采用多层次特征融合SPP-net的暂态稳定多任务预测  

Multi-task prediction for transient stability using,multi-level feature fusion based SPP-net

作　　者：陈庆超 韩松[1] 毛钧毅 CHEN Qing-chao;HAN Song;MAO Jun-yi(The Electrical Engineering College,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学电气工程学院,贵阳550025

出　　处：《控制与决策》2022年第5期1279-1288,共10页Control and Decision

基　　金：国家自然科学基金项目(51567006);贵州省普通高等高校科技拔尖人才支持计划项目(2018036);贵州省科学技术基金项目(黔科合基础[2019]1100);贵州省科技创新人才团队项目([2018]5615)。

摘　　要：为提升基于卷积神经网络(CNN)的电力系统暂态稳定预测性能并呈现更全面的预测结果,提出一种基于多层次特征融合空间金字塔池化网络(MSPP-net)的暂态稳定多任务预测方法.首先,通过同步相量测量装置(PMUs)获取故障清除后各发电机功角、机端母线电压幅值及相角数据,构造出一个三维输入矩阵;其次,在CNN的基础上采用空间金字塔池化层提取高层特征的多尺度信息,通过跳跃链接获取不同卷积层多层次特征信息,并进行特征融合;最后,通过硬参数共享机制建立MSPP-net多任务学习模型,以实现暂态稳定性判断、临界发电机识别和稳定裕度预测.在IEEE 10机39母线系统、IEEE 50机145母线系统和中国某省简化系统上进行仿真验证.与传统浅层及深度学习方法相比,结果验证了所提方法的有效性和更优的预测性能,以及该方法在噪声环境或PMUs非100%覆盖条件下的适用性.In order to improve the performance of transient stability predictions based on convolutional neural networks(CNNs)and demonstrate multi-angle auxiliary decision-making information,such as transient stability classification and margin,etc.,this paper proposes a multi-task model for transient stability prediction using the multi-level feature fusion based spatial pyramid pooling convolutional network.Firstly,the short-time disturbed trajectories of each generator can be obtained by phasor measurement units(PMUs),and a three-dimension information matrix may be constructed using these trajectories.Then,the spatial pyramid pooling layer and multi-level pooling layer can be employed for extracting and fusing multi-scale and multi-level feature based on the CNN.Finally,the MSPP-net is built by hard parameter sharing,so as to achieve transient stability classication,critical generators identification and stability margin prediction.The case studies have been carried on an IEEE 39-bus system,an IEEE 145-bus system and a certain provincial power grid.The results in comparison with those results from the conventional methods show that the proposed methodology is valid,and it shows the applicability when the information of PUMs is incomplete or contains noise.

关 键 词：多层次特征融合 空间金字塔池化网络 暂态稳定预测 多任务预测 卷积神经网络 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]