A hybrid deep learning approach by integrating extreme gradient boosting‐long short‐term memory with generalized autoregressive conditional heteroscedasticity family models for natural gas load volatility prediction

Natural gas load forecasting provides decision‐making support for natural gas dispatch and management, pipeline network construction, pricing, and sustainable energy development. To explain the uncertainty and volatility in natural gas load forecasting, this study predicts the natural gas load volatility. As the natural gas load volatility has the time‐series features, along with long‐term memory, volatility aggregation, asymmetry, and nonnormality, this study proposes a natural gas load volatility prediction model by combining generalized autoregressive conditional heteroscedasticity (GARCH) family models, XGBoost algorithm, and long short‐term memory (LSTM) network. The model first takes the GARCH family models parameters of sliding estimation and meteorological factors as the influencing factors of volatility, and then it screens these influencing factors through the extreme gradient boosting (XGBoost) algorithm. Finally, the selected important features are input into the LSTM network to predict the volatility, and the 90% confidence interval of the volatility is calculated. Compared with a variety of single and combined models, the model proposed in this study has an average reduction of 45.404% in the evaluation index of mean squared error. The experimental results show that the model proposed in this study has a good performance and accuracy in predicting the volatility of natural gas load. (1) The calculation method of natural gas load volatility is very explicit, which distinguishes itself from the previous concept of volatility in the field of financial assets. In addition, a specific statistical description and analysis of natural gas load volatility are carried out, which is different from the previous volatility analysis of prices and stocks. (2) A hybrid deep learning model for natural gas load volatility forecasting is established based on generalized autoregressive conditional heteroscedasticity (GARCH) family and extreme gradient boosting (XGBoost)‐long short‐term memory (LSTM), which can effectively capture the nonlinearity and diversity of natural gas load volatility and its influencing factors. (3) In the previous literature, there is still a lack of research on natural gas load volatility prediction. To provide certain empirical evidence, we conducted an in‐depth evaluation of different GARCH family models, a combination of models of the GARCH family and deep learning algorithms. The results show that the appropriate GARCH family parame