Time sequence prediction method based on grey wolf optimization echo state network

Abstract

The invention discloses a time sequence prediction method based on a grey wolf optimization echo state network. According to the method, the output weight of the echo state network is adjusted throughthe grey wolf algorithm so that optimization of the echo state network can be realized, the problem of training difficulty of the echo state network prediction method can be effectively solved, the constructed echo state network prediction method has better adaptability, the prediction accuracy is obviously higher than that of the present echo state network prediction method and other network prediction methods and thus the application value is enabled to be higher.

Description

technical field [0001] The invention relates to the field of time series research and analysis, in particular to a time series prediction method based on a grey wolf-optimized echo state network. Background technique [0002] As a set of random variables sorted by time, time series widely exists in many fields of life, including business, meteorology, finance, agriculture, etc. In order to better understand the inherent laws of things, the prediction of time series has become one of the hot issues of extensive research attention. [0003] Due to the strong nonlinearity and randomness of time series, in order to predict time series data more accurately, researchers in various fields have proposed a variety of time series forecasting models. Among them, Echo State Network (ESN), as a new type of recurrent neural network, has been widely used in nonlinear time series prediction. It uses the reserve pool to replace the hidden layer of the traditional neural network, and its co...

AI Technical Summary

Problems solved by technology

However, due to the unique structural characteristics of ESN, traditional ESN network training requires a large number of training samples, making training difficult, thus affecting prediction accuracy

Images