Scholarlink

<p>This paper presents a hybrid model combining Genetic Algorithm and Particle Swarm Optimization for multi-objective scheduling optimization in power systems. The model aims to minimize power generation costs, reduce emissions, and enhance system stability. A real-time scheduling approach is incorporated, enabling dynamic adjustments to fluctuating loads and optimizing the power system through rolling-horizon rescheduling. Experimental results based on actual data from a regional power system show that the hybrid GA-PSO model reduces generation costs by 12.5%, emissions by 9.8%, and improves system stability by 15.3%. These results demonstrate the model’s effectiveness in solving multi-objective scheduling problems and its potential application in sustainable power system management.</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

Research on multi-objective scheduling optimization of power system based on hybrid model of genetic algorithm and particle swarm optimization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月15日

查看全文
  • Xia Zhao

摘要

This paper presents a hybrid model combining Genetic Algorithm and Particle Swarm Optimization for multi-objective scheduling optimization in power systems. The model aims to minimize power generation costs, reduce emissions, and enhance system stability. A real-time scheduling approach is incorporated, enabling dynamic adjustments to fluctuating loads and optimizing the power system through rolling-horizon rescheduling. Experimental results based on actual data from a regional power system show that the hybrid GA-PSO model reduces generation costs by 12.5%, emissions by 9.8%, and improves system stability by 15.3%. These results demonstrate the model’s effectiveness in solving multi-objective scheduling problems and its potential application in sustainable power system management.