考虑风电接入的电力系统暂态稳定自适应评估  

Adaptive Assessment of Transient Stability in Power Systems Considering Wind Power Access

作　　者：别芳玫 万靖 李慧慧 陈睿 范玉宏 BIE Fangmei;WAN Jing;LI Huihui;CHEN Rui;FAN Yuhong(Economy&Technology Research Institute of State Grid Hubei Electric Power Company,Wuhan 430077,Hubei,China)

机构地区：[1]国网湖北省电力有限公司经济技术研究院,湖北武汉430077

出　　处：《电网与清洁能源》2025年第1期97-105,112,共10页Power System and Clean Energy

基　　金：国家自然科学基金项目(52007103)。

摘　　要：为了充分考虑风电出力接入对电力系统的影响,提出一种基于高斯混合模型(gaussian mixture model,GMM)和自适应深度随机配置网络(deep stochastic configuration network,DeepSCN)的暂态稳定评估(transient stability assessment,TSA)方法。考虑影响风电出力的主要因素有风速和风向等,以风速、风向为变量构建GMM,并根据GMM对样本进行聚类,得到样本分别属于每个类别的概率;训练不同聚类中心下的自适应DeepSCN评估模型,根据样本属于不同类别的概率赋予样本输入不同评估模型后评估结果的权重,根据综合结果确定样本的稳定性,从而降低风电出力不确定性对评估精度的干扰,提高评估的准确率。在改进的IEEE39节点系统上进行测试,仿真结果表明,所提方法降低了风电出力不确定对TSA的影响,提高了评估的准确度,从而证明所提TSA方法具有较好的实用性。To comprehensively account for the impact of wind power access on power systems,a novel transient stability assessment(TSA)method based on Gaussian mixture model(GMM)and adaptive Deep Random Configuration network(DeepSCN)is introduced.First,considering that wind speed and wind direction are the main factors affecting wind power output,a GMM is constructed with wind speed and wind direction as variables,and the samples are clustered according to the GMM to obtain the probability that the samples belong to each category respectively.Second,the adaptive DeepSCN evaluation model under different clustering centers is trained,and the evaluation results are weighted according to the probability that the samples belong to different categories.The stability of the samples is determined according to the comprehensive results,so as to reduce the impact of wind power output uncertainty on the evaluation accuracy and improve the accuracy of the evaluation.Finally,it is tested on the improved IEEE 39-node system,and the simulation results show that the proposed method reduces the impact of uncertain wind power output on TSA,and improves the accuracy of the evaluation,indicating that the proposed TSA method has good practicability.

关 键 词：电力系统 风电并网 高斯混合模型 聚类 自适应深度随机配置网络 暂态稳定评估 

分 类 号：TM712[电气工程—电力系统及自动化]