A Distribution Network Operational Situation Perception Technology Based on Graph Convolutional Neural Network-Enhanced Digital Twin Model
DOI:
https://doi.org/10.13052/dgaej2156-3306.4123Keywords:
Graph convolution neural network, digital twin model, distribution network, operation, situational perceptionAbstract
Currently, traditional monitoring methods based on physical models and SCADA static data struggle to achieve real-time insight, trend prediction, and proactive early warning of system operational states. To accurately perceive the operational situation and locate faults in distribution networks, this study introduces a distribution network operational situation perception approach grounded in graph convolutional neural network-enhanced digital twin model. This method enhances the traditional digital twin model with graph convolutional neural networks to achieve accurate positioning and fault analysis of distribution network operational situations. The research findings demonstrate that, compared to the traditional random forest algorithm, the new method improves positioning accuracy by approximately 10.5%. Meanwhile, the average positioning error of the new method is reduced by about 3.4 compared to the traditional random forest algorithm. Furthermore, using a single graph convolutional neural network results in a 7.5% decrease in positioning accuracy and a 2.1 increase in positioning error compared to the improved model proposed in this study. Stability testing shows that when the learning rate is set to 0.0003 or 0.0005, the accuracy of the model reaches 98% after 100 iterations of training. The robustness verification shows that under the interference scenario of injecting 2% false data, the accuracy, recall, F1 score, and precision of the model remain above 98%. Thus, employing the new improved model can significantly enhance the fault positioning accuracy for distribution network operational situations. This holds considerable research significance for achieving effective operational situation perception and positioning in distribution networks.
Downloads
References
Li Z, Xu Y, Wang P, Xiao G. Restoration of a multi-energy distribution system with joint district network reconfiguration via distributed stochastic programming [J]. IEEE Transactions on Smart Grid, 2023, 15(3): 2667–2680. DOI: 10.1109/TSG.2023.3317780.
Sheta A N, Sedhom B E, Pal A, El M M S, Eladl A A. Stability-constrained settings of directional overcurrent relays with shifted user-defined characteristics for distribution networks with ders [J]. IEEE Transactions on Power Delivery, 2024, 39(4): 2401–2413. DOI: 10.1109/TPWRD.2024.3403921.
Ebrahimi H, Yazdaninejadi A, Golshannavaz S. Transient stability enhancement in multiple-microgrid networks by cloud energy storage system alongside considering protection system limitations [J]. IET Generation, Transmission & Distribution, 2023, 17(8): 1816–1826. DOI: 10.1049/gtd2.12539.
Mishra A, Tripathy M, Ray P. A survey on different techniques for distribution network reconfiguration [J]. Journal of Engineering Research, 2024, 12(1): 173–181. DOI: 10.1016/j.jer.2023.09.001.
Heluany J B, Gkioulos V. A review on digital twins for power generation and distribution [J]. International Journal of Information Security, 2024, 23(2): 1171–1195. DOI: 10.1007/s10207-023-00784-x.
Tang F, Luo L, Guo Z, Li Y, Zhao M, Kato N. Semi-distributed network fault diagnosis based on digital twin network in highly dynamic heterogeneous networks [J]. IEEE Transactions on Mobile Computing, 2024, 24(5): 3979–3992. DOI: 10.1109/TMC.2024.3519576.
Ebtia A, Ghafouri M, Debbabi M, Kassouf M, Mohammadi A. Power distribution network topology detection using dual-graph structure graph neural network model [J]. IEEE Transactions on Smart Grid, 2024, 16(2): 1833–1850. DOI: 10.1109/TSG.2024.3512457.
Madbhavi R, Natarajan B, Srinivasan B. Graph neural network-based distribution system state estimators [J]. IEEE Transactions on Industrial Informatics, 2023, 19(12): 11630–11639. DOI: 10.1109/TII.2023.3248082.
Nguyen B L H, Vu T V, Nguyen T T, Panwar M, Hovsapian R. Spatial-temporal recurrent graph neural networks for fault diagnostics in power distribution systems [J]. IEEE Access, 2023, 11(1): 46039–46050. DOI: 10.1109/ACCESS.2023.3273292.
Meng Q, Tong X, Hussain S, Luo F, Zhou F, He Y, Li B. Enhancing distribution system stability and efficiency through multi-power supply startup optimization for new energy integration[J]. IET Generation, Transmission & Distribution, 2024, 18(21): 3487–3500. DOI: 10.1049/gtd2.13299.
Pirouzi S, Zadehbagheri M, Behzadpoor S. Optimal placement of distributed generation and distributed automation in the distribution grid based on operation, reliability, and economic objective of distribution system operator[J]. Electrical Engineering, 2024, 106(6): 7899–7912. DOI: 10.1007/s00202-024-02458-w.
Guo M F, Liu W L, Gao J H, Chen D Y. A data-enhanced high impedance fault detection method under imbalanced sample scenarios in distribution networks [J]. IEEE Transactions on Industry Applications, 2023, 59(4): 4720–4733. DOI: 10.1109/TIA.2023.3256975.
Cao H, Zhang D, Yi S. Real-Time Machine Learning-based fault Detection, Classification, and locating in large scale solar Energy-Based Systems: Digital twin simulation [J]. Solar Energy, 2023, 251(1): 77–85. DOI: 10.1016/j.solener.2022.12.042.
Khan M M S, Giraldo J, Parvania M. Real-time cyber attack localization in distribution systems using digital twin reference model [J]. IEEE Transactions on Power Delivery, 2023, 38(5): 3238–3249. DOI: 10.1109/TPWRD.2023.3296312.
Fan S, Wang X, Shi C, Cui P, Wang B. Generalizing graph neural networks on out-of-distribution graphs [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 46(1): 322–337. DOI: 10.1109/TPAMI.2023.3321097.
Gao M, Yu J, Yang Z, Zhao J. A physics-guided graph convolution neural network for optimal power flow [J]. IEEE Transactions on Power Systems, 2023, 39(1): 380–390. DOI: 10.1109/TPWRS.2023.3238377.
Vatter J, Mayer R, Jacobsen H A. The evolution of distributed systems for graph neural networks and their origin in graph processing and deep learning: A survey [J]. ACM Computing Surveys, 2023, 56(1): 1–37. DOI: 10.1145/3597428.
Wang Y, Fu W, Zhang X, Zhen Z, Wang F. Dynamic directed graph convolution network based ultra-short-term forecasting method of distributed photovoltaic power to enhance the resilience and flexibility of distribution network [J]. IET Generation, Transmission & Distribution, 2024, 18(2): 337–352. DOI: 10.1049/gtd2.12963.
Kammoun M, Kammoun A, Abid M. LSTM-AE-WLDL: Unsupervised LSTM auto-encoders for leak detection and location in water distribution networks [J]. Water Resources Management, 2023, 37(2): 731–746. DOI: 10.1007/s11269-022-03397-6.
Raghuvamsi Y, Teeparthi K. Distribution system state estimation with Transformer-Bi-LSTM-based imputation model for missing measurements [J]. Neural Computing and Applications, 2024, 36(3): 1295–1312. DOI: 10.1007/s00521-023-09097-5.
Guha D, Chatterjee R, Sikdar B. Anomaly detection using LSTM-based variational autoencoder in unsupervised data in power grid[J]. IEEE Systems Journal, 2023, 17(3): 4313–4323. DOI: 10.1109/JSYST.2023.3266554.
Liu K, Sheng W, Li Z, Liu F, Liu Q, Huang Y, Li Y. An energy optimal schedule method for distribution network considering the access of distributed generation and energy storage [J]. IET Generation, Transmission & Distribution, 2023, 17(13): 2996–3015. DOI: 10.1049/gtd2.12855.
