A Model-Free Predictor Based on Predictive Tracking for Time Series

The majorities of the existing predictors for states are model-dependent and therefore require some prior knowledge for the identification of complex systems, usually involving system identification, extensive training or online adaptation in the case of time-varying systems. In this paper a model-free predictor (MFP) for a time series produced by an unknown nonlinear system or process is proposed. The dynamic function of the MFP is independent of the predicted system or process, avoiding the explicit model identification or approximation of the system or process. The MFP is able to accurately predict future values of a time series, is exponentially stable, has few tuning parameters and is desirable for engineering applications due to simplicity, fast prediction speed and extremely low computational load. The performance of the proposed MFP is demonstrated using the prediction of hyperchaos.