2023年7月17日发(作者:)
圜脚圜  ̄ ey oflMo Ck ̄ud ̄ uling xioopeng Fan,Jiannong Cao,and Haixia Mao A S u rvey of Mobi le Cloud Co m p uti n g 一1●_一 (1.Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences; 2.Department of Computing,Hong Kong Polytechnic University; 3 Department of Land Surveying and Geo-informatics,Hong Kong Polytechnic University) Abatract:Mobile Cloud Computing(MCC)is emerging as one of the most important branches of cloud computing.In this paper,MCC is defined as cloud computing extended by mobility,and a new ad—hoc infrastructure based on mobile devicesIt provides mobile .users with data storage and processing services on a cloud computing platform Because mobile cloud computing is still in jts infancy we aim to clarify confusion that has arisen from different views.Existing works are reviewedand an overview of recent advances In 。mobile cloud computing is provided.We investigate representative infrastructures of mobile cloud computing and analyze key components.Moreover。emerging MCC models and services are discussed,and challenging issues are identified that will need to be addressed in future work. Keywords:mobile cloud computing;cloud computing 1 l ntroduction ince the first computer was invented in 1 946,people have whethe r it is caIled cloud computing or on—demand computing Software as a resources in mobile devices But what does mobile cloud computing really mean?Different people hold different views and there are several existing definitions of mobile cloud computing Service(SaaS)or Internet as platform, the overriding idea is a shlfI in the dreamt of using computing resources as a utiIity—l ke water geography ot computation In general,cloud computing is In[14],mobile cloud computing was first referred fo as aR infrastructure electricity,gas,or the telephone There has been a long—held perception that computing wiI Ione day be the fifth web-based processing[7],whereby shared resources,software,and information are provided on demand to where data storage and processing could happen outside the mobile device,enabling a new class of applications--especially context-aware mobile sociaI networks Mobile cloud applications move computing power and data storage away frOm mobile phones and into the utility Cloud computing[1]-[6]might be the most promising way of realizing this dream. fn recent research on cloud computers,smartphones『81,and other similar devices.Cloud computing is also a new style of computing in which dynamically scalable resources are computing,one of the most important lssues has been how to sweep up data provided as vi rtualIzed services『91. This allows service p roviders and users and programs from desktop PCs[1】 and instalI them in the compute cloud. to adjust their computing capacity depending on how much is needed at a cloud This brings mobile applications and computing not iust to smartphone users buf to a broad range of mobile subsc ribers. Cloud computing refers to applications delivered as services ove r the Internet and also the hardware and systems software in the data centers thal given time or for a given task Mobile computing[1 0]means using portable devices to run stand-alone In terms of services『71,mobile cloud computina extends processing and applications and/or accessing remote applications via wireless networks. Increasing the number of mobile applications demands g reate r resources and improved inte ractivity for p rovide those services[2]However, This research is partially supported by Hong storage beyond devices and seamlessly integrates with other se rvices and sensor data to open up new classes of application Kong RGC under the GRF grant PolyU51 0611 0E and Nokia Research Lab(Belling)under the grant H—ZG19.This work is also partially better experience Resources in cloud In[9],mobile cloud computing is defined as an extension of cloud computing in which foundation supported by the National S&T Major Project of China under No.2009ZX03006-001 and Guangdong S&T Major Project under No.2009AO802O7002. platforms such as Amazon EC2『1 11, Microsoft Azure f1 21 and Google AppEngine[13]can remedy the lack of hardware consists at least partly of Z'rE COMMUNICATIONS] mobile devices This definition recognizes the opportunity to harness collective sensing,storage,and computationaI capabiIities of multipie networked wi reless devices to create a distrjbuted infrastructure lhal supports a wealth of new applIcations. Therefore our goaI in this survey is to eliminate confusion by clarifying the terms and concepts,p redicting slate—Of—the—a rl mobiIe cloud computing,discussing future trends, and identifyinq technicaI and n0n—lechnjcaI obstacles and opportunities 2 Mobile Cloud Computing Definitions of mobile cloud computing can be divided into two classes The first refers to carrying out data storage and P rocessina outside moblle devices『1 51 Mobile devices are simply ferminals in cloud computing. only intended to provide a more convenient way of accessing services in lhe cloud The benefil of this is thal storage and computing Iimitations of mobile devices are avoided,and a new IeveI of security is provided by centralizing maintenance of security—criticaI software The second class of definitions refers to comPuting where data stora#e and p rocessing are also carried out on mobile devices『91 The infrastructure of the cloud is different frOm that of data—center“pay—as—you—use”cloud computing.Each node is owned by a differenl user and js Iikely to be mobjle Using mobile hardware for cloud computlng has advantages over using traditionaI hardware These advantages include computational access to multimedia and sensor data without the need for large network transfers,more efficienf access to data stored on other mobile devices,and distributed owne rship and maintenance of hardware In lhis pape r mobile cloud computing is defined as cloud computing extended by mobility and a new ad—hoc infrastrucfure based on mobile devices It p rovides mobile users with data storage and processing services on a cloud computing A Survey of Mobile Cloud Computing Xiaopeng Fan,Jiannong Cao,and Haixia Mao platform Using this definition.we clarify overcome these obstacles For two differences between mob_le example.Iong WAN latencies are a computing and cloud computing fundamentaI obstacle when a mobile First lhere is an overlap between lhe device executes a resource—intensive two computing paradigms Cloud application on a distant computing aims to provide services to hiah-performance server or cluster A users without letting them know where solution is lo instantiate customized these services are hosted or how they service software on a nearby cloudIel are de¨vered Mobile computing aims 『1 81 and then to use thaf service over a to support mobiIity so lhal users can wi reless LAN access resources with wireless technology. Second it is possible lo build up 3 Existing Works On Mob_le clouds within mobiIe devices for data Cloud Computing storage and processing.Although According to our definition of mobile mobile devices nowadays are weak in cloud comPutjng。there are two key terms ot energy,power,storage,and issues:How to build up a mobile cloud communication.1his situation wiII be using mobile devices and how to improved d ramatically with lhe access services provided by clouds in development of technology In[9], a mobile way.Thus.existing work on Hyrax shows that a platform derived mobile cIoud comPuting can be from Hadoop[1 6】can support cloud classified as that based on the cloud computing on And roid n 71 Platform.or that based on access smartphones lt demonstrates the schemes For the former we investigate possjbility that a cloud composed of existing work on mobile cloud platforms mobile devices can provide basic consisting of mobile devices.The Hyrax functions and services of cloud 『91 platform js derived from Hadoop computing [1 6]and supports cloud computing on Whv do we need mobile cloud And roid『1 71 smartphones To the best computing?There are at least three of our knowledge it is the only platform possible explanations. comprised of mobiIe devices For the Flrs1.mobility support is very Iatter.we investigate exjstina access important in allowing users access lo schemes in mobile cloud computing cloud services.Service availability is MobiIe cloud computing is stilI in its considered the first obstacle『91 for infancy.and we investigate Virtual cloud computing.Mob_le cloud Machine(VM)一based cloudlets『1 81 computing exploits information about a and inte…gent access schemes『1 51 user’s location,context,and requested services and significantly evolves the 3.1 Hyrax heterOgeneOus access management The goal of Hyrax is to develop a schemes for traditionaI heter0aeneOus mobiIe cloud infrastructure that enables access scenarios This is called smartphone applications with “intel Jigent access”n 51.It can distributed data and computation noticeably improve user experience Hyrax aIlOWS app Jications to Second.the capacity of moblle conveniently use data and execute devices has increased dramaticallY computing Jobs on smartphone with the growth of mobile users, networks and helerOaeneOus networks especially with the prevalence of of phones and servers Research has  ̄martphone use rs Each mobile device been focused primarily on has storage,computing,senslng,and implementation and evaluation of power resources By using these mobiIe cloud computing nfrastructure resources,applications or services can based on MapReduce『1 91 be easily accessed by users inside and MapReduce,Hadoop,and And roid outside ihe mobile network shouId be introduced before descrjbing Thi rd.1here are st…some obstacles Hyrax infrastructure. to implementing cloud computing,and MapReduce is conside red a mobile computing technology can help prog ramming modef for processmg and ZTE COMMUNICATIONS@ 函警珊四 0fM0 CloudC0rnpU付ng . .竺 does not support peer—to—peer networking yet,the phones communicate with each other on an isolated 802 1 l g network via a Linksys WRT54G wireless router with no firmware modificationsNameNode and Job 1 racker processes are run on a .desktop machine connected behind this router via EthernetThe phones are .connected via USB to a controller that executes experiment scriptsThese scripts are used to install Hyrax.. generating large data setsA user specifies a map function that processes .separate Android servi’ce processes within the same applicationAndroid applications may consist of multiple .initialize the clusterrun benchmarks,, and collect and post process data. a key/value pair in order to generate a set otintermediate key/value pairs lt also has a reduce function that me rges all intermediate values associated with the same lntermediate keyThe MapReduce runtime system splits input .processes,some of which run as backg round servicesSince DataNode .1 o determine the advantages and drawbacks of Hyraxan application ,was developed on it.The Hyrax multimedia search and sharing applicationHyraxTube,allows users to ,and TaskTracker are run as Android services,they can run in the background of other appIications browse videos and images stored on a data,schedules map and reduce tasks .A thread is also spawned to record mtormation about the system and transfers input and output data to machines running the tasksThe re is a .network ot phones and search by timelocation,and qualityQuality ratings ..。 based on sensor data are generated by .load--including power leve1 and CPUmaster to manage jobs,assign tasks to slave machines,and provide focations ot ntermediiate values fo reduce tasks. memory,network,and disk l/O statistics--into the Ioca1 fi Ie system Within the applicationa server is run tO ,period ical ly executing a MapReduce Job-Requests are serviced by reading results generated by the MapReduce Job from HDFS The client interface is implemented as a web application so Apache Hadoop js an open source allow externaf scripts to centreI data uploading,kil lthe programand check ,implementation of MapReduce that is used by many organizations for that it can be used on mobile devices and desktop machines. the program status.Fig2 illustrates the .large—scale data processing.1t is designed to operate data stored in a distributed file systemHadoop ,data Jnteractions between al{the software components on each phone Hyrax IS implemented jn a rea J testbed consisting of a cluster of 1 0 3.2 VM——Based Cloudlets Satyanarayanan et a1[1 8】present a .Distributed File System(HDFS)There are tour types of processes in Hadoop lnstances:NameNode,JobTrackerDataNode,and TaskTrackerThere is . .Android G 1(HTC Dream)phones and 5 HTC Magic phoneseach running Android 1l5 CupcakeSince Android ,.new VISIOn for mobile cloud computing J hey foresee a new world in which mobile computing seamlessly augments users’cognitive abilities via one NameNode and one JobTracker in a Hadoop cluster NameNode schedules jobs and coordinates sub—tasks among TaskTrackers A DataNode instance and a TaskTracker jnstance both run on each worker machine.DataNode stores and provides access to data blocksand l ask l racker executes tasks assigned to it by JobTracker Clients access files ,by tirst requesting block Iocations from NameNode and then requesting blocks directly from these Iocations The hardware and software layers of Hvrax are described ln Fig.1 Hyrax ports Hadoop to the Android platform.fn Hyrax,each machine runs one fnstance of NameNode and one Jnstance of JobTracker.DataNode and IaskI racker are run on each phone in
发布者:admin,转转请注明出处:http://www.yc00.com/news/1689543135a264771.html
评论列表(0条)