Collaborative Research: RI: Small: Deep Constrained Learning for Power Systems

合作研究：RI：小型：电力系统的深度约束学习

• 批准号: 2007095
• 负责人: Pascal Van Hentenryck
• 金额: $ 25万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2007095&HistoricalAwards=false
• 关键词: Collaborative; Research; RI; Small; Deep

In the last two decades, artificial intelligence has achieved remarkable progress in a variety of disciplines such as computer vision and natural language understanding. This project aims at leveraging robust artificial intelligence for transforming the electrical power grid, the largest machine built by humankind. Indeed, the integration of substantial renewable resources in power generation raises substantial computational challenges and, in particular, the solving of complex optimization problems with increased frequency. The project proposes a new paradigm, Deep Constrained Learning, to solve these large-scale optimization problems in real time, while ensuring efficient and reliable grid operations. If successful, the project may fundamentally transform how the grid is operated and bring significant economic and environmental benefits. While the development of Deep Constrained Learning is grounded in energy applications, the project findings may generalize to a broader class of engineering applications with hard physical or operational constraints.From a scientific standpoint, Deep Constrained Learning (DCL) is a tight integration of machine learning and optimization that delivers, in real time, reliable near-optimal solutions to large-scale nonconvex optimization problems. The project contributes to new scientific and engineering knowledge along two directions. It first demonstrates how DCL provides a principled way to accommodate hard constraints in deep learning by combining key methodologies from optimization into the training cycle of deep neural networks. Second, it shows how to exploit domain knowledge for model reduction, allowing DCL to handle the size and complexity of real power grids.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.

在过去的二十年里，人工智能在计算机视觉和自然语言理解等多个学科方面取得了显著的进步。该项目旨在利用强大的人工智能来改造电网，这是人类建造的最大的机器。事实上，大量可再生资源在发电中的整合带来了巨大的计算挑战，特别是以更高的频率解决复杂的优化问题。该项目提出了一种新的范式-深度约束学习，以实时解决这些大规模优化问题，同时确保高效可靠的网格运行。如果成功，该项目可能会从根本上改变电网的运营方式，并带来显著的经济和环境效益。虽然深度约束学习的发展以能源应用为基础，但该项目的研究成果可能会推广到更广泛的具有硬物理或操作约束的工程应用中。从科学的角度来看，深度约束学习(DCL)是机器学习和优化的紧密结合，它实时地为大规模非凸优化问题提供可靠的近最优解。该项目在两个方向上为新的科学和工程知识做出了贡献。它首先展示了DCL如何通过将优化的关键方法结合到深度神经网络的训练周期中来提供一种原则性的方法来适应深度学习中的硬约束。其次，它展示了如何利用领域知识进行模型简化，使DCL能够处理实际电网的规模和复杂性。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。

项目成果

Fast Approximations for Job Shop Scheduling: A Lagrangian Dual Deep Learning Method.

车间调度的快速近似：拉格朗日对偶深度学习方法。

• DOI: 10.48550/arxiv.2110.06365
• 发表时间: 2022
• 期刊: Thirty- Sixth AAAI Conference on Artificial Intelligence (AAAI-22
• 作者: James Kotary, Ferdinando Fioretto

Compact Optimization Learning for AC Optimal Power Flow

交流最优潮流的紧凑优化学习

• 发表时间: 2023
• 期刊: IEEE transactions on power systems
• 影响因子: 6.6
• 作者: Seonho Park, Wenbo Chen

Privacy-Preserving and Accountable Multi-agent Learning

• DOI: 10.5555/3463952.3464174
• 发表时间: 2021
• 作者: Anudit Nagar;Cuong Tran;Ferdinando Fioretto

Confidence-Aware Graph Neural Networks for Learning Reliability Assessment Commitments

• DOI: 10.1109/tpwrs.2023.3298735
• 发表时间: 2022-11
• 期刊: IEEE Transactions on Power Systems
• 影响因子: 6.6
• 作者: Seonho Park;Wenbo Chen;Dahyeon Han;Mathieu Tanneau;Pascal Van Hentenryck

Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach

• DOI: 10.1609/aaai.v35i11.17193
• 发表时间: 2020-09
• 期刊: ArXiv
• 作者: Cuong Tran;Ferdinando Fioretto;Pascal Van Hentenryck