[1]王电钢,黄林,常健,等.基于ARIMA和CART的负载预测模型[J].深圳大学学报理工版,2019,(No.3(221-346)):245-251.[doi:10.3724/SP.J.1249.2019.03229]
 WANG Diangang,HUANG Lin,CHANG Jian,et al.Load forecasting model based on ARIMA and CART[J].Journal of Shenzhen University Science and Engineering,2019,(No.3(221-346)):245-251.[doi:10.3724/SP.J.1249.2019.03229]
点击复制

基于ARIMA和CART的负载预测模型
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
期数:
2019年No.3(221-346)
页码:
245-251
栏目:
【电子与信息科学】
出版日期:
2019-05-20

文章信息/Info

Title:
Load forecasting model based on ARIMA and CART
作者:
王电钢1黄林1常健1梅克进2牛新征2
1) 国网四川省电力公司信息通信公司,四川成都 610015; 2) 电子科技大学计算机科学与工程学院,四川成都 611731
Author(s):
WANG Diangang1 HUANG Lin1 CHANG Jian1 MEI Kejin2 and NIU Xinzheng2
1) State Grid Sichuan Electric Power Company Information and Communication Corporation, Chengdu 610015, Sichuan Province, P.R.China 2) School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, Sichuan Province, P.R.China
关键词:
计算机应用技术时间序列负载预测最小二乘法自回归差分滑动平均模型分类回归树
Keywords:
computer application technology time series load forecasting least square method auto regressive integrated moving average (ARIMA) classification and regression tree (CART)
分类号:
TP301.6
DOI:
10.3724/SP.J.1249.2019.03229
文献标志码:
A
摘要:
主机资源的负载预测对运营维护工作具有重要意义.传统负载预测方法通常采用线性时间序列模型拟合负载数据,而负载受复杂的内外部环境影响,线性模型无法很好地表征负载数据规律.为了提高模型的精度,提出了将负载信息分解为线性部分和非线性部分的思想,并将自回归差分滑动平均(autoregressive integrated moving average,ARIMA)模型和分类回归树(classification and regression tree,CART)模型相结合进行预测.通过加权最小二乘法改进的ARIMA预测线性部分,通过边界判定优化的CART预测非线性部分,并结合两者以获得综合预测结果.在真实负载数据集进行了对比实验,结果表明,改进后的算法预测精度相较于传统方法提高了15%以上,并且对偏远值和不同的时间间隔都均有良好的适应性.
Abstract:
The load forecasting of host resources is of great significance to the operation and maintenance work. The traditional load forecasting method usually uses a linear model to fit the load data. In the actual operation of the equipment, its load is affected by the complex internal and external environment, and there are nonlinear factors. The linear time series model can not well characterize the law of the load data. In order to improve the accuracy of the model, the idea of decomposing the load information into a linear part and a nonlinear part is proposed, and the autoregressive integrated moving average (ARIMA) and classification and regression tree (CART) models are combined to predict. Specifically, the ARIMA prediction linear part improved by the weighted least squares method is used to determine the nonlinear part of the optimized CART prediction by the boundary, and the prediction results of the two are combined to obtain the comprehensive prediction result. The comparison experiments are carried out on the real load dataset. The results show that the improved algorithm's prediction accuracy is improved by more than 15% compared with the traditional method, and it has good adaptability to remote values and different time intervals.

相似文献/References:

[1]谷建伟,隋顾磊,李志涛,等.基于ARIMA-Kalman滤波器数据挖掘模型的油井产量预测[J].深圳大学学报理工版,2018,35(No.6(551-660)):575.[doi:10.3724/SP.J.1249.2018.06575]
 GU Jianwei,SUI Gulei,LI Zhitao,et al.Oil well production forecasting method based on ARIMA-Kalman filter data mining model[J].Journal of Shenzhen University Science and Engineering,2018,35(No.3(221-346)):575.[doi:10.3724/SP.J.1249.2018.06575]
[2]聂飞平,王成龙,王榕.基于二部图的快速聚类算法[J].深圳大学学报理工版,2019,(No.1(1-110)):18.[doi:10.3724/SP.J.1249.2019.01018]
 NIE Feiping,WANG Chenglong,and WANG Rong.Fast clustering with bipartite graph[J].Journal of Shenzhen University Science and Engineering,2019,(No.3(221-346)):18.[doi:10.3724/SP.J.1249.2019.01018]

更新日期/Last Update: 2019-04-22