Scholarlink

<p>In this research, A novel approach for optimizing load shedding during power system stress conditions is introduced by combining gravitational search and particle swarm optimization (GSA-PSO) with Deep Learning. This approach aims to determine the most effective load-shedding strategy for specific buses, to prevent revenue loss and voltage instability in power systems. The smallest eigenvalue sensitivity of the load flow Jacobian matrix as an indicator is used to identify the buses for load shedding. Furthermore, inequality constraints are calculated for the current operational state and the anticipated load in the next interval. To evaluate the performance of the proposed approach, experiments were conducted on two different power systems: the IEEE 30-bus and 14-bus systems. The GSAPSO-Deep Learning approach was implemented in the Python environment. The results obtained using the proposed method were compared with those of other models, as well as their variants, using statistical inference.</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

Enhancing voltage stability and load shedding optimization through a fusion of gravitational search algorithm and particle swarm optimization with deep learning

  • 期刊论文

  • 发表日期：

    2025年1月1日

查看全文
  • Masoud Ahmadipour,
  • Zaipatimah Ali,
  • Hussein Mohammed Ridha

摘要

In this research, A novel approach for optimizing load shedding during power system stress conditions is introduced by combining gravitational search and particle swarm optimization (GSA-PSO) with Deep Learning. This approach aims to determine the most effective load-shedding strategy for specific buses, to prevent revenue loss and voltage instability in power systems. The smallest eigenvalue sensitivity of the load flow Jacobian matrix as an indicator is used to identify the buses for load shedding. Furthermore, inequality constraints are calculated for the current operational state and the anticipated load in the next interval. To evaluate the performance of the proposed approach, experiments were conducted on two different power systems: the IEEE 30-bus and 14-bus systems. The GSAPSO-Deep Learning approach was implemented in the Python environment. The results obtained using the proposed method were compared with those of other models, as well as their variants, using statistical inference.