Partial Knowledge Data-Driven Event Detection for Power Distribution Networks
Partial Knowledge Data-Driven Event Detection for Power Distribution Networks
复制标题
DOI：
10.1109/tsg.2017.2681962
复制
发表时间：
2018-09
影响因子：
9.6
通讯作者：
Yuxun Zhou;R. Arghandeh;C. Spanos
中科院分区：
文献类型：
--
作者：
Yuxun Zhou;R. Arghandeh;C. Spanos
电力系统已经纳入越来越多的非常规发电和负荷，如分布式可再生能源，电动汽车和可控负荷。感应潮流的动态性和随机性对系统诊断和控制提出了高分辨率的监测技术和敏捷的决策支持技术的要求。探讨了微相量测量单元（$\mu$ PMU）数据在配电网事件检测中的应用。提出了一种新的数据驱动的事件检测方法--隐结构半监督机（HS 3 M）。HS 3 M只需要部分专家知识：它将未标记数据和部分标记数据结合在一个大的学习目标中，以弥合监督学习，半监督学习和隐藏结构学习之间的差距。针对非凸学习目标的优化问题，通过其与凹规划的等价性，建立了一种新的全局优化算法--参数对偶优化算法。最后，在一个安装了$\mu$PMU的实际配电馈线上对所提方法进行了验证，结果证明了基于学习的事件检测框架的有效性，以及其作为电力系统安全性和可靠性核心算法之一的潜力。
The power system has been incorporating increasing amount of unconventional generations and loads, such as distributed renewable resources, electric vehicles, and controllable loads. The induced dynamic and stochastic power flow require high-resolution monitoring technology and agile decision support techniques for system diagnosis and control. This paper discusses the application of micro-phasor measurement unit ( $\mu$ PMU) data for power distribution network event detection. A novel data-driven event detection method, namely hidden structure semi-supervised machine (HS3M), is established. HS3M only requires partial expert knowledge: it combines unlabeled data and partly labeled data in a large margin learning objective to bridge the gap between supervised learning, semi-supervised learning, and learning with hidden structures. To optimize the non-convex learning objective, a novel global optimization algorithm, namely parametric dual optimization procedure, is established through its equivalence to a concave programming. Finally, the proposed method is validated on an actual distribution feeder with installed $\mu$ PMUs, and the result justifies the effectiveness of the learning-based event detection framework, as well as its potential to serve as one of the core algorithms for power system security and reliability.