Acceso abierto

A new strategy for power monitoring data collection based on data mining and its role in improving prediction accuracy

Junpeng Zhao

Junpeng Zhao

State Grid Hebei Marketing Services CenterShijiazhuang, China
Buscar este autor en
Sciendo|Google Scholar
Zhao, Junpeng
, 
Yangrui Zhang

Yangrui Zhang

State Grid Hebei Marketing Services CenterShijiazhuang, China
Buscar este autor en
Sciendo|Google Scholar
Zhang, Yangrui
, 
Hongying Wang

Hongying Wang

State Grid Hebei Marketing Services CenterShijiazhuang, China
Buscar este autor en
Sciendo|Google Scholar
Wang, Hongying
, 
Yajie Zhang

Yajie Zhang

State Grid Xiongan New Area Electric Power Supply CompanyXiong’an, China
Buscar este autor en
Sciendo|Google Scholar
Zhang, Yajie
 y 
Shaokang Feng

Shaokang Feng

State Grid Hebei Marketing Services CenterShijiazhuang, China
Buscar este autor en
Sciendo|Google Scholar
Feng, Shaokang
  
19 mar 2025
A new strategy for power monitoring data collection based on data mining and its role in improving prediction accuracy's Cover Image
Acerca de este artículo
Artículo anterior
Artículo siguiente
Cite
Descargar portada
Publicado en línea: 19 mar 2025
Recibido: 16 nov 2024
Aceptado: 19 feb 2025
DOI: https://doi.org/10.2478/amns-2025-0551
Palabras clave
© 2025 Junpeng Zhao et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Specific workflow diagram for clearing data
Specific workflow diagram for clearing data

Figure 2.

The load prediction flow chart based on the improved transformer model
The load prediction flow chart based on the improved transformer model

Figure 3.

The distribution curve of 220 sample points
The distribution curve of 220 sample points

Figure 4.

Traditional rapid peak algorithm decision diagram
Traditional rapid peak algorithm decision diagram

Figure 5.

Improved fast density peak clustering algorithm decision diagram
Improved fast density peak clustering algorithm decision diagram

Figure 6.

Predictions of different models on public data sets 1
Predictions of different models on public data sets 1

Figure 7.

The results of different models on public data set 2
The results of different models on public data set 2

Figure 8.

Prediction of real data sets
Prediction of real data sets

Different models of the evaluation indicators on public data set 2

Model MAPE(%) RMSE(MW) MAE(MW) R2
LSTM 3.67 320.4859 235.0074 0.9397
BiLSTM-Attention 3.02 235.8231 171.6748 0.9762
Improve transformer 1.40 124.5055 84.5468 0.9963

Evaluation indicators of different models in public data sets 1

Model MAPE(%) RMSE(MW) MAE(MW) R2
LSTM 2.96 281.0886 183.2736 0.9542
BiLSTM-Attention 2.65 227.4795 161.2114 0.9701
Improve transformer 1.03 85.4571 62.3925 0.9984

Anomalous data distribution

Abnormal value label Date
5 2022/05
21 2019/12
63 2019/10
96 2019/07
108 2019/05
126 2021/09
143 2022/12
187 2023/10
202 2023/06

The results of different models in the real data set

Model MAPE(%) RMSE(MW) MAE(MW) R2
LSTM 5.23 683.7404 473.8774 0.9483
BiLSTM-Attention 4.57 596.3083 426.4559 0.9583
Improve transformer 4.15 496.1061 356.6518 0.9771
Idioma:
Inglés
Calendario de la edición:
1 veces al año
Temas de la revista:
Ciencias de la vida, Ciencias de la vida, otros, Matemáticas, Matemáticas aplicadas, Matemáticas generales, Física, Física, otros
RSS Feed de revista