Forecasting hybrid neural network with variational learning rate and q -DSCID synchronization evaluation for energy mark
- PDF / 2,184,898 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 3 Downloads / 181 Views
METHODOLOGIES AND APPLICATION
Forecasting hybrid neural network with variational learning rate and q-DSCID synchronization evaluation for energy market Bin Wang1 · Jun Wang1
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Because of the nonlinearity, uncertainty, and dynamics of crude oil price, its price forecasting has continuously been a burdensome international research issue. To better implement the prediction of the energy market by machine learning algorithms, premeditating the influence factors of historical data in different periods on prediction consequence, random inheritance formula error correction algorithm is proposed in this work. The empirical wavelet transform and reconstruction are applied to extract data features simultaneously. A novel hybrid neural network model is constructed, which integrates empirical wavelet transform, Elman recurrent neural network, and random inheritance formula. Variational learning rate is proposed and used to ameliorate the selection of parameters for the network training procedure. In this paper, the proposed model is applied in crude oil futures price forecasting. Further, a variety of evaluation indicators are introduced to contrast and evaluate the predictions. An original representative synchronization evaluation arithmetic q-order dyadic scales complexity invariant distance is put forward and utilized. Demonstration results suggest that the proposed model has superior preciseness among comparison models. Keywords Hybrid neural network · Empirical wavelet transform · Random inheritance formula · Variational learning rate · Crude oil futures price · q-order dyadic scales complexity invariant distance
Abbreviations VR EWT RIF ANN RNN GRU ERNN RIF-ERNN EWT-RIF-ERNN
CID
q-DSCID Variational learning rate Empirical wavelet transform Random inheritance formula Artificial neural network Recurrent neural network Gated recurrent unit Elman recurrent neural network Random inheritance Elman recurrent neural network Random inheritance Elman recurrent neural network with empirical wavelet transform Complexity invariant distance
Communicated by V. Loia.
B B 1
Bin Wang [email protected] Jun Wang [email protected] School of Science, Beijing Jiaotong University, Beijing 100044, China
WTI BRE PTR SNP
q-order dyadic scales complexity invariant distance West Texas intermediate crude oil Brent crude oil China Petroleum and Natural Gas Co., Ltd China Petrochemical Co., Ltd
1 Introduction Crude oil appertains to non-renewable resource, also be praised as the blood of industry (Hart 2016). It evolves an inestimable mission in guaranteeing national economic, social development, and national defense security (Sun et al. 2015; Wu and Zhang 2014; Park and Ratti 2008; Jammazi and Aloui 2012). In recent years, the price of crude oil has been rising unceasingly, which has a tremendous impact on the global economy. If the energy futures price and its trend can be more accurately predicted, it will perform an energetic reference intention in the decision mak
Data Loading...
