期刊导航

论文摘要

基于贝叶斯与因果岭回归的物联网流量预测模型

The flow prediction model in Internet of Things based on Bayesian and causal ridge regression

作者:陈翔(西安工业大学建筑工程学院, 西安 710021);唐俊勇(西安工业大学计算机科学与工程学院, 西安 710021)

Author:CHEN Xiang(School of Civil Engineering, Xi'an Technological University, Xi'an 710021, China);TANG Jun-Yong(School of Computer Science and Engineering, Xi'an Technological University, Xi'an 710021, China)

收稿日期:2017-09-21          年卷(期)页码:2018,55(5):965-970

期刊名称:四川大学学报: 自然科学版

Journal Name:Journal of Sichuan University (Natural Science Edition)

关键字:物联网;流量;预测;贝叶斯;因果岭回归

Key words:Internet of Things; Flow; Prediction; Bayesian; Causal Ridge Regression

基金项目:陕西省科技厅工业科技攻关项目(2016GY 088)

中文摘要

针对物联网流量预测困难的问题,提出了一种基于贝叶斯与因果岭回归的物联网流量预测模型.该模型首先根据物联网流量传输波动影响链路变化等因果关系,深入刻画物联网流量局部特征,并利用薛定谔方程优化识别模型,同时结合贝叶斯拟合因果关系联合岭回归方法建立预测模型.最后,通过仿真实验研究了该模型与其他方法之间的性能状况,结果表明该模型在平均队列、阻塞率和延迟率等方面具有较大优势.

英文摘要

In order to solve the flow prediction problem of Internet of Things, a flow In order to solve the flow prediction problem of Internet of Things, a flow prediction model is proposed based on Bayesian and causal ridge regression.At first,the local characteristic of flow is deeply depicted considering the causal relationship between the fluctuation of the traffic flow and the change of the link;in addition, Schrodinger equation is used to optimize the recognition model.Then,the prediction model is built with Bayesian and causal ridge regression.Finally,the performance of this model and other methods is studied by simulation experiment.The results show that this model has a great advantage in average queue,blocking rate,delay rate and so on.

关闭

Copyright © 2020四川大学期刊社 版权所有.

地址:成都市一环路南一段24号

邮编:610065