DDDAS-TMRP: Data-Driven Power System Operations

本研究的主要目标是开发新的算法和工具，分布式收集，共享，挖掘和利用数据的合作健康监测和脆弱性评估的电力系统在真实的时间。今天，在电力系统、系统理论和计算机科学领域存在实现这一目标的基本概念和技术，但利用它们来实现这一愿景将需要本文提出的重要的多学科协同努力。该项目旨在为监测和控制互连工程系统中的数据利用所需的必要多学科系统做出根本性贡献。该提案的重点是创建新的数据驱动工具，用于电力系统的操作和控制。应用系统包括传统的SCADA系统以及新兴的相量测量单元（PMU）数据集中器。这项工作将集中在五个具体的任务领域：基于分布式代理的系统监测;模式识别和变化检测;早期预警的签名动态分析;数据驱动的低阶安全评估建模;电力系统健康监测的自动可视化。这项工作将在若干领域产生更广泛的影响。首先，在数据操作，可视化和处理的结果将在其他领域的应用。任何严重依赖测量进行监测和控制的复杂系统都需要从广泛区域和时间范围内接收的大量数据中提取关键信息。其次，几位研究人员通过电力系统工程研究中心（PSRC）与电力行业密切合作，该研究中心是NSF工业/大学合作研究中心，旨在促进13所大学和35家公司之间的合作。该项目的结果自然会以研讨会、教程和与行业互动的形式影响这种合作。

The main objective of this research is to develop new algorithms and tools for the distributed collection, sharing, mining and harnessing of data for cooperative health monitoring and vulnerability assessment of power systems in real time. Fundamental concepts and technology for achieving this objective exist today in the areas of power systems, system theory and computer science, but harnessing them to achieve this vision will require the significant multidisciplinary concerted effort proposed here. The project aims at making fundamental contributions to the necessarilymultidisciplinary systems required for data utilization in monitoring and control of interconnectedengineering systems. The application that this proposal focuses on is the creation of new data-driven tools for electric power system operation and control. The applications systems include traditional SCADA systems as well as the emerging Phasor Measurement Unit (PMU) data concentrators. This effort will focus on five specific task areas: Distributed agent-based system monitoring; Pattern recognition and change detection; Dynamic analysis of signatures for early warning; Data-driven, low-order modeling for security assessment; Automated visualization for power system health monitoring. This work will provide a broader impact in several areas. First, the results in data manipulation, visualization, and processing will have application in other domains. Any complex system that relies heavily on measurements for monitoring and control shares the same need to extract key information from massive amounts of data received over wide areas and time scales. Second, several of the investigators work very closely with the electric power industry through the Power Systems Engineering Research Center (PSERC), an NSF Industry/University Cooperative Research Center designed to stimulate collaboration among 13 universities and 35 companies. Results from this project will naturally influence that collaboration in the form of seminars, tutorials, and interaction with industry.