CPS: Synergy: Collaborative Research: Diagnostics and Prognostics Using Temporal Causal Models for Cyber Physical Systems- A Case of Smart Electric Grid

智能电网等具有社会重要性的网络物理系统(CP)的可靠运行对于一个充满活力的经济的无缝运行至关重要。持续的停电可能会导致大面积的重大停电，造成数百万美元的损失。因此，通过执行故障诊断和预测来减少这种系统性故障的有效计算技术和工具是必要的。智能电网是一种CPS：它由物理组件(包括发电、输电和配电设施)和网络组件(如智能传感器、通信网络和控制软件)组成。这笔赠款提供资金，用于开发新的方法，为智能电网建立模型，代表物理和网络组件中的故障依赖关系。这些模型将被用来建立一个综合的系统范围的解决方案，用于诊断故障和预测未来的故障传播，这可以考虑到现有的保护机制。这项工作的原创性贡献将是对大型分布式网络物理系统中多个级别的故障进行集成建模，并开发用于诊断和预测的新的、分层的、健壮的在线算法。如果成功，基于模型的故障诊断和预测技术将通过识别即将到来的故障传播和确定关键故障的发生时间来提高在大型系统中隔离故障的有效性，这将增加系统的可靠性并减少故障造成的损失。这项工作将弥合计算机科学中使用的故障管理方法和电力工程之间的差距，这些方法是随着电网变得更加智能、更加复杂和数据密集型而需要的。该项目的成果将包括建模和运行时软件原型、研究出版物和与行业合作伙伴合作的实验结果，这些结果将提供给科学界。

Reliable operation of cyber-physical systems (CPS) of societal importance such as Smart Electric Grids is critical for the seamless functioning of a vibrant economy. Sustained power outages can lead to major disruptions over large areas costing millions of dollars. Efficient computational techniques and tools that curtail such systematic failures by performing fault diagnosis and prognostics are therefore necessary. The Smart Electric Grid is a CPS: it consists of networks of physical components (including generation, transmission, and distribution facilities) interfaced with cyber components (such as intelligent sensors, communication networks, and control software). This grant provides funding to develop new methods to build models for the smart grid representing the failure dependencies in the physical and cyber components. The models will be used to build an integrated system-wide solution for diagnosing faults and predicting future failure propagations that can account for existing protection mechanisms. The original contribution of this work will be in the integrated modeling of failures on multiple levels in a large distributed cyber-physical system and the development of novel, hierarchical, robust, online algorithms for diagnostics and prognostics. If successful, the model-based fault diagnostics and prognostics techniques will improve the effectiveness of isolating failures in large systems by identifying impending failure propagations and determining the time to critical failures that will increase system reliability and reduce the losses accrued due to failures. This work will bridge the gap between fault management approaches used in computer science and power engineering that are needed as the grid becomes smarter, more complex, and more data intensive. Outcomes of this project will include modeling and run-time software prototypes, research publications, and experimental results in collaborations with industry partners that will be made available to the scientific community.