CAP: AI-Assisted Supervisory Control of Wind Farm Connection to the Grid for Stability Monitoring

该项目是一个扩展人工智能能力建设试点(CAP)，重点是在加州州立大学圣马科斯分校建立和发展与人工智能相关的活动。这将通过增加一批人工智能从业者来实现，这将推动该机构人工智能支持的研究和教育的可持续扩张。在我们拥抱可再生能源的同时，我们面临着维持稳定的能源电网的挑战。人工智能(AI)可以通过增强预测能力来提高电力系统在故障发生前的意识，从而为优化利用可再生能源铺平道路。在教育方面，活动将产生自给自足的实践项目和单元培训教程，丰富计算机科学和电气工程本科生和研究生课程。该项目旨在开发新的人工智能和机器学习模型，用于风电场并网的监督控制，以进行稳定性监测。最先进的技术将功率测量转换为波形图像进行分析，这对于实时分析具有相当大的开销。相反，该项目将专注于开发创新的AI/ML模型，该模型可以直接分析原始数据，以进行准确的故障预测和检测，从而在故障或其他紧急情况下实现更好的响应。这对于维持电网稳定是至关重要的。此外，该项目将建立新的网络基础设施，以提供人工智能和电力系统的多学科研究机会。虽然风电场的振荡预测和缓解是目标问题，但同样的概念可以更广泛地应用于电网异常检测和网络安全挑战。此外，开发的AI/ML模型可能为其他资产监控应用铺平道路，如电气化交通系统和医疗监控。考虑到可以应用该方法的应用程序过多，该项目可能会产生重大的更广泛的影响。扩展人工智能计划支持少数族裔服务机构的人工智能驱动的教育和劳动力发展、基础设施和研究，以加强和多样化美国的研究和教育途径，并在STEM职业生涯中为历史上被边缘化的社区提供新的机会。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，被认为值得支持。

This project is an ExpandAI Capacity building pilot (CAP), which focuses on establishing and growing AI related activities at the California State University at San Marcos. This will be accomplished by growing a pool of AI practitioners that will drive a sustainable expansion of AI-powered research and education at the institution. As we embrace renewable energy sources, we face the challenge of maintaining a stable energy grid. Artificial Intelligence (AI) can pave the path for optimized use of renewables by enhancing prediction capabilities to increase power systems awareness before failures occur. On the educational side, activities will result in self-contained, hands-on projects and modular training tutorials that will enrich Computer Science and Electrical Engineering undergraduate and graduate curricula. The project aims to develop novel AI and machine learning models for supervisory control of wind farm connection to the grid for stability monitoring. State-of-the-art techniques convert power measurement to waveform images for analysis which has a considerable overhead for real-time analysis. This project will instead focus on developing innovative AI/ML models that can directly analyze raw data for accurate fault prediction and detection to achieve improved response during faults or other emergency conditions. This is essential for maintaining grid stability. Additionally, the project will establish new cyberinfrastructure to provide multi-disciplinary research opportunities in AI and power systems. While oscillation prediction and mitigation in wind farms is the target problem, the same concept can be applied more generally to grid anomaly detection and cybersecurity challenges. In addition, the AI/ML models developed could potentially pave the way for other asset monitoring applications, such as electrified transportation systems and healthcare monitoring. Given the plethora of applications where the approach can be applied, the project is likely to have significant broader impacts. The ExpandAI Program supports AI-powered education and workforce development, infrastructure and research at Minority Serving Institutions to strengthen and diversify U.S. research and education pathways and provide historically marginalized communities with new opportunities in STEM careers.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.