Natural gas consumption forecasting using a novel two-stage model based on improved sparrow search algorithm

The foundation of natural gas intelligent scheduling is the accurate prediction of natural gas consumption (NGC). However, because of its volatility, this brings difficulties and challenges in accurately predicting NGC. To address this problem, an improved model is developed combining improved sparrow search algorithm (ISSA), long short-term memory (LSTM), and wavelet transform (WT). First, the performance of ISSA is tested. Second, the NGC is divided into several high- and low-frequency components applying different layers of Coilfets’, Fejer-Korovkins’, Symletss’, Haars’, and Discretes’ orders. In addition, the LSTM is applied to forecast the decomposed components in view of the one- and multi-step, and its hyper-parameters are optimized by ISSA. At last, the final prediction results are reconstructed. The research results indicate that: (1) Comparing to other machine algorithms (e.g. fuzzy neural network), the convergence speed and stability of ISSA are stronger in view of standard deviation and mean; (2) The prediction performance of the developed model is better than that of other forecasting models; (3) The forecasting performance of the single-step forecasting is superior to that of the two-, three-, and four- step; (4) The computational load of the proposed prediction model is the highest compared to other models, and the prediction accuracy is still excellent on the extended time series.