CAREER: A Multi-faceted Framework to Enable Computationally Efficient Evaluation and Automatic Design for Large-scale Economics-driven Transmission Planning

NSF CAREER项目旨在将电力系统经济驱动的传输规划的计算效率提高三个数量级，以将冗长的规划过程转变为灵活的过程，并为美国电网快速变化的能源和政策环境做好准备。该项目将为电力传输系统规划设计和评估的基本方法和计算工具带来革命性的变化。这将通过探索研究创新建模、模拟、计算和设计和集成在一起形成一个整体的解决方案。该项目的智力价值包括：(1)揭示了实现经济驱动的传输规划的三个数量级性能加速的技术途径，(2)推进对电力传输系统的理解、建模和控制方面的知识，(3)在网络理论、数学方法和计算方法方面产生新的知识，(4)在大规模网络系统扩展的设计和改进方面产生科学发现。该项目的更广泛影响包括：(1)大幅缩短经济驱动的输电规划时间表，提供更有效的输电扩展策略，并释放巨大的经济效益；(2)为基础设施规划提供自动化设计方法；(3)促进基础设施的跨部门和跨行业整合。(4)提高对输电系统在整合清洁能源和应对气候变化中的关键作用的认识。经济驱动的输电规划问题可以被描述为一个具有时序性的大规模数学优化问题。这类数学问题广泛存在于各种工程和社会问题中。尽管文献继续提供逐步提高的解决方案质量和处理非凸性的能力，但由于固有的计算挑战，这些解决方案方法无法处理或扩展到大规模的现实系统。NSF CAREER项目计划通过创新和集成网络缩减、分解和图形处理单元（GPU）计算、基于人工智能（AI）的传输选项设计以及基于参数分析的细化来解决这一问题。该项目将通过外展、游戏和课程开发、培训和软件来促进电力工程教育和培养跨学科思维。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This NSF CAREER project aims to improve the computational efficiency of economics driven transmission planning for electric power systems by up to three orders of magnitude, in order to transform lengthy planning processes toward an agile process and prepare the US power grids for rapidly changing energy and policy landscape. The project will bring transformative change in the fundamental methods and computational tools for the design and evaluation of electric power transmission system planning. This will be achieved by exploring research innovations in modeling, simulation, computing and design and integrating them together to form a holistic solution. The intellectual merits of the project include (1) revealing a technological path to achieving up to three orders of magnitude performance speedup for economics-driven transmission planning, (2) advancing knowledge in understanding, modeling and control of electrical transmission systems, (3) producing new knowledge in network theory, mathematical methods and computational methods, (4) producing scientific findings in design and refinement for large-scale networked system expansion. The broader impacts of the project include (1) dramatically shortening the timeline of economics driven transmission planning, providing more effective transmission expansion strategies, and unleashing immense economic benefits, (2) providing an automated design approach for infrastructure planning, (3) facilitating cross-sector and cross-industry integration of infrastructures, (4) raising awareness of electric transmission system’s critical role in integrating clean energy and combating climate change.The economics-driven transmission planning problem can be characterized as a large-scale mathematical optimization with chronology. Such mathematical problems are widely present in various engineering and social problems. Although the literature continues to offer gradually improved solution quality and ability to handle non-convexity, these solution methods are not tractable or scalable to large-scale realistic systems due to the inherent computational challenges. This NSF CAREER project plans to address it through innovations in and integration of network reduction, decomposition and graphics processing unit (GPU) computing, artificial intelligence (AI)-based transmission option design, and parametric analysis-based refinement. The project will promote power engineering education and foster interdisciplinary thinking through outreach, game and course development, training and software.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.