Power grid operation in distribution grids with convolutional neural networks

被引:1
作者
Linke, Manuela [1 ]
Messmer, Tobias [1 ]
Micard, Gabriel [1 ]
Schubert, Gunnar [1 ]
机构
[1] HTWG Konstanz, Dept Elect Engn & Informat Technol, Alfred Wachtel Str 8, D-78462 Constance, Germany
来源
SMART ENERGY | 2025年 / 17卷
关键词
Power grid operation; Convolutional neural network; Artificial intelligence; Smart grids; Resilient energy system; Sector coupling; OPTIMIZATION;
D O I
10.1016/j.segy.2024.100169
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
The efficient and reliable operation of power grids is of great importance for ensuring astable and uninterrupted supply of electricity. Traditional grid operation techniques have faced challenges due to the increasing integration of renewable energy sources and fluctuating demand patterns caused by the electrification of the heat and mobility sector. This paper presents a novel application of convolutional neural networks in grid operation, utilising their capabilities to recognise fault patterns and finding solutions. Different input data arrangements were investigated to reflect the relationships between neighbouring nodes as imposed by the grid topology. As disturbances we consider voltage deviations exceeding 3% of the nominal voltage or transformer and line overloads. To counteract, we use tab position changes of the transformer stations as well as remote controllable switches installed in the grid. The algorithms are trained and tested on a virtual grid based on real measurement data. Our models show excellent results with test accuracy of up to 99.06% in detecting disturbances in the grid and suggest a suitable solution without performing time-consuming load flow calculations. The proposed approach holds significant potential to address the challenges associated with modern grid operation, paving the way for more efficient and sustainable energy systems.
引用
收藏
页数:12
相关论文
共 50 条
[41]   The Autonomic Power System - Network Operation and Control Beyond Smart Grids [J].
McArthur, S. D. J. ;
Taylor, P. C. ;
Ault, G. W. ;
King, J. E. ;
Athanasiadis, D. ;
Alimisis, V. D. ;
Czaplewski, M. .
2012 3RD IEEE PES INNOVATIVE SMART GRID TECHNOLOGIES EUROPE (ISGT EUROPE), 2012,
[42]   Contamination source identification in water distribution networks using convolutional neural network [J].
Lian Sun ;
Hexiang Yan ;
Kunlun Xin ;
Tao Tao .
Environmental Science and Pollution Research, 2019, 26 :36786-36797
[43]   Contamination source identification in water distribution networks using convolutional neural network [J].
Sun, Lian ;
Yan, Hexiang ;
Xin, Kunlun ;
Tao, Tao .
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2019, 26 (36) :36786-36797
[44]   SIMULATION OF DIABETIC RETINOPATHY UTILIZING CONVOLUTIONAL NEURAL NETWORKS [J].
Rajarajeswari, P. ;
Moorthy, Jayashree ;
Beg, O. Anwar .
JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY, 2022, 22 (02)
[45]   Marine Objects Recognition Using Convolutional Neural Networks [J].
Lorencin, Ivan ;
Andelic, Nikola ;
Mrzljak, Vedran ;
Car, Zlatan .
NASE MORE, 2019, 66 (03) :112-119
[46]   Location Property of Convolutional Neural Networks for Image Classification [J].
Liang, Cong ;
Zhang, Haixia ;
Yuan, Dongfeng ;
Zhang, Minggao .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (09) :3831-3845
[47]   Research and Implementation of High Computational Power for Training and Inference of Convolutional Neural Networks [J].
Li, Tianling ;
He, Bin ;
Zheng, Yangyang .
APPLIED SCIENCES-BASEL, 2023, 13 (02)
[48]   On the effects of recursive convolutional layers in convolutional neural networks [J].
Chagnon, Johan ;
Hagenbuchner, Markus ;
Tsoi, Ah Chung ;
Scarselli, Franco .
NEUROCOMPUTING, 2024, 591
[49]   Classification of operation cases in electric arc welding wachine by using deep convolutional neural networks [J].
Nogay, Hidir Selcuk ;
Akinci, Tahir Cetin .
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (12) :6657-6670
[50]   A Flexible Sparsity-Aware Accelerator with High Sensitivity and Efficient Operation for Convolutional Neural Networks [J].
Haiying Yuan ;
Zhiyong Zeng ;
Junpeng Cheng ;
Minghao Li .
Circuits, Systems, and Signal Processing, 2022, 41 :4370-4389