Prediction method of multivariate time series

Abstract

The invention discloses a multivariate time sequence prediction method. The multivariate time sequence prediction method comprises the following steps: modeling a multivariate time sequence; preprocessing the multivariate time series, including stabilization of non-stationary data, noise filtering of noise-containing data, normalization of data of different dimensions and phase-space reconstruction; then, according to the characteristics of the data, establishing a suitable prediction model, wherein the prediction model is mainly divided into a global prediction model, a local prediction model and a self-adaptive prediction model; and a global prediction model regarding all observation samples as research objects, and realizing the research on the dynamic characteristics of an unknown system by establishing a corresponding nonlinear mapping relation. According to the method, the nonlinear prediction model of the multivariate sequence is established, so that the prediction precision is high, the calculation complexity is low, the model has good adaptability, and the online prediction precision is relatively high.

Description

technical field [0001] The invention relates to the technical field of time series prediction, in particular to a multivariate time series prediction method. Background technique [0002] Time series forecasting has been widely used in industry, finance, military and other fields. Since most of the time series in real life are nonlinear and unstable, the prediction of nonlinear and unstable time series has always been a hot topic. research scholars in various fields. At present, one of the main methods for forecasting nonlinear and unstable time series is to use Echo State Network (ESN). The characteristic of ESN is that it only needs to train the output weights from the reserve pool to the output layer during training, which solves the problems of traditional neural networks that are easy to fall into local optimum and complex training algorithms. Therefore, computing output weights is the key to echo state network learning. However, the existing time series prediction i...

AI Technical Summary

Problems solved by technology

However, the existing time series prediction is computationally inefficient due to the influence of network output and errors during training

Images