摘要
快速准确地实现暂态稳定评估,是电力系统安全运行的重要保障。近年来迅速发展的深度学习技术已经成为解决这一问题的有效手段,然而基于神经网络的深度学习模型存在着调参困难、训练时间长和样本需求量大等缺点。文中将故障切除时刻系统的物理量作为输入特征,以系统的暂态稳定状态作为输出结果,采用集成决策树方法,构建了基于深度森林的电力系统暂态稳定评估模型。新英格兰39节点系统的算例分析表明,所提方法与深度神经网络相比,参数设置简单、训练速度更快,即使在训练样本数量较少时也能有效避免过拟合,具有良好的泛化能力。
The quick and precise implementation of transient stability assessment(TSA)is of great significance for the safe operation of power system.In recent years,the rapid development of deep learning techniques has become the effective measures to deal with this issue.However,the deep learning models based on neural networks have some drawbacks including difficulty in parameter regulation,long training time and big demand of samples.In this paper,we establish a transient stability assessment model for power system based on deep forest.Some physical characteristics at the fault clearing moment are selected as the input features,and the transient stability state of a system is considered as the output result.The simulations on New England 39-bus system show that,compared with the deep neutral network,the proposed method has advantages in simple parameter setting,rapid training speed,moreover,it can effectively avoid over-fitting and has a good generalization ability even when the number of training samples is small.
作者
李淼
雷鸣
周挺
李永龙
肖宜
严斌俊
Li Miao;Lei Ming;Zhou Ting;Li Yonglong;Xiao Yi;Yan Binjun(State Grid Hubei Electric Power Company,Wuhan 430077,China;School of Electrical Engineering and Automation,Wuhan University,Wuhan 430072,China)
出处
《电测与仪表》
北大核心
2021年第2期53-58,共6页
Electrical Measurement & Instrumentation
基金
湖北省电力公司科技项目(521505190005)。
关键词
深度学习
暂态稳定评估
深度森林
deep learning
transient stability assessment
deep forest
