基于堆叠变分自动编码器的电力系统暂态稳定评估方法  

Transient stability assessment method of electric power systems based on stacked variational auto-encoder

作　　者：王怀远 陈启凡 WANG Huaiyuan;CHEN Qifan(College of Electrical Engineering and Automation,Fuzhou University,Fuzhou 350116,China)

机构地区：[1]福州大学电气工程与自动化学院

出　　处：《电力自动化设备》2019年第12期134-139,共6页Electric Power Automation Equipment

基　　金：福建省中青年教师教育科研项目(JT180018)~~

摘　　要：通过模型的构建和特征量的提取2个方面,提出了一种具有较好抗噪能力的暂态稳定性判别模型。模型的构建采用堆叠变分自动编码器,并在训练过程中引入L2正则化,加强了稳定性判别模型的泛化能力。同时,特征量的提取时刻与传统方法不同,通过设定所有发电机最大功角差值的阈值,当系统发展至该阈值时,进行特征量的提取。在IEEE 39节点系统中进行仿真验证,仿真结果表明,采用上述特征量提取方法,大幅降低了稳定性判别模型的误判率,同时设定合理的阈值并不会影响实时控制措施的启动,加强了模型的抗噪能力。From the two aspects of model construction and characteristic quantities extraction,a transient stability discriminant model with better noise immunity is proposed.A stacked variational auto-encoder is adopted to construct the assessment model.Besides,a L2 regularization method is introduced in the training process,which enhances the generalization ability of the stability discriminant model.Meanwhile,the characteristic quantities extraction time of the proposed method is different from the traditional method.By setting the threshold of the maximum power angle difference of all generators,when the system develops to the threshold,the characteristic quantities extraction is carried out.The simulative results based on IEEE 39-bus system show that the miscalculation of the stability assessment model is greatly reduced with the proposed characteristic quantities extraction method.Meanwhile the reasonable threshold will not affect the start of real-time control methods,and the noise immunity ability of the model can be also strengthened.

关 键 词：深度学习 堆叠变分自动编码器 暂态分析 稳定性 抗噪能力 特征量 电力系统 

分 类 号：TM731[电气工程—电力系统及自动化]