• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 人工智能与数据挖掘 • 上一篇    下一篇

含风电场的旋转备用容量优化调度研究

孙鹤旭1,2,张航1,2,雷兆明1,2,张维1,2   

  1. (1.河北工业大学人工智能与数据科学学院,天津 300130;2.河北省控制工程技术研究中心,天津 300130)
     
  • 收稿日期:2019-03-27 修回日期:2019-05-21 出版日期:2019-12-25 发布日期:2019-12-25
  • 基金资助:

    河北省创新能力提升计划(18961604H);河北省科技计划(17214304D);河北省自然科学基金(F2018202206)

Rotating reserve capacity optimization
scheduling in wind power systems

SUN He-xu1,2,ZHANG Hang1,2,LEI Zhao-ming1,2,ZHANG Wei1,2   

  1. (1.School of Artificial Intelligence,Hebei University of Technology,Tianjin 300130;
    2.Control Engineering Technology Research Center of Hebei Province,Tianjin 300130,China)
     
  • Received:2019-03-27 Revised:2019-05-21 Online:2019-12-25 Published:2019-12-25

摘要:

为保证含风电电力系统的安全稳定与经济运行,构建了以最小化系统运行成本为目标的旋转备用容量优化调度模型。为提升模型的求解运算速度,提出一种改进的模拟植物生长算法对模型进行优化求解。针对算法在对模型求解时优化效率低、易陷入局部最优等不足做出改进,将反向学习思想引入植物生长算法,对生长点进行反向变异以扩展算法的搜索空间;通过智能变步长搜索和精英集的变异机制,保证快速寻优的同时提高求解精度。通过标准测试函数验证了改进后的算法计算速度更快,寻优能力更强。最后,在IEEE 30节点系统上进行实例验证,实验结果表明,所提出的模型能够有效地解决含风电场的旋转备用容量优化调度问题。

关键词: 含风电电力系统, 旋转备用, 模拟植物生长算法, 反向学习, 智能变步长

Abstract:

In order to ensure the safety, stability and economic operation of the wind power systems, a rotating reserve capacity optimization scheduling model with the minimum total operating cost is constructed.To improve the speed of solving the model, an improved simulated plant growth algorithm is proposed to optimize the model. In order to solve the problems such as low optimization efficiency and ease of falling into local optimum when solving the model, the reverse learning idea is introduced into the plant growth algorithm, the growth point is inversely mutated to expand the search space of the algorithm, and the intelligent variable step search and the variation mechanism of the elite set are adopted to ensure the fast optimization and improve the solution accuracy. The standard test function is used to verify that the improved algorithm has faster calculation speed and better optimization ability. Finally,the example verification is carried out on the IEEE 30 bus system. The experimental results show that the proposed model can effectively solve the rotating reserve capacity optimization scheduling problem in the wind power systems.
 

Key words: wind power system, rotating reserve, plant growth simulation algorithm, opposition-based learning, intelligent variable step