Design and implementation of a P2P Cloud system

Abstract

Cloud Computing has gained popularity in both research and industrial communities. Cloud users can acquire computing resources on a need basis, achieving on demand scalability; Cloud providers can maximize resource utilizations of datacenters, increasing their return on investments. While Cloud systems are usually hosted in large datacenters and are centrally managed, other types of Cloud architectures can be imagined. In this paper we describe the design and prototype implementation of a fully decentralized, P2P Cloud. A P2P Cloud allows organizations or even individual to build a computing infrastructure out of existing resources, which can be easily allocated among different tasks. We focus on the problem of maintaining a coherent structure over a set of unreliable computing resources. We show that gossip-based protocols can be used to maintain an overlay network on top of the computing nodes, and to partition the set of resources into multiple slices in such a way that the failure of individual nodes do not compromise the overall structure. Resource partitioning is one of the most important features of a Cloud, and therefore must be supported efficiently and reliably on any Cloud architecture. We describe a prototype Java implementation that is being developed to demonstrate the effectiveness of the proposed approach.

Energy-efficient peer-to-peer networking for constrained-capacity mobile environments

“…P2P systems have also high potential for optimizing content delivery in otherwise client/server-based systems, such as in cloud computing, where P2P can alleviate server load by taking into use the spare computational and storage resources of end-user devices (Korzun & Gurtov 2013, Babaoglu et al 2012, Trajkovska et al 2010, Zhelev & Georgiev 2011. However, the high energy consumption at peer nodes (Nurminen & Nöyränen 2008) and the limitations concerning the mobile environment (Kellerer et al 2006, Mäkinen & Nurminen 2008) have so far made P2P networking unfeasible in mobile environment.…”

“…P2P networks are known for their superior scalability: since computational resources are provided by participating end-user devices, resources inherently scale up with network size. Whereas with traditional client/server-based architectures, the requirements for service infrastructure grow along with the number of users and the amount of stored and transferred data, P2P-assisted cloud computing (Babaoglu et al 2012, Trajkovska et al 2010, Zhelev & Georgiev 2011 alleviates server load by taking into use the spare computational and storage resources of participating peer nodes. These peer nodes can include end-user devices in addition to dedicated server machines.…”

Decentralized Stream Processing Over Web-Enabled Devices

“…In [4,5], the authors proposed the design and implementation of a generalpurpose framework to support distributed applications running over a very large and unreliable set of networked computing devices. We also adopted the concepts of application suite description and slicing.…”

Outlook on moving of computing services towards the data sources

“…NaDa approach was proposed several years ago (Vytautas et al, 2009) to improve video streaming services taking advantage of the in-transit machines of the IP providers. The same concept has been applied to other applications, for example in P2P clouds based in nano centres (Babaoglu et al, 2012). More recently, multiple layered clouds can solve several IoT applications with nano and micro data centres in front of the conventional cloud infrastructure (Petri et al, 2014).…”