Predicting heartbeat arrival time for failure detection over internet using auto-regressive exogenous model  

Predicting heartbeat arrival time for failure detection over internet using auto-regressive exogenous model

在线阅读下载全文

作  者:赵海军 

机构地区:[1]Information Network Center,Beijing University of Posts and Telecommunications,Beijing 100876,P.R.China

出  处:《High Technology Letters》2008年第4期370-376,共7页高技术通讯(英文版)

基  金:the National Basic Research Program of China(No.2003CB314806);China Next Generation Intemet Project(CNGI-04-6-2T)

摘  要:Predicting heartbeat message arrival time is crucial for the quality of failure detection service over intemet. However, intemet dynamic characteristics make it very difficult to understand message behavior and accurately predict heartbeat arrival time. To solve this problem, a novel black-box model is proposed to predict the next heartbeat arrival time. Heartbeat arrival time is modeled as auto-regressive process, heartbeat sending time is modeled as exogenous variable, the model' s coefficients are estimated based on the sliding window of observations and this result is used to predict the next heartbeat arrival time. Simulation shows that this adaptive auto-regressive exogenous (ARX) model can accurately capture heartbeat arrival dynamics and minimize prediction error in different network environments.Predicting heartbeat message arrival time is crucial for the quality of failure detection service over in-ternet.However,internet dynamic characteristics make it very difficult to understand message behaviorand accurately predict heartbeat arrival time.To solve this problem,a novel black-box model is proposedto predict the next heartbeat arrival time.Heartbeat arrival time is modeled as auto-regressive process,heartbeat sending time is modeled as exogenous variable,the model's coefficients are estimated based onthe sliding window of observations and this result is used to predict the next heartbeat arrival time.Simu-lation shows that this adaptive auto-regressive exogenous (ARX) model can accurately capture heartbeatarrival dynamics and minimize prediction error in different network environments.

关 键 词:INTERACT failure detection ADAPTIVE HEARTBEAT PREDICTION 

分 类 号:TH789[机械工程—仪器科学与技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象