Forecasting energy demand in China and India: Using single-linear, hybrid-linear, and non-linear time series forecast techniques

Abstract

Better forecasting energy demand in China and India can help those countries meet future challenges caused by the changes in that demand, as well as inform future global energy needs. In this study, the single-linear, hybrid-linear, and non-linear forecasting techniques based on grey theory are developed to more accurately forecasting energy demand in China and India. These prosed techniques were applied to simulate China’s and India’s energy consumption of China and India between 1990 and 2016. Three standards (trend map, error measure, and fit method) of analyzing quality of forecast technique are used to quantify the quality of these proposed technique. The results show these proposed techniques have a very high degree of fit, a low error rate, and high fitting precision. For example, the mean absolute percent error of single-linear, hybrid-linear, and non-linear techniques are 1.30–3.08%, 0.80–2.57%, and 2.06–2.19%, respectively. The results of optimality analysis show these proposed models can produce reliable forecasting results in China and India, which might be used to forecasting energy demand in other countries/regions. Our forecasting results show the annual growth rate of India’s energy demand from 2017 to 2026 will be 4.49%–5.21% (single-linear), 2.42%–7.04% (hybrid-linear), 0.58%–4.02% (non-linear), respectively. The annual growth rate of China’s energy demand from 2017 to 2026 will be 1.36%–1.70% (single-linear), 1.04%–1.49% (hybrid-linear), 1.80%–2.34% (non-linear), respectively. The growth rate of India’s energy consumption is expected to be 2–4 times that of China from 2017 to 2026, indicating India will become even more important in the global energy market.