Planning: Artificial Intelligence Assisted High-Performance Parallel Computing for Power System Optimization

规划：人工智能辅助高性能并行计算电力系统优化

• 批准号: 2414141
• 负责人: Lin Gong
• 金额: $ 10万
• 依托单位: Jackson State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2414141&HistoricalAwards=false
• 关键词: Planning; Artificial; Intelligence; Assisted; Performance

In the increasingly electrified society, the growing dependence on electricity poses challenges to the energy industry, particularly as transformative shifts in modern power grids unfold. The critical importance of robust power systems and their optimal operations is underscored by the need for reliable, resilient, sustainable, efficient, and affordable electric power. Addressing the complexity of large-scale, geographically distributed, and interconnected nonlinear networks in modern power system operations requires advanced computing technologies. This planning grant project aims to lay the foundation for a comprehensive research initiative, investigating how the parallel algorithms and High-Performance Computing (HPC) techniques with the assistance of Artificial Intelligence (AI) technologies can efficiently tackle complex optimization problems in power system operations. The successful outcome of this inquiry has the potential to yield billions of dollars in annual savings within the U.S. energy sector through systematic power system optimization.While recent strides have been made in parallel algorithms and HPC techniques, their consistent effectiveness falls short in meeting the stringent requirements of power system operations. Striking a flexible balance between solution quality and speed remains a challenge, coupled with limited adaptability and scalability for addressing varying attributes, sizes, or complexities of problems. This project seeks to overcome these limitations by exploring innovative strategies that leverage the power of AI. The planning grant activities will involve extensive literature reviews, pilot studies, interdisciplinary collaborations, the identification of critical issues and knowledge gaps, and the design of a comprehensive research methodology. These activities will deepen understanding in AI technologies, HPC techniques, parallel optimization, mathematical programming, and power system engineering. Particularly, they will underscore the combined benefits and applications of these techniques for developing next-generation AI-assisted High-Performance Parallel Computing (AI-HPPC) methods and tools. These efforts are also instrumental in increasing the intellectual merit and broader impacts of the planning grant, aligning the prepared full HBCU-EiR proposal with targeted NSF research funding programs, and ultimately elevating the accomplishments of the future full HBCU-EiR research project.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.

在日益电气化的社会中，对电力的日益依赖给能源行业带来了挑战，特别是随着现代电网变革的展开。对可靠、有弹性、可持续、高效和负担得起的电力的需求凸显了强大的电力系统及其最佳运行的至关重要性。解决现代电力系统运行中大规模、地理分布且互连的非线性网络的复杂性需要先进的计算技术。该规划资助项目旨在为综合研究计划奠定基础，研究并行算法和高性能计算（HPC）技术如何在人工智能（AI）技术的帮助下有效解决电力系统运行中的复杂优化问题。这项调查的成功结果有可能通过系统的电力系统优化在美国能源行业每年节省数十亿美元。虽然最近在并行算法和 HPC 技术方面取得了长足的进步，但其一致的有效性仍不足以满足严格的要求电力系统运行的要求。在解决方案质量和速度之间实现灵活的平衡仍然是一个挑战，而且解决不同属性、大小或复杂性的问题的适应性和可扩展性也有限。该项目旨在通过探索利用人工智能力量的创新策略来克服这些限制。规划资助活动将涉及广泛的文献综述、试点研究、跨学科合作、关键问题和知识差距的识别以及综合研究方法的设计。这些活动将加深对人工智能技术、高性能计算技术、并行优化、数学编程和电力系统工程的理解。特别是，他们将强调这些技术在开发下一代人工智能辅助高性能并行计算（AI-HPPC）方法和工具方面的综合优势和应用。这些努力还有助于提高规划拨款的智力价值和更广泛的影响，使准备好的完整 HBCU-EiR 提案与有针对性的 NSF 研究资助计划保持一致，并最终提升未来完整 HBCU-EiR 研究项目的成就。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。