Scholarlink

<p>Blackouts in power systems have an impact on the nation’s economy and all aspects of human existence. The crucial buses or line’s fault led to cascading failures. In this concern Transmission network reconfiguration (TNR) has drawn a lot of interest. TNR is an essential action plan stage that allows for the restoration of power systems. This article proposes Machine Learning (ML) based power flow model which can be utilised for TNR. Further, the proposed model considers Static Var Compensator and different sectionalizing switches during different configuration. Three different system case studies have been carried out considering SVC connected without reconfiguration, reconfiguration without SVC, reconfiguration with SVC network power flow using KNN, Ridge Regression, Linear Regression ML approaches to determine the power flow output. The results of the proposed approach have been compared with the existing conventional load flow techniques. The simulation reveals the similar results which shows the effectiveness of the model. IEEE 30 bus system has been used as the test system.</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

Data driven power flow analysis of SVC connected network during power network reconfiguration

  • 期刊论文

  • 发表日期：

    2025年5月30日

查看全文
  • Deblina Bhowmick,
  • Dipu Sarkar

摘要

Blackouts in power systems have an impact on the nation’s economy and all aspects of human existence. The crucial buses or line’s fault led to cascading failures. In this concern Transmission network reconfiguration (TNR) has drawn a lot of interest. TNR is an essential action plan stage that allows for the restoration of power systems. This article proposes Machine Learning (ML) based power flow model which can be utilised for TNR. Further, the proposed model considers Static Var Compensator and different sectionalizing switches during different configuration. Three different system case studies have been carried out considering SVC connected without reconfiguration, reconfiguration without SVC, reconfiguration with SVC network power flow using KNN, Ridge Regression, Linear Regression ML approaches to determine the power flow output. The results of the proposed approach have been compared with the existing conventional load flow techniques. The simulation reveals the similar results which shows the effectiveness of the model. IEEE 30 bus system has been used as the test system.