EAGER/Collaborative Research: Real-Time: Hybrid Control Architectures Combining Physical Models and Real-time Learning

EAGER/协作研究：实时：结合物理模型和实时学习的混合控制架构

基本信息

批准号：
1839387
负责人：
Luis Duffaut Espinosa
金额：
$ 14.99万
依托单位：
University of Vermont & State Agricultural College
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2018
资助国家：
美国
起止时间：
2018-09-01 至 2020-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1839387&HistoricalAwards=false
关键词：
EAGER Collaborative Research Real Time

项目摘要

Machine learning has become a focus of many researchers as effective solution to many complex engineering problems. At its core machine learning are the methods that provide computers ways to learn using available data. Artificial neural networks (ANN) have traditionally been the backbone of machine learning methods. While these learning systems certainly have their strengths, they also have limitations in the context of control engineering. For example, physics based models often provide key physical insight into the design of control systems for power grids, autonomous vehicles, and robots. So completely discarding such models in the context of learning based control systems is often counterproductive. This EArly-concept Grant for Exploratory Research (EAGER) project aims to develop a new, foundational and innovative control architecture which combines the advantages of model based design methods with those of real-time learning. The architecture is based on recent advances in the mathematical modeling of dynamical systems. While well suited for a variety of applications in engineering, biology, and ecology, the target application is the safe and reliable control of smart grids. The latter are clearly of vital importance for future economic development and the security of the nation's constantly evolving energy distribution system. Project outcomes will provide practical solutions to complex energy management problems involving uncertain power demands, energy limits, and use of renewable resources while at the same time maintaining grid stability and reliability.The hybrid control architecture involves a given system and an assumed physical model both driven by the same control input. The measured difference between their outputs defines an error system. The key idea is to use a generic input-output representation known as a Chen-Fliess functional series to describe this unknown error system. The series coefficients are estimated in real-time via a minimum mean-square error estimator. Effectively, the conventional artificial neuron is replaced here by this new type of learning unit to approximate the error system. The control problem is solved via predictive control using the assumed model and the learned error system. The enabling technology is recent advances in the numerical approximation of Chen-Fliess series which make it possible to implement the scheme in discrete-time. The specific objectives of the project are to (1) advance the theoretical foundations that underpin real-time learning for control applications, including the cascading of these new learning units for deep learning (2) optimize and adapt the novel theoretical results for real-time control of smart grids to provide a priori performance guarantees. The main problem here lies in the uncertainty coming from the over-simplified/poorly modeled dynamics of the grid in addition to the action of renewable resources.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.

机器学习已成为许多研究人员作为许多复杂工程问题的有效解决方案的重点。在其核心机器学习上是使用可用数据提供计算机学习方法的方法。传统上，人工神经网络（ANN）是机器学习方法的骨干。尽管这些学习系统肯定具有自己的优势，但在控制工程的背景下，它们也有局限性。例如，基于物理的模型通常会为电网，自动驾驶汽车和机器人的控制系统设计提供关键的物理见解。因此，在基于学习的控制系统的背景下，完全丢弃此类模型通常会适得其反。这项对探索性研究（急切）项目的早期概念赠款旨在开发一种新的，基础和创新的控制架构，将基于模型的设计方法与实时学习的优势相结合。该体系结构基于动态系统的数学建模的最新进展。虽然非常适合工程，生物学和生态学的各种应用，但目标应用是对智能电网的安全可靠控制。后者显然对未来的经济发展和国家不断发展的能源分配系统的安全至关重要。项目成果将为复杂的能源管理问题提供实用的解决方案，这些问题涉及不确定的功率需求，能源限制和使用可再生资源，同时保持网格稳定性和可靠性。混合控制体系结构涉及给定的系统，并且假定的物理模型均由同一控制输入驱动。其输出之间的测量差定义了错误系统。关键思想是使用称为Chen-Fliess功能系列的通用输入输出表示形式来描述这个未知的错误系统。通过最小均方误差估计器实时估算串联系数。有效地，在此替换了这种新型的学习单元以近似误差系统，在此替换了常规的人工神经元。使用假定模型和学习误差系统通过预测控制解决了控制问题。促成技术是Chen-Fliess系列的数值近似值的最新进展，这使得在离散时间实施该方案成为可能。该项目的具体目标是（1）推进为控制应用程序实时学习的基础的理论基础，包括将这些新的学习单元级联以进行深度学习（2）优化并适应新颖的理论结果，以实时控制智能电网以提供先验性能保证。此处的主要问题在于，除了可再生资源的作用外，来自网格的过度模拟/模型动态的不确定性。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子优点和更广泛的影响审查标准通过评估来进行评估的。