convolutional Neural Network in High-Proportion Renewable Energy Systems

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Xiaoqiang Wei,
  • Xinyan Cui,
  • Jiayi Wang,
  • Qing Liu,
  • Hao Yang

摘要

With the low-carbon transformation of energy and the increasing proportion of new energy connected to the power grid, the short-circuit ratio of the power grid has decreased, and the voltage support capacity of the power grid has weakened. The voltage support strength urgently needs more theoretically scientific and engineering practical quantitative evaluation indicators and calculation methods. This paper first analyzes the definition and related derivation formula of MRSCR that can take into account the mutual influence between stations. Secondly, it introduces the relevant definition of graph convolutional neural network, and constructs a model for calculating MRSCR using graph convolutional neural network according to the topological structure of the power grid. This model can quantitatively analyze the critical short-circuit ratio of multiple renewable energy stations. Finally, the GCN based method is verified on the improved Nordic system based on BPA software.