DAE-PINN: a physics-informed neural network model for simulating differential algebraic equations with application to power networks

DAE-PINN: a physics-informed neural network model for simulating differential algebraic equations with application to power networks
复制标题

DAE-PINN:一种基于物理的神经网络模型,用于模拟微分代数方程并应用于电力网络

DOI:
10.1007/s00521-022-07886-y
复制
发表时间:
2023
影响因子:
6
通讯作者:
Lin, Guang
Lin, Guang
中科院分区:
计算机科学3区
文献类型:
--
作者:
Moya, Christian;Lin, Guang

文献摘要

参考文献

被引文献

相似文献

基于深度学习的代理建模正在成为学习和模拟动态系统的一种很有前途的方法。然而,深度学习方法发现学习刚性动力学非常具有挑战性。在本文中,我们开发了DAE-PINN,这是第一个有效的物理深度学习框架,用于学习和模拟非线性微分代数方程(DAE)的解轨迹。DAE用于对复杂的工程系统进行建模,例如,电力网络,并提出了一个“形式”的无限刚度,这使得学习他们的解决方案轨迹具有挑战性。我们的DAE-PINN将其有效性建立在隐式Runge-Kutta时间步进方案(专为解决DAE而设计)和物理信息神经网络(PINN)(我们训练以满足底层问题动态的深度神经网络)之间的协同作用上。此外,我们的框架(i)使用基于惩罚的方法强制神经网络满足DAE作为(近似)硬约束,以及(ii)能够模拟长期范围的DAE。我们通过学习三总线电力网络的解决方案轨迹来展示DAE-PINN的有效性和准确性。
Deep learning-based surrogate modeling is becoming a promising approach for learning and simulating dynamical systems. However, deep-learning methods find it very challenging to learn stiff dynamics. In this paper, we develop DAE-PINN, the first effective physics-informed deep-learning framework for learning and simulating the solution trajectories ofnonlinear differential-algebraic equations(DAE). DAEs are used to model complex engineering systems, e.g., power networks, and present a “form” of infinite stiffness, which makes learning their solution trajectories challenging. Our DAE-PINN bases its effectiveness on the synergy betweenimplicit Runge–Kuttatime-stepping schemes (designed specifically for solving DAEs) andphysics-informed neural networks(PINN) (deep neural networks that we train to satisfy the dynamics of the underlying problem). Furthermore, our framework (i) enforces the neural network to satisfy the DAEs as (approximate) hard constraints using a penalty-based method and (ii) enables simulating DAEs for long-time horizons. We showcase the effectiveness and accuracy of DAE-PINN by learning the solution trajectories of a three-bus power network.
一种基于多阶段深度学习的多尺度模型缩减算法
DOI: 10.1016/j.cam.2021.113506
发表时间: 2020
期刊: J. Comput. Appl. Math.
影响因子: --
作者:
Eric T. Chung;W. Leung;Sai;Zecheng Zhang
通讯作者: Zecheng Zhang
DOI: --
发表时间: 2018-01
期刊: arXiv: Dynamical Systems
影响因子: --
作者:
M. Raissi;P. Perdikaris;G. Karniadakis
通讯作者: M. Raissi;P. Perdikaris;G. Karniadakis
使用全同态加密和区块链的去中心化 VANET 隐私保护深度学习模型
DOI: --
发表时间: 2021
期刊: IEEE transactions on intelligent transportation systems (Print)
影响因子: --
作者:
Jianguo Chen;Kenli Li;Philip S. Yu
通讯作者: Philip S. Yu
DOI: 10.1073/pnas.1517384113
发表时间: 2016-04-12
影响因子: 11.1
作者:
Brunton, Steven L.;Proctor, Joshua L.;Kutz, J. Nathan
通讯作者: Kutz, J. Nathan
DOI: --
发表时间: 2020
期刊:
影响因子: --
作者:
H. Roy;E. Moudrianakis
通讯作者: E. Moudrianakis