Collaborative Research: AMPS: Rethinking State Estimation for Power Distribution Systems in the Quantum Era

合作研究：AMPS：重新思考量子时代配电系统的状态估计

• 批准号: 2229074
• 负责人: Tuyen Vu
• 金额: $ 20万
• 依托单位: Clarkson University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-01-01 至 2025-12-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2229074&HistoricalAwards=false
• 关键词: Collaborative; Research; AMPS; Rethinking; State

The accelerated transition to renewable energy and the rapid modernization of power systems with smart Internet-of-Thing (IoT) devices have presented new integration challenges and made the systems highly vulnerable to new cyberthreats. These challenges and risks underscore the urgent need for more advanced and robust state and situation awareness that are essential to the early detection and mitigation of grid incidents. This project aims to establish a novel collection of quantum architectures, algorithms, and mathematical tools for quantum era power system state estimation (SE), a critical process in supervisory control and data acquisition (SCADA) systems. By capitalizing on the recent breakthroughs and real-world applications in quantum computing and quantum networking, the project investigates how the massive power of quantum computing can provide more rapid and accurate responses to changes in the systems. Further, the project leverages quantum networking to provide data communication with high confidentiality and integrity, raising the power grid security to the next level. This project will have broad community and societal impacts through open-source software release and the education and training of the next generation of engineers, particularly those from underrepresented groups in STEM.The goal of this project is to develop a holistic quantum-inspired framework for power state estimation, addressing the cyber risks and operational challenges for decentralized grids. Towards this goal, four main research activities include 1) Quantum network architecture - designing a network and service-oriented architecture and protocols to implement the quantum key distribution and to handle the confidential communications in smart grids; 2) Quantum computing for SE - developing timely and high-efficient solutions for power state estimation, including efficient preprocessing, optimizing Ising Hamiltonian, hardware-embedding, and annealing; and 3) Distributed quantum systems for SE - proposing a robust and trust-worthy distributed system state estimation with a support of quantum networking, quantum computing, and advanced deep learning methods. 4) Assessment - deploying, testing, and conducting comprehensive performance assessment of the proposed framework based on a quantum cyber-physical testbed to support the state estimation in smart grids enabled by quantum networking and computing technologies. This project will lay the mathematical and algorithmic foundation for the application of quantum technologies in smart grids.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

向可再生能源的加速过渡以及采用智能物联网 (IoT) 设备的电力系统的快速现代化带来了新的集成挑战，并使系统极易受到新的网络威胁。这些挑战和风险凸显了迫切需要更先进、更强大的状态和态势感知能力，这对于及早发现和缓解电网事故至关重要。该项目旨在为量子时代电力系统状态估计（SE）建立一套新颖的量子架构、算法和数学工具，这是监督控制和数据采集（SCADA）系统中的关键过程。通过利用量子计算和量子网络方面的最新突破和实际应用，该项目研究了量子计算的巨大威力如何能够对系统的变化提供更快速、更准确的响应。此外，该项目利用量子网络提供高保密性和完整性的数据通信，将电网安全提升到一个新的水平。该项目将通过开源软件发布以及对下一代工程师（特别是来自 STEM 领域代表性不足群体的工程师）的教育和培训，产生广泛的社区和社会影响。该项目的目标是开发一个整体的量子启发框架电力状态估计，解决分散式电网的网络风险和运营挑战。为了实现这一目标，四项主要研究活动包括：1）量子网络架构——设计网络和面向服务的架构和协议，以实现量子密钥分发并处理智能电网中的机密通信； 2）SE量子计算——开发及时高效的功率状态估计解决方案，包括高效预处理、优化伊辛哈密顿量、硬件嵌入和退火； 3）用于SE的分布式量子系统——在量子网络、量子计算和先进深度学习方法的支持下，提出一种稳健且值得信赖的分布式系统状态估计。 4）评估——基于量子网络物理测试平台部署、测试和对所提出的框架进行全面性能评估，以支持量子网络和计算技术支持的智能电网状态估计。该项目将为量子技术在智能电网中的应用奠定数学和算法基础。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，认为值得支持。

项目成果

Spatial-Temporal Recurrent Graph Neural Networks for Fault Diagnostics in Power Distribution Systems

用于配电系统故障诊断的时空循环图神经网络

• DOI: 10.1109/access.2023.3273292
• 发表时间: 2022-10-27
• 期刊: IEEE Access
• 影响因子: 3.9
• 作者: Bang L. H. Nguyen;T. Vu;Thai;M. Panwar;R. Hovsapian
• 通讯作者: R. Hovsapian

State Estimation for Power Distribution System Using Graph Neural Networks

使用图神经网络的配电系统状态估计

• DOI: 10.1109/ests56571.2023.10220523
• 发表时间: 2023-08-01
• 期刊: 2023 IEEE Electric Ship Technologies Symposium (ESTS)
• 作者: Quang;Bang L. H. Nguyen;T. Vu;T. Ngo
• 通讯作者: T. Ngo

1-D Convolutional Graph Convolutional Networks for Fault Detection in Distributed Energy Systems

用于分布式能源系统故障检测的一维卷积图卷积网络

• DOI: 10.1109/oncon56984.2022.10126859
• 发表时间: 2022-11-05
• 期刊: 2022 IEEE 1st Industrial Electronics Society Annual On-Line Conference (ONCON)
• 作者: Bang L. H. Nguyen;T. Vu;Thai;M. Panwar;R. Hovsapian
• 通讯作者: R. Hovsapian