Multivariate time series modeling and prediction based on reservoir independent components

Abstract

This paper presents a multivariate time series modeling and prediction method based on reservoir independent components. As a new type of recurrent neural networks (RNNs), reservoir computing methods have become a new hot topic and attracted wide attention from researchers in the field of time series prediction. It has overcome the problems that traditional gradient descent training algorithms present, for example, the process is computationally expensive, and easy to end in a local minimum. However, there are ill-posed solutions when least square estimation methods are used to calculate the output weights because of the collinear columns or rows in the state matrix. Therefore, we use independent component analysis (ICA) to extract the independent components of the state matrix. In addition, this paper proposes an iterative prediction model based on local error compensation to solve the problem of accumulated errors in multiple-step prediction, in order to realize medium-term prediction. The models have been simulated on benchmark dataset of Lorenz time series and a real-world application of Dalian monthly average temperature-rainfall time series. Simulation results substantiate the proposed methods' effectiveness and characteristics.