基于改进域对抗迁移学习的电力系统暂态稳定自适应评估  

Self-adaptive Transient Stability Assessment of Power System Based on Improved Domain Adversarial Transfer Learning

作　　者：申锦鹏 杨军[1] 李蕊 张俊[1] 王晓[2] 王飞跃[2] SHEN Jinpeng;YANG Jun;LI Rui;ZHANG Jun;WANG Xiao;WANG Feiyue(School of Electrical Engineering and Automation,Wuhan University,Wuhan 430072,China;State Key Laboratory for Management and Control of Complex Systems,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]武汉大学电气与自动化学院,湖北省武汉市430072 [2]中国科学院自动化研究所复杂系统管理与控制国家重点实验室,北京市100190

出　　处：《电力系统自动化》2022年第23期67-75,共9页Automation of Electric Power Systems

基　　金：国家重点研发计划资助项目(2018AAA0101502);国家电网有限公司总部科技项目(人在回路的大电网调控混合增强智能基础理论)。

摘　　要：在电力系统运行方式和拓扑结构频繁变化时,数据驱动的电力系统暂态稳定评估方法在实际系统中的应用效果会变差。针对这一问题,提出了一种基于改进域对抗迁移学习的暂态稳定自适应评估方法。根据电力系统量测数据的特点,设计了深度神经网络,并在运行场景改变后,利用梯度翻转层引入域对抗训练机制,提取源域和目标域之间的公共特征,缩小域间分布差异,减少训练样本需求。同时,同步迁移源域的模型知识并更新特征提取器参数,保证模型更新的快速性和准确性。IEEE 39节点系统和美国南卡罗莱纳州500节点电网测试结果表明,通过合理迁移原始数据以及模型,所提方法可减少目标域训练样本规模,具有快速性、通用性和较强的自适应性。For the data-driven power system transient stability assessment method, when the operation mode and topology of the power system is changing frequently, its application effect in the actual system is getting worse. To solve this problem, a selfadaptive transient stability assessment method based on the improved domain adversarial transfer learning is proposed. Based on the characteristics of the power system measurement data, a deep neural network is designed. After the operation scenario is changed, the gradient reversal layer is used to add the domain adversarial training mechanism to extract the common features between the source domain and the target domain, thus the distribution difference between the domains and the demand for training samples are reduced. At the same time, the knowledge of the source domain model is transferred, and the parameters of the feature extractor are updated synchronously to ensure the rapidity and accuracy of the model updating. The test results of the IEEE 39-bus system and the South Carolina 500-bus power grid in USA show that the proposed method can reduce the size of training samples in the target domain by reasonably transferring the original data and model, and has rapidity, versatility, and strong adaptability.

关 键 词：暂态稳定评估 迁移学习 域对抗神经网络 电力系统 

分 类 号：TM712[电气工程—电力系统及自动化] TP181[自动化与计算机技术—控制理论与控制工程]