CAREER: Risk-Sensitive Market Design for Power Systems: Scalable Learning and Pricing

风能和太阳能等可再生资源的积极整合使电力系统面临电力供应的不确定性。一个人无法控制什么时候阳光灿烂，什么时候刮风。这个NSF职业项目旨在使电力市场在其日常运营中有意义地适应这种不确定性。目前的电力市场进程对不确定性要么持被动态度，要么持保守态度。这个项目将通过采用风险敏感的设计范例带来变革性的变化--一个在两个极端之间取得健康平衡的范例。该项目的智力优势包括结合多个领域的最新进展的新颖方法，包括优化理论、机器学习和网络市场，以实现电网中的大规模可再生能源整合。该项目的更广泛影响包括研究成果在其他工程领域的广泛适用性、模拟设计的开源方法、跨学科课程开发计划以及与K-12学生和电力行业的社区参与努力。该项目的主要研究成果将包括对风险敏感的电力市场结算公式、计算这些公式的解决方案的高效算法框架，以及由这些公式得出的市场参与者的定价设计。一些研究任务的目标是电力系统的可实施解决方案。其他人将开发新的理论框架，广泛应用于其他工程背景--例如，在决策中有意义地结合历史测量和模拟数据的机制。计算机模拟的研究成果将通过GitHub和Jupyter笔记本电脑提供，以便其他研究人员可以验证和使用。将开发将电力工程与现代数据科学和经济学相结合的跨学科课程。教学创新将提高课堂参与度和沟通技能。这一奖项反映了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。

The aggressive integration of renewable resources such as wind and solar exposes the power system to uncertainty in power supply. One cannot control when the sun shines or when the wind blows. This NSF CAREER project aims to make electricity markets meaningfully accommodate such uncertainties in their daily operations. Current electricity market processes take either a reactive or a conservative view towards uncertainty. This project will bring transformative change by adopting a risk-sensitive design paradigm--one that strikes a healthy balance between the two extremes. The intellectual merits of the project include novel approaches to combine recent advances from multiple domains including optimization theory, machine learning and networked markets to enable large-scale renewable integration in the power grid. The broader impacts of the project include wide applicability of research outcomes to other engineering domains, open-source approach to simulation design, an interdisciplinary curriculum development plan, and community engagement efforts with K-12 students and the power industry. Key research outcomes of this project will include risk-sensitive electricity market clearing formulations, efficient algorithmic frameworks to compute solutions to these formulations, and pricing design for market participants derived from these formulations. Some research tasks target implementable solutions for power systems. Others will develop new theoretical frameworks that apply broadly to other engineering context - for example, mechanisms to meaningfully combine historical measurements and simulated data in decision-making. Research outputs from computer simulations will be made available via GitHub and Jupyter Notebooks to make them verifiable and usable by other researchers. Inter-disciplinary course curricula combining power engineering with modern data science and economics will be developed. Teaching innovations will enhance classroom engagement and communication skills. Special attention will be paid to undergraduate involvement in research.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.