Forecasting per Capita Energy Consumption in China Using a Spatial Discrete Grey Prediction Model

To overcome the limitations of present grey models in spatial data analysis, a weight matrix is incorporated into discrete model to create SDGM(1,1,m) model, and L1-SDGM(1,1,m) proposed, considering time lag effect realize simultaneous forecasting data. The validation achieved, finally, per capita energy consumption levels (PCECs) 30 provinces China from 2020 2025 predicted using with metabolic mechanism. We draw following conclusions. First, established this paper are reasonable improve accuracy while supporting interactive regional forecasting. Second, although resembles DGM(1,n) their modeling conditions targets different. Third, can be used effectively analyze spillover effects within selected interval achieving accurate predictions; notably, 2010 2017, PCECs Inner Mongolia Qinghai were most affected by factors, Jilin, Jiangxi, other influenced little factors. Fourth, predictions indicate that Chinese will increase under current conditions, such as Beijing expected decrease.