Collaborative Research: Physics Informed Real-time Optimal Power Flow

合作研究：基于物理的实时最佳潮流

基本信息

批准号：
2334448
负责人：
Ferdinando Fioretto
金额：
$ 22.5万
依托单位：
University of Virginia Main Campus
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2023
资助国家：
美国
起止时间：
2023-08-01 至 2026-06-30
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2334448&HistoricalAwards=false
关键词：
Collaborative Research Physics Informed Real

项目摘要

This NSF project aims to develop a physics-informed real-time optimal power flow model using machine learning techniques to address the gap in providing close to optimal solutions for power plant outputs while considering practical dynamical constraints to avoid frequency fluctuations and grid instabilities. The intellectual merits of the project include developing techniques to integrate physical and dynamical principles in machine learning pipelines and methods to ensure scalable and reliable solutions to optimal power flow problems. The broader impacts of the project include significant long-term impacts on power grids, reducing carbon emissions and increasing grid reliability, especially under extreme weather, increased demand, and uncertainty from intermittent generation. The PIs will also engage with national laboratories and non-profit organizations to ensure that the developed model is accessible and usable by the broader community, including utilities, policymakers, and researchers. Furthermore, the project will provide opportunities for training and education in the intersection of physics, engineering, and machine learning, thereby contributing to the development of a skilled workforce in the field of energy and sustainability.The project makes four key scientific and engineering contributions: (1) Advancements in combining physics-informed neural networks with conventional feed-forward neural networks to predict solutions to optimal power flow problems in real-time, pursuing dynamic stability while also optimality. (2) Novel approaches of ensuring constraint satisfaction in the learned embedding. (3) Investigation of techniques to ensure scalability of training to large, realistically-sized networks. (4) Pursuit of model robustness by assessing model performance under measurement noise and analyzing model reliability to develop insights into high-quality approximations of the optimal power flow problem. The proposed model holds the promise to expedite the adoption of increased renewable energy into the power grid, reducing curtailment resulting from stability concerns and suboptimalities resulting from conventional heuristic droop control.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.

该 NSF 项目旨在利用机器学习技术开发一种基于物理的实时最优潮流模型，以解决在为发电厂输出提供接近最优解决方案方面的差距，同时考虑实际动态约束以避免频率波动和电网不稳定。该项目的智力优势包括开发将物理和动力学原理集成到机器学习管道和方法中的技术，以确保针对最佳潮流问题提供可扩展且可靠的解决方案。该项目的更广泛影响包括对电网的重大长期影响、减少碳排放和提高电网可靠性，特别是在极端天气、需求增加和间歇性发电的不确定性下。 PI 还将与国家实验室和非营利组织合作，确保开发的模型可供更广泛的社区（包括公用事业公司、政策制定者和研究人员）访问和使用。此外，该项目还将提供物理、工程和机器学习交叉领域的培训和教育机会，从而有助于能源和可持续发展领域熟练劳动力的发展。该项目做出了四项关键的科学和工程贡献： (1) 将物理信息神经网络与传统前馈神经网络相结合，实时预测最优潮流问题的解决方案，在追求动态稳定性的同时也追求最优性。 (2) 确保学习嵌入中约束满足的新方法。 (3) 研究确保训练可扩展至大型、实际规模的网络的技术。 (4) 通过评估测量噪声下的模型性能并分析模型可靠性来追求模型的鲁棒性，以深入了解最优潮流问题的高质量近似。拟议的模型有望加快电网中更多可再生能源的采用，减少因稳定性问题和传统启发式下垂控制导致的次优性而导致的限电。该奖项反映了 NSF 的法定使命，并通过使用评估结果被认为值得支持。基金会的智力价值和更广泛的影响审查标准。

项目成果

期刊论文数量（5）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

An Analysis of the Reliability of AC Optimal Power Flow Deep Learning Proxies

交流最优潮流深度学习代理的可靠性分析

DOI：
发表时间：
2023-09
期刊：
IEEE PES Innovative Smart Grid TechnologiesIndia
影响因子：
0
作者：
Dinh, My H.;Fioretto, Ferdinando;Mohammadian, Mostafa;Baker, Kyri
通讯作者：
Baker, Kyri

Price-Aware Deep Learning for Electricity Markets

电力市场的价格感知深度学习

DOI：
发表时间：
2024-02
期刊：
Advances in neural information processing systems
影响因子：
0
作者：
Dvorkin, Vladimir;Fioretto, Ferdinando
通讯作者：
Fioretto, Ferdinando

Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities

以决策为中心的学习：基础、最新技术、基准和未来机会

DOI：
10.48550/arxiv.2307.13565
发表时间：
2023-07-25
期刊：
ArXiv
影响因子：
0
作者：
Jayanta M;i;i;James Kotary;Senne Berden;Maxime Mulamba;Víctor Bucarey;Tias Guns;Ferdin;o Fioretto;o
通讯作者：
o

Predict-Then-Optimize by Proxy: Learning Joint Models of Prediction and Optimization

通过代理预测然后优化：学习预测和优化的联合模型

DOI：
10.48550/arxiv.2311.13087
发表时间：
2023-11-22
期刊：
ArXiv
影响因子：
0
作者：
James Kotary;Vincenzo Di Vito;Jacob Christopher;P. V. Hentenryck;Ferdin;o Fioretto;o
通讯作者：
o

Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization

分析和增强展开优化的后向收敛性