Compound Autoregressive Network for Prediction of Multivariate Time Series

Complexity - Tập 2019 Số 1 - 2019
Yuting Bai1,2, Xue‐Bo Jin1,2, Xiaoyi Wang1,2, Tingli Su1,2, Jianlei Kong1,2, Yutian Lu3
1Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing, 100048, China
2School of Computer and Information Engineering, Beijing Technology and Business University, Beijing, 100048, China
3State Grid Beijing Electric Power Company, Beijing 100031, China

Tóm tắt

The prediction information has effects on the emergency prevention and advanced control in various complex systems. There are obvious nonlinear, nonstationary, and complicated characteristics in the time series. Moreover, multiple variables in the time‐series impact on each other to make the prediction more difficult. Then, a solution of time‐series prediction for the multivariate was explored in this paper. Firstly, a compound neural network framework was designed with the primary and auxiliary networks. The framework attempted to extract the change features of the time series as well as the interactive relation of multiple related variables. Secondly, the structures of the primary and auxiliary networks were studied based on the nonlinear autoregressive model. The learning method was also introduced to obtain the available models. Thirdly, the prediction algorithm was concluded for the time series with multiple variables. Finally, the experiments on environment‐monitoring data were conducted to verify the methods. The results prove that the proposed method can obtain the accurate prediction value in the short term.

Từ khóa


Tài liệu tham khảo

10.1371/journal.pone.0152491

Liu X., 2018, The EFDC model integration and application in the Three Gorges reservoir, Research of Environmental Sciences, 31, 283

10.1504/ijep.2008.021135

Borrego G. E. P., 1976, Time Series Analysis: Forecasting and Control

10.1080/2150704x.2017.1418992

10.1016/j.cie.2018.02.023

10.1080/03610918.2018.1458138

Chen L., 2012, Autoregressive integrated moving average model in food poisoning prediction in Hunan province, Journal of Central South University, 37, 142

10.1631/fitee.1500381

Yang H., 2019, Review of time series prediction methods, Computer Science, 46, 21

10.1016/j.asoc.2017.04.014

DalyC. MooreD. L. andHaddadR. J. Nonlinear auto-regressive neural network model for forecasting Hi-Def H.265 video traffic over Ethernet passive optical networks Proceedings of the IEEE SoutheastCon 2017 March 2017 Charlotte NC USA IEEE 1–7.

10.1109/TNNLS.2015.2411671

10.1016/j.eswa.2015.09.052

10.1016/j.renene.2016.02.003

10.1016/j.eswa.2014.08.018

10.1080/095400999116340

GravesA. FernándezS. andSchmidhuberJ. Multi-dimensional recurrent neural networks Lecture Notes in Computer Science 4668 Proceedings of the International Conference on Artificial Neural Networks 2007 549–558 https://doi.org/10.1007/978-3-540-74690-4_56.

10.1109/78.650093

10.1162/neco.1997.9.8.1735

GravesA. FernándezS. andSchmidhuberJ. Bidirectional LSTM networks for improved phoneme classification and recognition Proceedings of the International Conference on Artificial Neural Networks September 2005 Munich Germany 799–804.

ChoK. MerrienboerB. V. GulcehreC.et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation Proceedings of the Conference on Empirical Methods in Natural Language Processing September 2014 Lisbon Portugal 1–14.

10.1007/s40953-018-0133-8

10.1109/tsmc.2016.2562511

Thông tin
Thông tin xuất bản

Complexity

Tập 2019 Số 1

Thông tin tác giả