China’s primary energy demands in 2020: Predictions from an MPSO–RBF estimation model

In the present study, a Mix-encoding Particle Swarm Optimization and Radial Basis Function (MPSO–RBF) network-based energy demand forecasting model is proposed and applied to forecast China’s energy consumption until 2020. The energy demand is analyzed for the period from 1980 to 2009 based on GDP, population, proportion of industry in GDP, urbanization rate, and share of coal energy. The results reveal that the proposed MPSO–RBF based model has fewer hidden nodes and smaller estimated errors compared with other ANN-based estimation models. The average annual growth of China’s energy demand will be 6.70%, 2.81%, and 5.08% for the period between 2010 and 2020 in three scenarios and could reach 6.25 billion, 4.16 billion, and 5.29 billion tons coal equivalent in 2020. Regardless of future scenarios, China’s energy efficiency in 2020 will increase by more than 30% compared with 2009.

► A Mix-encoding PSO and RBF network-based energy demand forecasting model is proposed.
► The proposed model has simpler structure and smaller estimated errors than other ANN models.
► China’s energy demand could reach 6.25 billion, 4.16 billion, and 5.29 billion tons tce.
► China’s energy efficiency in 2020 will increase by more than 30% compared with 2009.