广东省能源需求预测模型构建及实证分析  

Construction of Energy Demand Forecasting Model and Empirical Analysis of Guangdong Province

作　　者：叶艺勇[1] 

机构地区：[1]五邑大学经济管理学院,广东江门529020

出　　处：《经济数学》2015年第3期64-72,共9页Journal of Quantitative Economics

基　　金：教育部人文社会科学青年基金项目(11YJC790205)

摘　　要：为了对广东省的能源需求进行准确的预测,首先分析了影响广东省能源需求的各种因素,构建了预测指标体系.在此基础上,针对能源系统非线性等复杂系统特征,结合粒子群算法和BP神经网络的优点,构建了改进的PSO-BP神经网络的预测模型,并通过主成分分析法对指标体系进行数据降维,以降低神经网络的规模和复杂程度.以广东省1985-2013年的能源需求数据进行模拟与仿真,并对2014-2018年的能源需求量进行预测,理论分析和实证研究表明,该方法能够很好的反映广东省能源需求的特征,预测结果较为准确合理.In order to make accurate forecast for energy demand of Guangdong province,this paper analyzed the various factors which impact on energy demand of Guangdong province,and constructed the predict index system.On this basis,ac-cording to the nonlinear characteristics of the energy system,combined with the advantages of particle swarm optimization algo-rithm and BP neural network,a prediction model was constructed based on PSO-BP neural network.And the method of princi-pal component analysis was used to reduce the dimensions of the prediction index system in order to reduce the size and com-plexity of the neural network.Then,this paper simulated the energy demand data of Guangdong province from 1 985 to 2013, and carried on the forecast energy demand of Guangdong province during 2014 to 2018.The theoretical analysis and empirical study show that this method can reflect the characteristics of energy demand of Guangdong province,and the predicted result is more accurate and reasonable.

关 键 词：能源需求预测 粒子群算法 BP神经网络 主成分分析法 

分 类 号：F201[经济管理—国民经济]