Distribution Grid Topology and Parameter Estimation Using Deep-Shallow Neural Network With Physical Consistency

被引:10
作者
Li, Haoran [1 ]
Weng, Yang [1 ]
Vittal, Vijay [1 ]
Blasch, Erik [2 ]
机构
[1] Arizona State Univ, Dept Elect Comp & Energy Engn, Tempe, AZ 85281 USA
[2] Air Force Res Lab, Informat Dept, Rome, NY 13441 USA
关键词
Mathematical models; Topology; Network topology; Load modeling; Correlation; Observability; Load flow; System identification; distribution systems; partial observability; deep neural network; reinforcement learning; SYSTEM STATE ESTIMATION; POWER; IDENTIFICATION; LIMITATIONS; LOAD;
D O I
10.1109/TSG.2023.3278702
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
To better monitor and control distribution grids, the exact knowledge of system topology and parameters is a fundamental requirement. However, topology information is usually incomplete due to limited sensors in the grid. Therefore, estimating the system parameters using partial data is a critical topic for distribution systems. Due to the high nonlinearity of unobservable system quantities and noises, Deep Neural Networks (DNNs) are widely utilized for accurate estimation. While traditional approaches either treat DNNs as a black box or embed little physical knowledge into DNNs, they cannot guarantee that the DNN model is consistent with physical equations and hence lack accuracy and interpretability. Therefore, we propose a Deep-Shallow neural Network (DSN) for distribution system estimation. The key is to create virtual nodes to represent nodes without sensors in the system, and denote a DNN to approximate missing quantities at virtual nodes. Then, the Power Flow (PF) equations can be estimated via a shallow neural network, achieving physical consistency. Isolated by virtual nodes, the whole system is decomposed into a set of reduced graphs with approximate PF equations. Likewise, we introduce a Reinforcement Learning-based search algorithm to connect the reduced grids into one connected system. Correspondingly, the DSN is fine-tuned to achieve consistency with the PF equations of the connected graph. Finally, the paper illustrates the superiority of the proposed DSN due to its physical consistency. Specifically, comprehensive experiments demonstrate the high performances of our DSN over other methods in distribution grids.
引用
收藏
页码:655 / 666
页数:12
相关论文
共 52 条
  • [1] Modern network reconfiguration techniques for service restoration in distribution systems: A step to a smarter grid
    Abu-Elanien, Ahmed E. B.
    Salama, M. M. A.
    Shaban, Khaled B.
    [J]. ALEXANDRIA ENGINEERING JOURNAL, 2018, 57 (04) : 3959 - 3967
  • [2] MEAN SQUARE ERROR OF PREDICTION AS A CRITERION FOR SELECTING VARIABLES
    ALLEN, DM
    [J]. TECHNOMETRICS, 1971, 13 (03) : 469 - &
  • [3] BACKPROPAGATION AND STOCHASTIC GRADIENT DESCENT METHOD
    AMARI, S
    [J]. NEUROCOMPUTING, 1993, 5 (4-5) : 185 - 196
  • [4] On Identification of Distribution Grids
    Ardakanian, Omid
    Wong, Vincent W. S.
    Dobbe, Roel
    Low, Steven H.
    von Meier, Alexandra
    Tomlin, Claire J.
    Yuan, Ye
    [J]. IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2019, 6 (03): : 950 - 960
  • [5] Enhancing Observability in Distribution Grids Using Smart Meter Data
    Bhela, Siddharth
    Kekatos, Vassilis
    Veeramachaneni, Sriharsha
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2018, 9 (06) : 5953 - 5961
  • [6] Bolognani S, 2013, IEEE DECIS CONTR P, P1659, DOI 10.1109/CDC.2013.6760120
  • [7] Discovering governing equations from data by sparse identification of nonlinear dynamical systems
    Brunton, Steven L.
    Proctor, Joshua L.
    Kutz, J. Nathan
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (15) : 3932 - 3937
  • [8] Inverter Probing for Power Distribution Network Topology Processing
    Cavraro, Guido
    Kekatos, Vassilis
    [J]. IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2019, 6 (03): : 980 - 992
  • [9] Voltage Analytics for Power Distribution Network Topology Verification
    Cavraro, Guido
    Kekatos, Vassilis
    Veeramachaneni, Sriharsha
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2019, 10 (01) : 1058 - 1067
  • [10] Graph Algorithms for Topology Identification Using Power Grid Probing
    Cavraro, Guido
    Kekatos, Vassilis
    [J]. IEEE CONTROL SYSTEMS LETTERS, 2018, 2 (04): : 689 - 694