Natural Gas Price Forecasting by a New Hybrid Model Combining Quadratic Decomposition Technology and LSTM Model

Research on the price prediction of natural gas is great significance to market participants all kinds. In order predict prices more reliably, this paper introduces a quadratic decomposition technology based combination variational modal (VMD) and ensemble empirical (EEMD), which decomposes residual term (Res) after VMD by EEMD; then, new hybrid model called VMD-EEMD-Res.-LSTM constructed in with long short-term memory (LSTM) model. The contribution that, unlike existing application research that combines LSTM model, it does not ignore important information contained VMD. verify predictive performance proposed uses data spot United States conduct multistep-ahead comparative analysis. results show has significant advantages.