Beyond the Clouds: How Should Next Generation Utility Computing Infrastructures Be Designed?

Bertier, Marin; Desprez, Frédéric; Fedak, Gilles; Lèbre, Adrien; Orgerie, Anne‐Cécile; Pastor, Jonathan; Quesnel, Flavien; Rouzaud-Cornabas, Jonathan; Tedeschi, Cédric

doi:10.1007/978-3-319-10530-7_14

Cited by 10 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, centralized architectures suffer downsides such as traffic delays, replication of data and scalability issues related with the physical constraints of datacenter resources. Moreover, it forces other actors involved in the communication (such as Internet Service Providers) to oversize their infrastructure in consequence [6].…”

Section: Context and Motivationmentioning

confidence: 99%

Microcities: A Platform Based on Microclouds for Neighborhood Services

Cuadrado-Cordero

Cuadrado

Phillips

et al. 2016

Algorithms and Architectures for Parallel Processing

Self Cite

View full text Add to dashboard Cite

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...

show abstract

Section: Context and Motivationmentioning

confidence: 99%

Microcities: A Platform Based on Microclouds for Neighborhood Services

Cuadrado-Cordero

Cuadrado

Phillips

et al. 2016

Algorithms and Architectures for Parallel Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Besides, a new model emerges: decentralized Cloud infrastructures [29]. Cloud providers expect to improve the performance of their Cloud and to leverage their available infrastructure.…”

Section: Offloading Data To the Edgementioning

confidence: 99%

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

Orgerie

Rodero³

et al. 2018

Future Generation Computer Systems

Self Cite

View full text Add to dashboard Cite

Internet of Things (IoT) is bringing an increasing number of connected devices that have a direct impact on the growth of data and energy-hungry services. These services are relying on Cloud infrastructures for storage and computing capabilities, transforming their architecture into more a distributed one based on edge facilities provided by Internet Service Providers (ISP). Yet, between the IoT device, communication network and Cloud infrastructure, it is unclear which part is the largest in terms of energy consumption. In this paper, we provide end-to-end energy models for Edge Cloud-based IoT platforms. These models are applied to a concrete scenario: data stream analysis produced by cameras embedded on vehicles. The validation combines measurements on real test-beds running the targeted application and simulations on well-known simulators for studying the scaling-up with an increasing number of IoT devices. Our results show that, for our scenario, the edge Cloud part embedding the computing resources consumes 3 times more than the IoT part comprising the IoT devices and the wireless access point.

show abstract

“…Similar to Chord, nodes in Koala are organized logically in a ring by assigning them a unique m-bit ID from a circular ID space, as shown in Figure 2. However, in contrast to Chord, routing in Koala is bidirectional, meaning that the logical distance d between two IDs is the smallest between the distances calculated in both directions, clockwise and counterclockwise, and it is defined as follows: (1) Each node has a routing table. For each entry of the routing table, a node stores four fields: i) the logical ID, ii) the IP, iii) the latency when reaching that entry expressed in Round Trip Time (RTT) and iv) an Ideal ID (IID) field that we explain below.…”

Section: B Koala: Under the Hoodmentioning

confidence: 99%

“…Various initiatives, such as the Discovery project [1], have suggested an alternative to such a centralized architecture by bringing the Cloud even closer to its clients. They propose a fully decentralized architecture which leverages the existing Internet Service Provider (ISP) backbone network infrastructures, by introducing computing resources in Point of Presence (PoP) within the backbone.…”

Section: Introductionmentioning

confidence: 99%

Koala: Towards Lazy and Locality-Aware Overlays for Decentralized Clouds

Tato

Bertier

Tedeschi

2018

2018 IEEE 2nd International Conference on Fog and Edge Computing (ICFEC)

Self Cite

View full text Add to dashboard Cite

Current cloud computing infrastructures and their management are highly centralized, and therefore they suffer from limitations in terms of network latency, energy consumption, and possible legal restrictions. Decentralizing the Cloud has been recently proposed as an alternative. However, the efficient management of a geographically dispersed platform brings new challenges related to service localization, network utilization and locality-awareness. We here consider a cloud topology composed of many small datacenters geographically dispersed within the backbone network. In this paper, we present the design, development and experimental validation of Koala, a novel overlay network that specifically targets such a geographically distributed cloud platform. The three key characteristics of Koala are laziness, latencyawareness and topology-awareness. By using application traffic, Koala maintains the overlay lazily while it takes locality into account in each routing decision. Although Koala's performance depends on application traffic, through simulation experiments we show that for a uniformly distributed traffic, Koala delivers similar routing complexity and reduced latency compared to a traditional proactive protocol, such as Chord. Additionally, we show that despite its passive maintenance, Koala can appropriately deal with churn by keeping the number of routing failures low, without significantly degrading the routing performance. Finally, we show how such an overlay adapts to a decentralized cloud composed of multiple small datacenters.

show abstract

Beyond the Clouds: How Should Next Generation Utility Computing Infrastructures Be Designed?

Cited by 10 publications

References 36 publications

Microcities: A Platform Based on Microclouds for Neighborhood Services

Microcities: A Platform Based on Microclouds for Neighborhood Services

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

Koala: Towards Lazy and Locality-Aware Overlays for Decentralized Clouds

Contact Info

Product

Resources

About