{"title":"Network-integrated edge computing orchestrator for application placement","authors":"Vasileios Karagiannis, Apostolos Papageorgiou","doi":"10.23919/CNSM.2017.8256008","DOIUrl":null,"url":null,"abstract":"In an effort to detach applications from centralized clouds with high latency responses, service providers turn their attention to edge computing solutions that offer low latency and improved user experience. Existing edge deployment strategies use network-related information as decision basis, but their design and their placement logic are biased by the assumption that the network cannot be controlled. In this paper, we design an orchestrator that operates within the telecom infrastructure and assumes cooperation with access and core network controllers. As a result, network adjustments can be requested, which leads to an orchestrator that participates in the provisioning of resources and solves an optimization problem that — contrary to the state of the art-performs sequential component placement and does not assume a known or fixed replication degree of the applications. Its function relies on heuristics, including one based on pre-computed shortest paths, which runs in polynomial time (i.e., much faster than an exhaustive search) and finds the optimal solution in approximately 99% of the tested scenarios.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"22","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 13th International Conference on Network and Service Management (CNSM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/CNSM.2017.8256008","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 22
Abstract
In an effort to detach applications from centralized clouds with high latency responses, service providers turn their attention to edge computing solutions that offer low latency and improved user experience. Existing edge deployment strategies use network-related information as decision basis, but their design and their placement logic are biased by the assumption that the network cannot be controlled. In this paper, we design an orchestrator that operates within the telecom infrastructure and assumes cooperation with access and core network controllers. As a result, network adjustments can be requested, which leads to an orchestrator that participates in the provisioning of resources and solves an optimization problem that — contrary to the state of the art-performs sequential component placement and does not assume a known or fixed replication degree of the applications. Its function relies on heuristics, including one based on pre-computed shortest paths, which runs in polynomial time (i.e., much faster than an exhaustive search) and finds the optimal solution in approximately 99% of the tested scenarios.