Premium
A two‐layer model for improving the energy efficiency of file sharing peer‐to‐peer networks
Author(s) -
Trunfio Paolo
Publication year - 2014
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.3213
Subject(s) - computer science , peer to peer , distributed hash table , file sharing , set (abstract data type) , search engine indexing , energy consumption , distributed computing , sleep mode , torrent file , aggregate (composite) , computer network , efficient energy use , energy (signal processing) , layer (electronics) , journaling file system , computer file , world wide web , database , the internet , engineering , materials science , mathematics , power consumption , composite material , power (physics) , quantum mechanics , programming language , statistics , physics , electrical engineering , chemistry , organic chemistry
Summary As peer‐to‐peer networks gather and share large sets of computing resources, their aggregate energy consumption is an important problem to be addressed, given the economic and environmental impact of energy production and use. This is particularly true for file sharing peer‐to‐peer networks, considered the vast number of nodes participating to these systems. To address such problem, this paper proposes a peer‐to‐peer file sharing model organized in two logical layers. The lower layer is composed of a set of peers providing the files to be shared. The upper layer includes a set of super peers organized to form a distributed hash table, whose purpose is indexing files and peers, including their availability status. Following a sleep‐and‐wake approach, energy saving is achieved by letting peers cyclically switch between normal and sleep modes, where the time passed in normal mode by a peer depends on the number of files it provides. An energy‐saving algorithm and an associated file search and retrieval strategy are proposed within this model. Simulation results show that more than 50% of energy can be saved using the proposed model and that more than 80% of file downloads start with no additional delay compared with a network in which all peers are always powered on. Copyright © 2014 John Wiley & Sons, Ltd.