Cheikh Saliou Mbacke Babou, Y. Owada, M. Inoue, K. Takizawa, T. Kuri
{"title":"HEC-NerveNet: A Resilient Edge Cloud Architecture for Beyond 5G Networks","authors":"Cheikh Saliou Mbacke Babou, Y. Owada, M. Inoue, K. Takizawa, T. Kuri","doi":"10.1109/iccworkshops53468.2022.9814556","DOIUrl":null,"url":null,"abstract":"Edge computing system is facing real challenges with the evolution of new information and communication technologies (ICT). In addition, with the advent of Internet of Things (IoT) and real-time services, current edge computing system is becoming an architecture that is inappropriate for some services that require ultra low-latency and very high throughput. In order to meet all the requirements of these services, a new edge computing architecture is required. For this purpose, Home Edge Computing (HEC) architecture has been proposed. However, edge computing system has encountered some issues such as resource limitation on home servers. Furthermore, most distributed systems (e.g. HEC) operate in online mode. In other words, once failures occur in the Internet (remote servers), applications/services will be not longer accessible. In this paper, we propose HEC-NerveNet architecture, a technique based on the HEC architecture and NerveNet technology (HEC-N), to allow users to have continuity of services (resilient), even if they do not access to the remote servers (cloud computing). As a reminder, NerveNet is a resilient distributed architecture that we proposed in 2011 after the natural disaster in Japan. It allows maintaining connectivity and services in case of network failure. In addition, NerveNet solution allows the automatic clustering, and fast recovery thanks to the mesh topology on NerveNet network. This can overcome the need to manually create clusters in the HEC architecture. In the simulation, we prove that our proposal (HEC- N) is very suitable for resilient architecture and the need for future generation networks (beyond 5G/6G networks) with improving the metrics such as ultra-low latency and very high throughput compared with the current HEC and NerveNet systems.","PeriodicalId":102261,"journal":{"name":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Communications Workshops (ICC Workshops)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/iccworkshops53468.2022.9814556","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
Edge computing system is facing real challenges with the evolution of new information and communication technologies (ICT). In addition, with the advent of Internet of Things (IoT) and real-time services, current edge computing system is becoming an architecture that is inappropriate for some services that require ultra low-latency and very high throughput. In order to meet all the requirements of these services, a new edge computing architecture is required. For this purpose, Home Edge Computing (HEC) architecture has been proposed. However, edge computing system has encountered some issues such as resource limitation on home servers. Furthermore, most distributed systems (e.g. HEC) operate in online mode. In other words, once failures occur in the Internet (remote servers), applications/services will be not longer accessible. In this paper, we propose HEC-NerveNet architecture, a technique based on the HEC architecture and NerveNet technology (HEC-N), to allow users to have continuity of services (resilient), even if they do not access to the remote servers (cloud computing). As a reminder, NerveNet is a resilient distributed architecture that we proposed in 2011 after the natural disaster in Japan. It allows maintaining connectivity and services in case of network failure. In addition, NerveNet solution allows the automatic clustering, and fast recovery thanks to the mesh topology on NerveNet network. This can overcome the need to manually create clusters in the HEC architecture. In the simulation, we prove that our proposal (HEC- N) is very suitable for resilient architecture and the need for future generation networks (beyond 5G/6G networks) with improving the metrics such as ultra-low latency and very high throughput compared with the current HEC and NerveNet systems.