Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting

Multivariable time series prediction has been widely studied in power energy, aerology, meteorology, finance, transportation, etc. Traditional modeling methods have complex patterns and are inefficient to capture long-term multivariate dependencies of data for desired forecasting accuracy. To addres...

Full description

Saved in:
Bibliographic Details
Published in:Electronics (Basel) 2019-08, Vol.8 (8), p.876
Main Authors: Wan, Renzhuo, Mei, Shuping, Wang, Jun, Liu, Min, Yang, Fan
Format: Article
Language:English
Subjects:
Aerology
Algorithms
Artificial intelligence
Artificial neural networks
Asymmetric structures
Atmospheric models
Convolution
Datasets
Decomposition
Design
Forecasting
Internet of Things
Machine learning
Mathematical models
Meteorology
Methods
Model accuracy
Multivariate analysis
Neural networks
Recurrent neural networks
Time series
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:Multivariable time series prediction has been widely studied in power energy, aerology, meteorology, finance, transportation, etc. Traditional modeling methods have complex patterns and are inefficient to capture long-term multivariate dependencies of data for desired forecasting accuracy. To address such concerns, various deep learning models based on Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) methods are proposed. To improve the prediction accuracy and minimize the multivariate time series data dependence for aperiodic data, in this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model. In this model, multi-variable time series prediction is constructed as a sequence-to-sequence scenario for non-periodic datasets. The multichannel residual blocks in parallel with asymmetric structure based on deep convolution neural network is proposed. The results are compared with rich competitive algorithms of long short term memory (LSTM), convolutional LSTM (ConvLSTM), Temporal Convolution Network (TCN) and Multivariate Attention LSTM-FCN (MALSTM-FCN), which indicate significant improvement of prediction accuracy, robust and generalization of our model.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics8080876