A Hybrid Residential Short-Term Load Forecasting Method Using Attention Mechanism and Deep Learning

Development in economics and social society has led to rapid growth in electricity demand. Accurate residential electricity load forecasting is helpful for the transformation of residential energy consumption structure and can also curb global climate warming. This paper proposes a hybrid residentia...

Full description

Saved in:
Bibliographic Details
Published inBuildings (Basel) Vol. 13; no. 1; p. 72
Main Authors Ji, Xinhui, Huang, Huijie, Chen, Dongsheng, Yin, Kangning, Zuo, Yi, Chen, Zhenping, Bai, Rui
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.01.2023
Subjects
Accuracy
Algorithms
Artificial intelligence
Artificial neural networks
attention mechanism
Climate change
Deep learning
Design
dilated convolutional neural network
Electric power demand
Electrical loads
Electricity
Energy consumption
Feature extraction
Forecasting
Global warming
long and short-term memory network
Long short-term memory
Machine learning
Neural networks
Residential energy
residential short-term load forecasting
Statistical methods
Support vector machines
Time series
Online AccessGet full text

Cover

More Information
Summary:Development in economics and social society has led to rapid growth in electricity demand. Accurate residential electricity load forecasting is helpful for the transformation of residential energy consumption structure and can also curb global climate warming. This paper proposes a hybrid residential short-term load forecasting framework (DCNN-LSTM-AE-AM) based on deep learning, which combines dilated convolutional neural network (DCNN), long short-term memory network (LSTM), autoencoder (AE), and attention mechanism (AM) to improve the prediction results. First, we design a T-nearest neighbors (TNN) algorithm to preprocess the original data. Further, a DCNN is introduced to extract the long-term feature. Secondly, we combine the LSTM with the AE (LSTM-AE) to learn the sequence features hidden in the extracted features and decode them into output features. Finally, the AM is further introduced to extract and fuse the high-level stage features to achieve the prediction results. Experiments on two real-world datasets show that the proposed method is good at capturing the oscillation characteristics of low-load data and outperforms other methods.
ISSN:2075-5309
2075-5309
DOI:10.3390/buildings13010072