Uneingeschränkter Zugang

Feeder loss estimation of transformer in long-short memory network, based on FCM clustering

Chang Liu

Chang Liu

Electric Power Research Institute of State Grid Sichuan Electric Power CompanyChengdu, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Liu, Chang
, 
Lin Xu

Lin Xu

Electric Power Research Institute of State Grid Sichuan Electric Power CompanyChengdu, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Xu, Lin
, 
Qian Xie

Qian Xie

Electric Power Research Institute of State Grid Sichuan Electric Power CompanyChengdu, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Xie, Qian
, 
Hua Zhang

Hua Zhang

Electric Power Research Institute of State Grid Sichuan Electric Power CompanyChengdu, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Zhang, Hua
, 
Hua Yang

Hua Yang

Electric Power Research Institute of State Grid Sichuan Electric Power CompanyChengdu, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Yang, Hua
, 
Shu Fang

Shu Fang

State Grid Sichuan Electric Power CompanyChengdu, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Fang, Shu
, 
Wei Wang

Wei Wang

Electric Power Research Institute of State Grid Shanxi Electric Power CompanyTaiyuan, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Wang, Wei
, 
Shixuan Lv

Shixuan Lv

Electric Power Research Institute of State Grid Shanxi Electric Power CompanyTaiyuan, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Lv, Shixuan
, 
Yinzhang Cheng

Yinzhang Cheng

Electric Power Research Institute of State Grid Shanxi Electric Power CompanyTaiyuan, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Cheng, Yinzhang
 und 
Guanliang Li

Guanliang Li

Electric Power Research Institute of State Grid Shanxi Electric Power CompanyTaiyuan, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Li, Guanliang
  
24. Sept. 2025
Feeder loss estimation of transformer in long-short memory network, based on FCM clustering's Cover Image
Über diesen Artikel
Vorheriger Artikel
Nächster Artikel
Zitieren
COVER HERUNTERLADEN
Online veröffentlicht: 24. Sept. 2025
Eingereicht: 10. Jan. 2025
Akzeptiert: 05. Mai 2025
DOI: https://doi.org/10.2478/amns-2025-0995
Schlüsselwörter
© 2025 Songyu Wu et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Method flowchart
Method flowchart

Figure 2.

Recurrent Neural Network Architecture for Long Short Term Memory Networks
Recurrent Neural Network Architecture for Long Short Term Memory Networks

Figure 3.

Multi head Attention Structure Diagram
Multi head Attention Structure Diagram

Figure 4.

Transformer Model for Long Short Term Memory
Transformer Model for Long Short Term Memory

Figure 5.

Distribution of feeder line loss rate error (First category)
Distribution of feeder line loss rate error (First category)

Figure 6.

Distribution of feeder line loss rate error (Second category)
Distribution of feeder line loss rate error (Second category)

Figure 7.

Distribution of feeder line loss rate error (Third category)
Distribution of feeder line loss rate error (Third category)

Evaluation System of Line Loss Rate Index

Dimension Index
Line characteristics Line current carrying capacity
Cable conversion rate
Capacity of distribution transform
Power supply radius
Operation parameter Average electricity consumption
Maximum load rate
Annual maximum current
Management level Meter reading accuracy
Equipment aging rate

Comparison of Line Loss Rate Estimation Errors

Model First category Second category Third category
MAE RMSE MAE RMSE MAE RMSE
GBDT 0.358 0.519 0.297 0.435 0.319 0.428
AdaBoost 0.358 0.506 0.346 0.437 0.348 0.432
XGBoost 0.361 0.487 0.314 0.469 0.305 0.371
WS 0.347 0.472 0.281 0.396 0.324 0.409
DEOW 0.334 0.493 0.276 0.408 0.351 0.478
Proposed algorithm 0.309 0.426 0.268 0.375 0.283 0.365

Comparison of Estimation Errors of Different Algorithms

Method First category Second category Third category
MAE RMSE MAE RMSE MAE RMSE
Reference [26] 0.365 0.478 0.296 0.396 0.317 0.396
Reference [27] 0.359 0.468 0.287 0.387 0.328 0.413
Proposed algorithm 0.317 0.446 0.273 0.371 0.287 0.375
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
1 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Biologie, Biologie, andere, Mathematik, Angewandte Mathematik, Mathematik, Allgemeines, Physik, Physik, andere
Zeitschrift RSS Feed