A Short-Term Load Forecasting Method Based on GRU-CNN Hybrid Neural Network Model

Short-term load forecasting (STLF) plays a very important role in improving the economy and stability of the power system operation. With the smart meters and smart sensors widely deployed in the power system, a large amount of data was generated but not fully utilized, these data are complex and di...

Full description

Saved in:
Bibliographic Details
Published in:Mathematical problems in engineering 2020, Vol.2020 (2020), p.1-10
Main Authors: Chen, Wei, Hao, Xiaohong, Kong, Chun, Wu, Lizhen
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Back propagation
Economic forecasting
Electricity
Electricity distribution
Feature extraction
Machine learning
Mathematical models
Model testing
Modules
Neural networks
Power
Propagation
Root-mean-square errors
Smart sensors
Statistical methods
Supply & demand
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Short-term load forecasting (STLF) plays a very important role in improving the economy and stability of the power system operation. With the smart meters and smart sensors widely deployed in the power system, a large amount of data was generated but not fully utilized, these data are complex and diverse, and most of the STLF methods cannot well handle such a huge, complex, and diverse data. For better accuracy of STLF, a GRU-CNN hybrid neural network model which combines the gated recurrent unit (GRU) and convolutional neural networks (CNN) was proposed; the feature vector of time sequence data is extracted by the GRU module, and the feature vector of other high-dimensional data is extracted by the CNN module. The proposed model was tested in a real-world experiment, and the mean absolute percentage error (MAPE) and the root mean square error (RMSE) of the GRU-CNN model are the lowest among BPNN, GRU, and CNN forecasting methods; the proposed GRU-CNN model can more fully use data and achieve more accurate short-term load forecasting.
ISSN:1024-123X
1563-5147
DOI:10.1155/2020/1428104