{"title":"一种新的基于覆盖的故障检测体系结构","authors":"Dhafer Ben Khedher, R. Glitho, R. Dssouli","doi":"10.1109/ICON.2007.4444074","DOIUrl":null,"url":null,"abstract":"Abstract-Node failures and message losses are frequent in MANETs. This paper proposes a novel overlay-based architecture for MANET applications to ensure that if a node fails, all the other nodes will be notified. Nodes form a self-organizing overlay network that is overlayed on the physical network. In an overlay network, a set of nodes, called detectors, periodically sense each other's heartbeat messages. Every detector also senses the heartbeat messages of a set of nodes. If a detector does not hear from a node after a timeout (possibly due to node failure or message loss), it identifies the failure of the node according to a set of failure detection rules and then reports the failure to all the other nodes. A simulation is done to demonstrate scalability and to compute the number of non-failed nodes declared as failed. Finally, we describe a use case for recovery in a conferencing situation in MANETs.","PeriodicalId":131548,"journal":{"name":"2007 15th IEEE International Conference on Networks","volume":"52 4","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"27","resultStr":"{\"title\":\"A Novel Overlay-Based Failure Detection Architecture for MANET Applications\",\"authors\":\"Dhafer Ben Khedher, R. Glitho, R. Dssouli\",\"doi\":\"10.1109/ICON.2007.4444074\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract-Node failures and message losses are frequent in MANETs. This paper proposes a novel overlay-based architecture for MANET applications to ensure that if a node fails, all the other nodes will be notified. Nodes form a self-organizing overlay network that is overlayed on the physical network. In an overlay network, a set of nodes, called detectors, periodically sense each other's heartbeat messages. Every detector also senses the heartbeat messages of a set of nodes. If a detector does not hear from a node after a timeout (possibly due to node failure or message loss), it identifies the failure of the node according to a set of failure detection rules and then reports the failure to all the other nodes. A simulation is done to demonstrate scalability and to compute the number of non-failed nodes declared as failed. Finally, we describe a use case for recovery in a conferencing situation in MANETs.\",\"PeriodicalId\":131548,\"journal\":{\"name\":\"2007 15th IEEE International Conference on Networks\",\"volume\":\"52 4\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"27\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 15th IEEE International Conference on Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICON.2007.4444074\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 15th IEEE International Conference on Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICON.2007.4444074","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Novel Overlay-Based Failure Detection Architecture for MANET Applications
Abstract-Node failures and message losses are frequent in MANETs. This paper proposes a novel overlay-based architecture for MANET applications to ensure that if a node fails, all the other nodes will be notified. Nodes form a self-organizing overlay network that is overlayed on the physical network. In an overlay network, a set of nodes, called detectors, periodically sense each other's heartbeat messages. Every detector also senses the heartbeat messages of a set of nodes. If a detector does not hear from a node after a timeout (possibly due to node failure or message loss), it identifies the failure of the node according to a set of failure detection rules and then reports the failure to all the other nodes. A simulation is done to demonstrate scalability and to compute the number of non-failed nodes declared as failed. Finally, we describe a use case for recovery in a conferencing situation in MANETs.