{"title":"A Randomized Low Latency Resource Sharing Algorithm for Fog Computing","authors":"R. Beraldi, Gabriele Proietti Mattia","doi":"10.1109/DS-RT47707.2019.8958709","DOIUrl":null,"url":null,"abstract":"In this paper, we propose and report a study of a low latency resource sharing protocol for Fog Computing. The protocol has its root in the power-of-random choices family of randomization protocol. The protocol, dubbed $LL_{g}(T)$ is designed to cope with a not homogeneous set of nodes and dealing with a communication latency comparable with the task execution, a characteristic of time-constrained applications supported by this service delivery model. The protocol allows to determine when a task can be moved from the origin fog node that receives the task to another node, where it can be executed faster. This task handoff is controlled via a threshold T. The remote node is selected uniformly at random.","PeriodicalId":377914,"journal":{"name":"2019 IEEE/ACM 23rd International Symposium on Distributed Simulation and Real Time Applications (DS-RT)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE/ACM 23rd International Symposium on Distributed Simulation and Real Time Applications (DS-RT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DS-RT47707.2019.8958709","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, we propose and report a study of a low latency resource sharing protocol for Fog Computing. The protocol has its root in the power-of-random choices family of randomization protocol. The protocol, dubbed $LL_{g}(T)$ is designed to cope with a not homogeneous set of nodes and dealing with a communication latency comparable with the task execution, a characteristic of time-constrained applications supported by this service delivery model. The protocol allows to determine when a task can be moved from the origin fog node that receives the task to another node, where it can be executed faster. This task handoff is controlled via a threshold T. The remote node is selected uniformly at random.