An Experimental Review on Deep Learning Architectures for Time Series Forecasting

被引:337
作者
Lara-Benitez, Pedro [1 ]
Carranza-Garcia, Manuel [1 ]
Riquelme, Jose C. [1 ]
机构
[1] Univ Seville, Div Comp Sci, ES-41012 Seville, Spain
关键词
Deep learning; forecasting; time series; review; NEURAL DYNAMIC CLASSIFICATION; CRACK DETECTION; NETWORKS; PREDICTION; MODEL; ENERGY; LSTM; DEMAND;
D O I
10.1142/S0129065721300011
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years, deep learning techniques have outperformed traditional models in many machine learning tasks. Deep neural networks have successfully been applied to address time series forecasting problems, which is a very important topic in data mining. They have proved to be an effective solution given their capacity to automatically learn the temporal dependencies present in time series. However, selecting the most convenient type of deep neural network and its parametrization is a complex task that requires considerable expertise. Therefore, there is a need for deeper studies on the suitability of all existing architectures for different forecasting tasks. In this work, we face two main challenges: a comprehensive review of the latest works using deep learning for time series forecasting and an experimental study comparing the performance of the most popular architectures. The comparison involves a thorough analysis of seven types of deep learning models in terms of accuracy and efficiency. We evaluate the rankings and distribution of results obtained with the proposed models under many different architecture configurations and training hyperparameters. The datasets used comprise more than 50,000 time series divided into 12 different forecasting problems. By training more than 38,000 models on these data, we provide the most extensive deep learning study for time series forecasting. Among all studied models, the results show that long short-term memory (LSTM) and convolutional networks (CNN) are the best alternatives, with LSTMs obtaining the most accurate forecasts. CNNs achieve comparable performance with less variability of results under different parameter configurations, while also being more efficient.
引用
收藏
页数:28
相关论文
共 112 条
[81]   Performing Multi-Target Regression via a Parameter Sharing-Based Deep Network [J].
Reyes, Oscar ;
Ventura, Sebastian .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2019, 29 (09)
[82]   Minimum Complexity Echo State Network [J].
Rodan, Ali ;
Tino, Peter .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2011, 22 (01) :131-144
[83]   Neural networks for recognizing human activities in home-like environments [J].
Rodriguez Lera, Francisco J. ;
Martin Rico, Francisco ;
Matellan Olivera, Vicente .
INTEGRATED COMPUTER-AIDED ENGINEERING, 2019, 26 (01) :37-47
[84]   Progressive preference articulation for decision making in multi-objective optimisation problems [J].
Rostami, Shahin ;
Neri, Ferrante ;
Epitropakis, Michael .
INTEGRATED COMPUTER-AIDED ENGINEERING, 2017, 24 (04) :315-335
[85]   Covariance matrix adaptation pareto archived evolution strategy with hypervolume-sorted adaptive grid algorithm [J].
Rostami, Shahin ;
Neri, Ferrante .
INTEGRATED COMPUTER-AIDED ENGINEERING, 2016, 23 (04) :313-329
[86]   Energy consumption forecasting based on Elman neural networks with evolutive optimization [J].
Ruiz, L. G. B. ;
Rueda, R. ;
Cuellar, M. P. ;
Pegalajar, M. C. .
EXPERT SYSTEMS WITH APPLICATIONS, 2018, 92 :380-389
[87]   Time series forecasting of petroleum production using deep LSTM recurrent networks [J].
Sagheer, Alaa ;
Kotb, Mostafa .
NEUROCOMPUTING, 2019, 323 (203-213) :203-213
[88]   Financial time series forecasting with deep learning : A systematic literature review: 2005-2019 [J].
Sezer, Omer Berat ;
Gudelek, Mehmet Ugur ;
Ozbayoglu, Ahmet Murat .
APPLIED SOFT COMPUTING, 2020, 90
[89]   Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques [J].
Sfetsos, A ;
Coonick, AH .
SOLAR ENERGY, 2000, 68 (02) :169-178
[90]   A novel time series forecasting model with deep learning [J].
Shen, Zhipeng ;
Zhang, Yuanming ;
Lu, Jiawei ;
Xu, Jun ;
Xiao, Gang .
NEUROCOMPUTING, 2020, 396 :302-313