Physics-informed geometric deep learning for inference tasks in power systems

被引:6
|
作者
de Jongh, Steven [1 ]
Gielnik, Frederik [1 ]
Mueller, Felicitas [1 ]
Schmit, Loris [1 ]
Suriyah, Michael [1 ]
Leibfried, Thomas [1 ]
机构
[1] Karlsruhe Inst Technol KIT, Insitute Elect Energy Syst & High Voltage Engn IEH, Karlsruhe, Germany
关键词
Approximate powerflows; Deep learning; Graph neural networks; Physics-informed neural networks; State estimation;
D O I
10.1016/j.epsr.2022.108362
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, geometric deep learning techniques are applied to learn approximate models for power system estimation and calculation tasks. Nine different graph neural network architectures from literature are compared for this purpose. The underlying graph and known physical algebraic equations are taken into account during training, which allows to learn inductive, approximate algorithms for state-and powerflow estimation. The learned models are applied on randomly generated synthetic electrical medium voltage grids that are generated based on typical grid properties. It is shown, that the learned models are able to estimate the system states with high accuracy and that the trained neural networks can be applied to previously unseen grid topologies. Different sensor configurations and assumed random sensor noise and failures are taken into account. The trained neural networks are able to estimate the states with high accuracy despite of high sensor failure rates as well as noise that is added to the system.
引用
收藏
页数:8
相关论文
共 50 条
  • [41] Physics-informed reinforcement learning for optimal control of nonlinear systems
    Wang, Yujia
    Wu, Zhe
    AICHE JOURNAL, 2024, 70 (10)
  • [42] A physics-informed deep learning closure for Lagrangian velocity gradient evolution
    Liu, Bo
    Wan, Zhen-Hua
    Lu, Xi-Yun
    Liu, Luo-Qin
    PHYSICS OF FLUIDS, 2023, 35 (11)
  • [43] Physics-Informed Deep Learning Inversion with Application to Noisy Magnetotelluric Measurements
    Liu, Wei
    Wang, He
    Xi, Zhenzhu
    Wang, Liang
    REMOTE SENSING, 2024, 16 (01)
  • [44] Physics-informed deep learning model in wind turbine response prediction
    Li, Xuan
    Zhang, Wei
    RENEWABLE ENERGY, 2022, 185 : 932 - 944
  • [45] Phase Retrieval for Fourier THz Imaging with Physics-Informed Deep Learning
    Xiang, Mingjun
    Wang, Lingxiao
    Yuan, Hui
    Zhou, Kai
    Roskos, Hartmut G.
    2022 47TH INTERNATIONAL CONFERENCE ON INFRARED, MILLIMETER AND TERAHERTZ WAVES (IRMMW-THZ 2022), 2022,
  • [46] Unsupervised physics-informed deep learning for assessing pulmonary artery hemodynamics
    Liu, Xiujian
    Xie, Baihong
    Zhang, Dong
    Zhang, Heye
    Gao, Zhifan
    de Albuquerque, Victor Hugo C.
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 257
  • [47] Multi-Objective Loss Balancing for Physics-Informed Deep Learning
    Bischof, Rafael
    Kraus, Michael A.
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2025, 439
  • [48] Phase-field modeling of fracture with physics-informed deep learning
    Manav, M.
    Molinaro, R.
    Mishra, S.
    De Lorenzis, L.
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 429
  • [49] Physics-Informed deep learning to predict flow fields in cyclone separators
    Queiroz, L. H.
    Santos, F. P.
    Oliveira, J. P.
    Souza, M. B.
    DIGITAL CHEMICAL ENGINEERING, 2021, 1
  • [50] Physics-informed deep-learning applications to experimental fluid mechanics
    Eivazi, Hamidreza
    Wang, Yuning
    Vinuesa, Ricardo
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (07)