基于混合时间序列模型的云南省能源消费预测研究  

Energy Consumption Prediction in Yunnan Province Based on Mixed Time Series Model

作　　者：尹潇潇 干文[2] 

机构地区：[1]云南财经大学统计与数学学院,昆明 [2]云南财经大学国际工商学院,昆明

出　　处：《统计学与应用》2014年第4期182-192,共11页Statistical and Application

摘　　要：能源是人类生存、经济发展和社会进步的重要物质保障。本文结合云南省能源消费总量的历史数据,首先建立趋势外推模型,预测云南省未来能源消费总量;然后将趋势外推模型和ARIMA模型相结合,利用混合时间序列模型进行预测和分析;通过比较上述预测结果,发现混合时间序列模型具有更好的预测效果,说明该模型对云南省能源消费总量的预测有重要的理论与现实意义。Energy is an important material security for human survival, economic development and social progress. Based on the historical data of energy consumption in Yunnan Province, we first estab- lish a trend extrapolation model to estimate the total energy consumption of Yunan Province in the future. Second, we combine the trend extrapolation model and ARIMA model to give a mixed time series model. The prediction results of these two models are analysed and compared. The results show that the mixed time series model is performed better. This indicates that the mixed time series model is a useful theoretical tool for energy prediction in Yunnan Province.

关 键 词：趋势外推 ARIMA模型 混合时间序列模型 能源消费 预测 

分 类 号：F2[经济管理—国民经济]