基于KPCA-RVM的电网无功储备需求计算方法研究
    点此下载全文
引用本文:袁文辉,张仰飞.基于KPCA-RVM的电网无功储备需求计算方法研究[J].计算技术与自动化,2023,(2):108-113
摘要点击次数: 124
全文下载次数: 0
作者单位
袁文辉,张仰飞 (南京工程学院 电力工程学院江苏 南京 211112) 
中文摘要:为解决传统电网无功储备需求计算过程复杂度高、耗时长的问题,提出了一种基于KPCA-RVM融合模型的电网无功储备需求快速计算方法。首先,采用核主成分分析法充分挖掘输入系统节点稳态运行特征量的有效信息,实现高维特征的降维,采用降维后的特征量作为模型的输入;其次,采用数据拟合能力较好的RVM网络对电网无功储备需求计算进行建模,构建基于RVM网络的快速计算模型;最后,采用IEEE 39节点系统数据进行仿真分析。仿真结果表明,所提方法在电网无功储备需求计算任务上具有较高计算精度且时间成本低。
中文关键词:高维特征  无功储备需求  相关向量机  核主成分分析
 
Research on Reactive Power Reserve Demand Calculation Method Based on KPCA-RVM
Abstract:In order to solve the problem of high complexity and long time consuming in the traditional reactive power reserve demand calculation process, a fast calculation method of reactive power reserve demand based on KPCA-RVM fusion model was proposed. Firstly, kernel principal component analysis was used to fully mine the effective information of the steady-state operation features of the input system nodes to achieve dimensionality reduction of high-dimensional features, and the dimensionality reduction was used as the input of the model. Secondly, the RVM network with better data fitting ability is used to model the reactive power reserve demand calculation of power grid, and a fast calculation model based on RVM network is constructed. Finally, IEEE 39-node system data is used for simulation analysis. Simulation results show that the proposed method has high computational accuracy and low time cost in the reactive power reserve requirement calculation task.
keywords:high-dimensional feature  reactive power reserve demand  correlation vector machine  kernel principal component analysis
查看全文   查看/发表评论   下载pdf阅读器