摘要
快速准确的电力系统扰动定位是实施及时有效的控制措施的重要前提。广域同步相量量测为快速准确的扰动定位提供了数据基础,同时刻画扰动传播的连续体动力学模型为扰动定位提供模型支撑。结合同步相量测量单元(phasor measurement unit,PMU)量测数据和扰动传播模型,该文提出一种基于模型–数据联合驱动的电网扰动定位方法。首先通过对PMU量测数据进行奇异谱分析和计算累计平方和指标来实现扰动检测。进而在部分PMU确定的子拓扑内,分别通过量测数据和传播模型提取二维时空特征。最后根据扰动传播过程中时空特征之间的相关性,提出基于度量学习的双通道三元孪生网络的扰动定位方法,仅利用部分PMU量测信息即可快速定位扰动位置,为后续抑制扰动的主动控制策略的投切奠定基础。基于IEEE 10机39节点系统,验证所提方法的有效性和鲁棒性。
Fast and accurate power system disturbance localization is an important prerequisite for power system active control. Wide-area measurement systems provides a data basis for event localization. Besides, the continuum dynamics model provides model support. Combining PMU measurement data and continuum model, a joint model and data-driven based event localization method is proposed in this paper. The disturbance is detected by singular spectrum analysis and cumulative sum of squares index. Furthermore, the partial PMU measurement information is used to form a sub-topology.The two-dimensional spatiotemporal features are constructed via the measurement data and the propagation model in the sub-topology. Finally, according to the correlation between spatiotemporal features, a double compound triplet network based on metric learning is proposed, which realizes fast event localization using less measurement information, and provides a basis for active control strategies. Based on the IEEE39-bus system, the effectiveness and robustness of the proposed method are verified.
作者
黄登一
刘灏
毕天姝
杨奇逊
HUANG Dengyi;LIU Hao;BI Tianshu;YANG Qixun(North China Branch of State Grid Corporation of China,Xicheng District,Beijing 100053,China;State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources(North China Electric Power University),ChangpingDistrict,Beijing 102206,China)
出处
《电网技术》
EI
CSCD
北大核心
2023年第3期1206-1217,共12页
Power System Technology
基金
国家自然科学基金项目(51725702,51627811)
国网北京市电力公司科技项目(SGBJDK00DWJS2100164)。
关键词
广域测量系统
扰动事件定位
奇异谱分析
模型–数据联合驱动
扰动传播
双通道三元孪生网络
wide area measurement system
disturbance event localization
singular spectrum analysis
joint model and data-driven approach
disturbance propagation
double compound triplet network
