鲁东大学学报(自然科学版)
魯東大學學報(自然科學版)
로동대학학보(자연과학판)
LUDONG UNIVERSITY JOURNAL(NATURAL SCIENCE EDITION)
2015年
3期
277-282
,共6页
用电量%ARIMA 模型%线性神经网络
用電量%ARIMA 模型%線性神經網絡
용전량%ARIMA 모형%선성신경망락
electricity consumption%ARIMA model%linear neural network
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。
利用二階差分後平穩的歷史用電量數據,建立 ARIMA(0,2,2)模型,計算平均相對誤差,併進一步採用線性神經網絡分段逼近歷史用電量之間的關繫。最後以北京市為例進行實證研究,結果顯示:線性神經網絡的預測效果優于 ARIMA 模型。
이용이계차분후평은적역사용전량수거,건립 ARIMA(0,2,2)모형,계산평균상대오차,병진일보채용선성신경망락분단핍근역사용전량지간적관계。최후이북경시위례진행실증연구,결과현시:선성신경망락적예측효과우우 ARIMA 모형。
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.