ARIMA Prediction Model-based Cluster Algorithm in Ad Hoc Networks
The paper introduces prediction mechanism in weighted clustering algorithm (WCA).Time series model (ARIMA) is embedded into the algorithm during routing maintance to predict the network node location.Combining with location information of nodes provided by GPS systems,the algorithm uses ARIMA to predict position of nodes at next time interval.So,it can calculate aggregate holding time of the nodes.Then,compare the predicted aggregate holding time of next moment with time warning threshold.If cluster structure is predicted unstable,recovery process will be activated before the link fails,and it will search appropriate routing in order to avoid frequent failures of network links.In this way,the influence to the routing protocols brought by the dynamic changes of network topology can be reduced.The simulation results show that,compared with LOWID and RLWCA not joined the forecasting mechanism,the proposed algorithm can dramatically improve the network packet delivery rate,reduce the network normalized expenses and the number of routing interruptions significantly,and improve network performance.
Ad Hoc network ARIMA Clustering algorithm CBRP Prediction
Yingyu Cao Ting Cao Huang Ye Yang Yan Jiafu Chu
School of Information Science and Engineering,Northeastern University,Shenyang, China College of Electronics Information Engineering Shenyang Aerospace University Shenyang, China school of Information Science and Engineering Northeastern University Shenyang, China
国际会议
沈阳
英文
132-136
2012-07-27（万方平台首次上网日期，不代表论文的发表时间）