Use of group method of data handling for transport energy demand modeling

Abstract

AbstractAs transport sector takes a big share of the whole energy consumption in China, it is crucial to predict its energy demand. To forecast China's transport energy demand, group method of data handling (GMDH) was introduced. The model can help policymakers’ select influential variables and build prediction models automatically. Furthermore, it can reduce the negative impact of the noise in the Chinese statistical data. To produce comparable results, four of the six data sets used in this paper contain the same variables as in previously published research. Artificial neural networks (ANN), GMDH, multiple linear regression (MLR), and support vector machine (SVM) models were trained using fivefold cross‐validation. The performance of these models was measured in terms of coefficient of determination and root mean square error. Results showed that GMDH achieved better performance than the other models. Finally, projections were made with two scenarios. Both of the projected results showed that the energy demands peak in certain years and then decrease gradually. This study suggests that GDP is not the essential variable, while urbanization rate is an important variable to forecast the transport energy demand in China. It also suggests that Chinese government needs to prepare for the development and deployment of transport energy.