灰色神经网络组合模型在能源需求中的应用

Application of the Gray Neural Network Combination Model in Forecasting Energy Demand of China

摘要: 能源是社会发展的基石，随着经济的发展，能源需求也不断增加，为此较高精度的对能源需求进行预测具有十分重要的意义。本文基于GM(1, 1)预测模型和BP神经网络模型，以与能源消耗总量相关的居民消费水平指数，能源生产总量，能源工业投资，国内生产总值，可供消费的能源总量，年末总人口为6个影响指标，建立串联式灰色神经网络模型对全国能源需求总量进行预测。选取2000~2011年全国能源消费总量实际数据为建模数据，以2012~2016年的实际数据为检验数据，对比分析GM(1, 1)、和灰色神经网络的预测精度。其结果表明，灰色神经网络模型预测精度最高，预测误差均方差为0.5840，小于单一的GM(1, 1)预测误差的均方差。

Abstract: Energy is the cornerstone of social development. With the development of economy, the demand for energy is increasing year by year. So it is very important to forecast the energy demand with high precision. In this paper, based on GM(1, 1) model and BP neural network model, a tandem type grey neural network model is established to forecast the national total energy demand using the resident consumption level index, the total energy production, the energy industry investment, the gross domestic product, the total energy available for consumption, and the total population at year-end as the influence indexes. The actual data of total energy consumption in 2000~2011 were selected as modeling data, and those in 2012~2016 were selected as testing data. Comparative analysis of GM(1, 1) and gray neural network prediction accuracy was made. The results show that the grey neural network model has the highest prediction accuracy and the mean variance of the prediction error is 0.5840, which is less than the mean variance of the single GM(1, 1) prediction error.