Construction and Application Analysis of an Intelligent Distribution Network Identification System Based on Deep Neural Networks

Yu Ma

doi:10.4108/ew.5547

Authors

Yu Ma Qilu University of Technology

DOI:

https://doi.org/10.4108/ew.5547

Keywords:

Deep neural network, Online topology identification, Topological labels, Intelligent distribution network, Light GBM algorithm

Abstract

INTRODUCTION: At present, the communication between measuring data and network topology in the distribution system cannot be accurately established. Therefore, deep neural networks were utilized to learn the mapping relationship between the measurement data and network topology, achieving topology structure discrimination under different working conditions.

OBJECTIVES: This study aims to establish a machine learning-based Intelligent Distribution Network (IDN) online topology recognition model to address the limited measurement equipment in distribution networks and improve the accuracy and efficiency of network topology recognition.

METHODS: First, light GBM was used for feature selection to reduce computational complexity and improve learning efficiency. Then, a DNN model was constructed for topological identification and enhances the model scalability through incremental and transfer learning mechanisms. In addition, the Cross-Validation Grid Search Algorithm (GSA) was used to optimize the hyperparameters to ensure that the model can achieve the optimal performance on different data sets. Finally, a new intelligent distribution network identification model (Intelligent Distribution Electricity Network Identification System, IDENIS) was constructed.

RESULTS: The study was experimentally verified on the distribution system of IEEE 33 and PG&E 69. The experimental results showed that the accuracy of the DNN-based model reached 0.9817 on the test set, while the accuracy after feature selection only decreased by 1.3%, and the features decreased by 81.8%. In the PG&E 69 node system, the features were reduced by 85.5%, while the identification accuracy was decreased by only 0.51%. These results demonstrated that the proposed method maintained high identification accuracy while reducing the computational resource consumption.

CONCLUSION: Its efficient computing speed fully meets the real-time requirements in practical applications. This paper provides new ideas and methods for achieving intelligent distribution network topology recognition of high proportion distributed power sources.

Downloads

Download data is not yet available.

References

[1] Moise I M, Meltzer V, Pincu E. A study on pellets as an alternative source of energy for fossil fuel using adiabatic combustion calorimetry. Revue Roumaine de Chimie, 2020, 65(2):211-215.

[2] Hua W, Chen Y, Qadrdan M, Jang J, Sun H, Wu J. Applications of blockchain and artificial intelligence technologies for enabling prosumers in smart grids: A review. Renewable & sustainable energy reviews, 2022, 161(6):112308-112320.

[3] Fan D, Ren Y, Feng Q, Liu Y, Wang Z, Lin J. Restoration of smart grids: Current status, challenges, and opportunities. Renewable and Sustainable Energy Reviews, 2021, 143(5):110909-110925.

[4] Wang K, Mao W, Song H, Evinemi E I. A multi-data training method for a deep neural network to improve the separation effect of simultaneous-source data. Geophysical Prospecting, 2023, 71(1):63-84.

[5] Chen Y H, Lin W T, Liu C W.Image recognition of interference fringes in polishing by convolutional neural network with data augmentation by deep convolutional generative adversarial network. Optical Engineering, 2022, 61(4):102-114.

[6] Lee S H, Yu W F, Yang C S. ILBPSDNet: Based on improved local binary pattern shallow deep convolutional neural network for character recognition. IET image processing, 2022,16(3):669-680.

[7] Yin L, Luo S, Ma C. Expandable depth and width adaptive dynamic programming for economic smart generation control of smart grids. Energy, 2021, 232(3):120964-120936.

[8] Lee R, Venieris S I, Lane N D. Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions. ACM computing surveys, 2022, 54(8):169-198.

[9] Yang A, Su Y, Wang Z, Jin S, Ren J, Zhang X, Shen W, Clark J H. A multi-task deep learning neural network for predicting flammability-related properties from molecular structures. Green Chemistry, 2021, 23(12):4451-4465.

[10] Alizadeh Bidgoli M, Ahmadian A. Multi-stage optimal scheduling of multi-microgrids using deep-learning artificial neural network and cooperative game approach. Energy, 2022, 239(6):122036-122050.

[11] Kumari P, Toshniwal D. Long short term memory–convolutional neural network based deep hybrid approach for solar irradiance forecasting. Applied Energy, 2021, 295(8):117061-117081.

[12] Xu Z, Jiang W, Xu J, Wang D, Wang Y, Ou Z. Distribution Network Topology Identification Using Asynchronous Transformer Monitoring Data. IEEE Transactions on Industry Applications, 2023,59(1):323-331.

[13] Jiang X, Stephen B, Mcarthure S. Automated Distribution Network Fault Cause Identification With Advanced Similarity Metrics. IEEE Transactions on Power Delivery, 2021, 36(2):785-793.

[14] Zhang W, Chang Z, Zhang C, Song G, Tan W. A quick fault location and isolation method for distribution network based on adaptive reclosing. IET Generation, Transmission & Distribution, 2022, 16(4):715-723.

[15] Chen Y, Yin J, Li Z, Wei R. Location for single-phase grounding fault in distribution network based on equivalent admittance distortion rate. IET Generation, Transmission & Distribution, 2021, 15(11):1716-1729.

[16] Dua G S, Tyagi B, Kumar V. A Novel Approach for Configuration Identification of Distribution Network Utilizing μPMU Data. IEEE Transactions on Industry Applications, 2021, 57(1):857-868.

[17] Tiwari D, Bhati B S, Nagpal B, Sankhwar S, AI-Turjman F. An enhanced intelligent model: To protect marine IoT sensor environment using ensemble machine learning approach. Ocean engineering, 2021, 242(11):110180-110190.

[18] Kunzweiler F, Biltzinger B, Greiner J, Burgess J M.Automatic detection of long-duration transients in Fermi-GBM data. Astronomy and astrophysics, 2022,665(3):22-31.

[19] Du X, Xu H, Zhu F. Understanding the Effect of Hyperparameter Optimization on Machine Learning Models for Structure Design Problems. Computer-Aided Design, 2021, 135(5):103013-103028.

[20] Mokayed H, Quan T Z, Alkhaled L, Sivakumar V. Real-time human detection and counting system using deep learning computer vision techniques. Artificial Intelligence and Applications. 2023, 1(4): 221-229.