基于ARIMA模型及线性神经网络的用电量需求预测研究  

Electricity Demand Forecasting Based on ARIMA Model and Linear Neural Network

作　　者：周林[1] 雍雪林[1] 

机构地区：[1]华北电力大学数理学院,北京102206

出　　处：《鲁东大学学报（自然科学版）》2015年第3期277-282,共6页Journal of Ludong University:Natural Science Edition

基　　金：国家自然科学基金(70971039;71271083;11301179);国家大学生创新实验项目华北电力大学(2014.03)

摘　　要：利用二阶差分后平稳的历史用电量数据,建立ARIMA(0,2,2)模型,计算平均相对误差,并进一步采用线性神经网络分段逼近历史用电量之间的关系.最后以北京市为例进行实证研究,结果显示:线性神经网络的预测效果优于ARIMA模型.ARIMA（0,2,2） model was established by using stationary data of historical electricity consumption after second order difference,and the average relative error was calculated. The relationship between the histor-ical power was approached piecewise based on linear neural network. Finally,an empirical case study on Beijing City was done, and the results show that the effect of linear neural network is better than ARIMA model.

关 键 词：用电量 ARIMA模型 线性神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]