Microcities: A Platform Based on Microclouds for Neighborhood Services

Abstract

Abstract:The current mobile Cloud computing trend has set the focus on the ubiquity of computation. However, the current architecture confines the cloud to datacenters, which are generally far from the user. Distance leads to increased utilization of the broadband Wide Area Network -WAN -and poor user experience, especially for interactive applications. Decentralized architectures are emerging as an alternative, but they still fail to adapt to situations where files are concurrently modified. A semi-decentralized approach which confines local traffic close to the user while still maintaining centralized characteristics, running on the users and network devices, can provide a better Quality of Experience (QoE) in large urban populations in mobile cloud networks. In this report, we propose a novel semi-centralized cloud architecture based on microclouds. Microclouds are dynamically created and allow users to contribute resources from their computers, mobile and network devices to the cloud. We present the process for building and reconfiguring the microclouds, whilst guaranteeing a high QoE to users of real-time applications. We also provide a description of a realistic mobile cloud use-case. Results from a simulation-based evaluation indicate that the microclouds architecture is able to sustain hundreds of mobile devices and provide a latency significantly lower than regular Clouds based on datacenters. Résumé : La tendance actuelle des applications mobiles dans les nuages informatiques (clouds) a mis láccent sur lómniprésence du calcul. Cependant, lárchitecture actuelle confine le cloud dans les centres de données qui sont généralement loin de lútilisateur. Cette distance conduit á une utilisation accrue de la bande passante des réseaux longue distance (Wide Area Network -WAN) et conduit á une expérience utilisateur médiocre, en particulier pour les applications interactives. Les architectures décentralisées apparaissent comme une alternative, mais elles ne parviennent pas toujours á s'adapter á des situations oú les fichiers sont modifiés de maniére concurrente. Une approche semi-décentralisée, mise en oeuvre sur les équipements des utilisateurs et du réseau et confinant le trafic local á proximité de lútilisateur tout en conservant les caractéristiques centralisées, peut fournir une meilleure qualité déxpérience (QoE) aux grandes populations urbaines utilisant les applications mobiles des clouds. Dans cet rapport, nous proposons une nouvelle architecture de cloud semi-centralisée fondée sur les "microclouds". Les microclouds sont créés dynamiquement et permettent aux utilisateurs de fournir au cloud des ressources de leurs ordinateurs, smartphones et équipements réseau. Nous présentons le processus de construction et de reconfiguration des microclouds, tout en garantissant un haut degré de QoE aux utilisateurs dápplications temps-réel. Nous donnons également une description dún cas d'utilisation réaliste de cloud mobile. Les résultats dúne évaluation menée par simulation indiquent que lárchitecture á base de m...

Leveraging Renewable Energy in Edge Clouds for Data Stream Analysis in IoT

“…From the latency point-ofview, we assume a 100 ms Round-Trip-Time (RTT) between the vehicles and the core cloud. This value is similar to what can be observed for accessing an Amazon Cloud for instance [27]. On the side of the solar power production, we employ a mini-scale solar power farm which is set up in the campus of University Nantes 1 .…”

End-to-end energy models for Edge Cloud-based IoT platforms: Application to data stream analysis in IoT

“…From the latency point-of-view, we assume a 100 ms Round-Trip-Time (RTT) between the vehicles and the core Cloud. This value is similar to what can be observed for accessing an Amazon Cloud for instance [54].…”

“…The energy consumption of the network flows depends also on the number of routers they have to cross. We consider a core Cloud located 10 hops away from the access point for a 100 ms Round-Trip-Time according to values measured in [54] between clients and Amazon Cloud. Finally, we consider a PUE of 1.7 in the access point and the network points-of-presence, which is a typical value for small data centers [55].…”

Incentives for Mobile Cloud Environments through P2P Auctions

“…We have chosen to study incentives to the use of neighborhood interactive applications deployed on a MC architecture, such as described in [4]. In this scenario multiple users collaborate using applications in a MC restricted to a neighborhood.…”