A Q-learning based model-free wide-area damping control under GPS spoofing attacks

GPS欺骗攻击下基于Q学习的无模型广域阻尼控制

• 批准号: 560831-2020
• 负责人: Wang, Xiaozhe
• 金额: $ 2.19万
• 依托单位: McGill University
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=707194
• 关键词: learning; based; model; free; wide

Ensuring the cybersecurity of modern electric power grids is critical to the social function and national security. The potential consequences of a successful large-scale cyberattack on a power grid cannot be overstated, since grid failures are not only costly but also profoundly disrupt people's daily lives and the delivery of essential services (water, food, health care, etc.). The proposed research project intends to study the impacts of one specific cyberattack, namely the global position system (GPS) spoofing attacks towards phasor measurement units (PMUs), on the wide-area damping control (WADC) of power systems and design a resilient WADC against the GPS spoofing attacks using machine learning techniques. The research outcomes will pave the way for enhancing the overall security and stability of Canadian power grids resilient to the GPS spoofing attacks. The results will also shed light on how we can defend against cyberattacks on electric power grids and minimize potential catastrophic consequences, ensuring the security and integrity of Canadian electric power grids.

保障现代电网的网络安全，对社会功能和国家安全至关重要。对电网成功进行大规模网络攻击的潜在后果怎么强调都不为过，因为电网故障不仅代价高昂，而且会严重扰乱人们的日常生活和基本服务（水、食品、医疗保健等）的提供。拟议的研究项目旨在研究一种特定的网络攻击，即对相量测量单元（PMU）的全球定位系统（GPS）欺骗攻击，对电力系统广域阻尼控制（WADC）的影响，并使用机器学习技术设计一个弹性WADC来对抗GPS欺骗攻击。研究成果将为提高加拿大电网抵御GPS欺骗攻击的整体安全性和稳定性铺平道路。研究结果还将揭示我们如何抵御对电网的网络攻击，并将潜在的灾难性后果降到最低，确保加拿大电网的安全性和完整性。