Please wait a minute...

Current Issue

    25 July 2011, Volume 32 Issue 7
    Comprehensive Review
    Cloud computing:architecture and key technologies
    Jun-zhou LUO,Jia-hui JIN,Ai-bo SONG,Fang DONG
    2011, 32(7):  3-21.  doi:1000-436X(2011)07-0003-19
    Asbtract ( 0 )   HTML ( 4)   PDF (306KB) ( 58 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Based on the analysis and summary of the previous work,the cloud computing framework can be divided into three layers:core cloud services,cloud service management and user access interface.To realize low-cost,reliable,available and scalable cloud services,the up-to-date key technologies and research progresses of the three layers within the cloud framework are reviewed intensively and extensively.Regarding cloud infrastructure,the strategies for data center design and management are introduced together with the virtualization technology.In respect of large-scale data processing,several platforms and their resource management and task scheduling mechanisms are investigated extensively.With regard to cloud service quality,both QoS guarantee and security/privacy protection are discussed in depth.The prospects for future research are further explored based on the new application models and limitations of cloud computing.Finally,the cloud computing platform and research work of Southeast University are introduced.

    Network optimization
    Fast route model in peer to peer network
    Shan-xiong CHEN,Li LI,Lin ZHANG
    2011, 32(7):  22-28.  doi:1000-436X(2011)07-0022-07
    Asbtract ( 0 )   HTML ( 0)   PDF (175KB) ( 5 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    A fast self-organizing routing model (FSRM) was proposed based on In the model,the approach of the route lookup,the system of nodes joining and leaving was described.When joining node need to select neighboring nodes,measured scheme of stability threshold ensure that the peer to peer network fast routing and convergence.The simulation results of the model performance are analyzed to prove the convergence time,node querying speed and adaptability to churn are better than the traditional model.

    Distance aware route algorithm for cloud computing based on CAN
    2011, 32(7):  29-39.  doi:1000-436X(2011)07-0029-11
    Asbtract ( 96 )   HTML ( 0)   PDF (384KB) ( 59 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Based on the traditional CRP mechanism,a new mechanism called M-CRP which is more adapt to the cloud computer mechanism was advanced.Based on traditional CAN,a new mechanism called M-CRP-CAN which make full use of M-CRP and make not only the CAN framework structure award of the physical location of nodes was advanced but also the routing mechanism give more thought about the physical topology.The self-adaption can make the M-CRP-CAN has more ability to change according to the net status.In network simulation platform,the experimental results show that M-CRP’s performance is better than CRP in aspect of efficiency and precision.This M-CRP improves CRP from aspect of efficiency,precision and performance with multi-level mechanism,which make the node in cloud,has more perception to the underlying topology.In the meantime the M-CRP-CAN with M-CRP approach has realized localization download and greatly raised the data transfer rate,reduced the cross-traffic in backbone network and improve the network performance therefore enhance cloud computing system efficiency.,

    Resource management
    Reliability enhenced resource reservation strategy in computing grid
    Chang-song DING,Zhi-gang HU,Peng XIAO
    2011, 32(7):  40-46.  doi:1000-436X(2011)07-0040-07
    Asbtract ( 97 )   HTML ( 0)   PDF (129KB) ( 88 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    A stochastic model was used to describe reservation service of grid resources and an approach calculating reliability-guarantee expressed as probability guarantee success rate was proposed for reservation requests.By the approach,a reliability-enhenced reservation strategy was proposed.Experimental results show that the proposed strategy can significantly improve resource utilization.Also,it is able to reduce the jobs' violation rate comparing to conventional reservation policy,with respect to adaptability to dynamic grid environment.

    Adaptive delay scheduling algorithm based on data center load analysis
    Jia-hui JIN,Jun-zhou LUO,Ai-bo SONG,Fang DONG
    2011, 32(7):  47-56.  doi:1000-436X(2011)07-0047-10
    Asbtract ( 106 )   HTML ( 2)   PDF (193KB) ( 107 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Current delay scheduling algorithms,based on static waiting time threshold,can not ada dynamic load of a data center.To address this issue,an adaptive waiting time threshold model was proposed.Based on this model,an adaptive delay scheduling algorithm (ADS) was designed.ADS adjusts jobs’waiting time threshold dynamically to reduce the job response time,according to the information of idle servers’ arrival intensity,available network bandwidth and job running status.A prototype system using ADS was developed,on which the validation of the adaptive waiting time threshold model and the evaluation of ADS’s performance were carried out.It is shown that ADS outperforms previous delay scheduling algorithms in term of the job response time.

    Forecast-based resource reconfiguration algorithm for network virtualization
    Shun-li ZHANG,Xue-song QIU,Ya-lian PAN,Luo-ming MENG
    2011, 32(7):  57-63.  doi:1000-436X(2011)07-0057-07
    Asbtract ( 72 )   HTML ( 0)   PDF (155KB) ( 160 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In order to solve imbalance issues of used resources of substrate network,which are brought by virtual network joining and leaving dynamically,forecast-based resource reconfiguration algorithm (FRRA) for network virtualization environment was proposed.Algorithm FRRA took ful advantage of known information to calculate interval of reconfiguration and used this interval to replace the periodic time span in previous algorithms.In order to make reconfiguration time global optimal,it took two measures:resources were divided into critcal resources and general resources,and different algorithms were used to key resources and common resources respectively; according to the probability that resource migration was failure,the limit number of reconfiguration requests was deduced.FRRA algorithm with VNA-II algorithm and PMPA algorithm in the experiments was compared.The results show that algorithm FRRA reduces reconfiguration cost 69% than that of VNA-II and 42% than that of PMPA.Algorithm FRRA improves VN request reception rate 29% than that of VNA-II and 52% than that of PMPA.

    Dynamical resource allocation algorithm research in network virtualization
    Juan LUO,Yue-yang XU,Ren-fa LI
    2011, 32(7):  64-70.  doi:1000-436X(2011)07-0064-07
    Asbtract ( 75 )   HTML ( 4)   PDF (137KB) ( 159 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Aim to the problem of resource allocation,a dynamical algorithm of allocating resource was proposed.The algorithm dynamical migrates virtual node,which based the average load discrepant degree of physical nodes and the tolerant load discrepant degree of substrate network.It will choose a proper host according to the values of synthetically impact factor ,that reduce impact on the delay of vir l link and the bandwidth of physical link.Simulation result shows that the algorithm can improve load balance on physical nodes,and reduce negative impact on delay and bandwidth.

    Guarantee of QoS
    Services selection based on trust evolution and union for cloud computing
    Chun-hua HU,Ji-bo LIU,Jian-xun LIU
    2011, 32(7):  71-79.  doi:1000-436X(2011)07-0071-09
    Asbtract ( 92 )   HTML ( 0)   PDF (146KB) ( 113 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    It was difficult for the service consumers to obtain high-quality composite services because of the existence of false or malicious service nodes in cloud computing en ironment.A novel cloud service-composition method based on the trust span tree was proposed.The trust relationship could be built after many times credible interaction between services requester and provider,and the trust union would be formed through the credible relationship evolution.So that the uncertain or malicious service should be excluded from the trust span tree,and the service composition would be carried out in a trust environment.At the same time,the measur ng strategy of trust relationship among cloud services based on information entropy was designed,which could resolve the deficiencies of the trust parameter analysed by simply weighted angle in the previous studies.The experimental result shows that the method proposed in this paper is more superior in credibility and security,comparing to the traditional services selection methods.

    Optimal service selection approach considering both atomic transaction and end-to-end QoS constraints
    Hai LIU,Wei-min ZHANG,Zhu-xi ZHANG,Xiong JIA,Wei LIAO
    2011, 32(7):  80-92.  doi:1000-436X(2011)07-0080-13
    Asbtract ( 65 )   HTML ( 0)   PDF (262KB) ( 37 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    An actual SCG (service candidate graph) model-based optimal service selection approach was proposed.,the approach created transactional constraint relationships among candidates as an actual SCG model with severa building rules,whose correctness had been also proved; Then,an optimal QoS-aware service selection algorithm on the basis of BFS (breadth first search) was designed,where a relaxing and pruming method was applied to keep the computation scale in polynomial time.Finally,simulation experiments were conducted with real-world QoS dataset and random dataset,whose results demonstrated the beneficial performance on global QoS utility and outstanding successful selecting ratio over other related work.Meanwhile,the correctnesss has also been proved in practice by implementing a transactional automation.

    QoS preference-aware replica selection strategy in cloud computing
    Run-qun XIONG,Jun-zhou LUO,Ai-bo SONG,Jia-hui JIN
    2011, 32(7):  93-102.  doi:1000-436X(2011)07-0093-10
    Asbtract ( 102 )   HTML ( 5)   PDF (212KB) ( 435 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    A QoS preference-aware replica selection strategy for a kind of users with individual QoS sensitivity (IQS) constraints in cloud computing datacenters was put forward in advance.According to the QoS requirements of data services from IQS users,a novel three-dimensional QoS model of replica selection was introduced,and a QoS preference-aware algorithm based on analytic hierarchy process (AHP) named QoPA was proposed to deal with the IQS constraints.In order to evaluate the replica sites in datacenters and provide the best of them to the IQS users,an algorithm for replica selection based on fuzzy comprehensive evaluat termed FCE_RS was designed and implemented.Results of experiments show that the FCE_RS can serve the various IQS users in cloud computing very well by providing reasonable replica strategies effectively.

    Noisy template skip list based log filtering in cloud systems
    Xiang RAO,Huai-min WANG,Hua CAI,Qi ZHOU,Ting-tao SUN,Dian-xi SHI,Gang YIN
    2011, 32(7):  103-113.  doi:1000-436X(2011)07-0103-11
    Asbtract ( 60 )   HTML ( 0)   PDF (235KB) ( 64 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    First model noisy event logs into time series,use Haar wavelet transform to get the approximation time series and construct the noisy template library with skip list.Then,the similarity between target log time series and noisy template to filter the noisy logs was compared.Experiment results on a real cloud service shows that successfully filter out the noisy log and increase the validity of fault feature.

    Hierarchical diagnostic approach for performance problems in cloud computing platforms
    Hai-bo MI,Huai-min WANG,Hua CAI,Gang YIN,Qi ZHOU,Ting-tao SUN,Yang-fan ZHOU
    2011, 32(7):  114-124.  doi:1000-436X(2011)07-0114-11
    Asbtract ( 67 )   HTML ( 0)   PDF (228KB) ( 77 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    A hierarchical diagnosis approach,namely Magnifier,was proposed,which models the execution path graph of a user request as component layer,module layer and function layer,and detects anomalies from higher layer to lower layer separately.Extensive experiments were conducted on the Alibaba cloud computing platform.The results indicate that,under the conditions of large volume of data and high complexity of execution paths,Magnifier can accurately and efficiently locate the prime causes of performance degradation.

    Access control and trust mechanism
    Achieving efficient dynamic cryptographic access control in cloud storage
    Cheng HONG,Min ZHANG,Deng-guo FENG
    2011, 32(7):  125-132.  doi:1000-436X(2011)07-0125-08
    Asbtract ( 133 )   HTML ( 7)   PDF (151KB) ( 924 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    To keep the data in the cloud confidential against unauthorized parties,a cryptographic access control solution called hybrid cloud re-encryption (HCRE) based on attribute-based encryption (ABE) was introduced.HCRE designed a secret sharing scheme to delegate the task of ABE re-encryption to the cloud service provider (CSP),which alleviates the administering burdens on the data owner.Experiments show that HCRE can handle dynamic access policies in a more efficient way.Additionally,HCRE does not reveal extra nformation of the plaintext to the CSP,thus it does no harm to the data confidentiality.

    New mapping approach based on reputation model under locator/ID separation protocol
    Ming WAN,Ying LIU,Hong-ke ZHANG
    2011, 32(7):  133-145.  doi:1000-436X(2011)07-0133-13
    Asbtract ( 45 )   HTML ( 0)   PDF (240KB) ( 49 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Through analyzing mapping spoofing which may exist or happen in the incoming mapping theory under locator/ID separation protocol,a new mapping approach to relieve the thread of mapping spoofing was proposed.This approach introduced the reputation model based on feedback evaluation into the mapping theory and increased the trustworthiness of the mapping information by means of the trust evaluation.Meanwhile,the self-certifying identifiers represented the identity information of tunnel routers,and guaranteed the authenticity of the mapping sources.Performance analysis and simulation results have shown that the approach provides a satisfying safeguard for the mapping theory.By setting the threshold of different trust va ue,this approach can effectively inhibit the tunnel routers from employing the mendacious mapping information,and further reduces the hazards of mapping spoofing.

    CP-ABE based data access control for cloud storage
    Guo-zi SUN,Yu DONG,Yun LI
    2011, 32(7):  146-152.  doi:1000-436X(2011)07-0146-07
    Asbtract ( 194 )   HTML ( 18)   PDF (106KB) ( 678 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    To solve the safety issues in cloud storage services for network characteristics and data sharing characteristics,and based on the CP-ABE(cipertext policy–attribute based encryption)algorithm,a cipher text access control mechanism was proposed.According to access control and related architecture,the corresponding secure data structure algorithms were given.After this,the simulations and the performance analysis were given to evaluate our algorithm.Under the premise of untrusted service provider,the proposed mechanism can ensure the data security of the cloud storage system in an open environment,and can reduce right management complexity through property management.

    Data outsourcing authentication model based on authenticated data structures for cloud computing
    Jian XU,Fu-cai ZHOU,Xu CHEN,Zhi-liang ZHU
    2011, 32(7):  153-160.  doi:1000-436X(2011)07-0153-08
    Asbtract ( 86 )   HTML ( 1)   PDF (118KB) ( 165 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The outsourcing authentication model based on authenticated data structures was proposed.The formal definition,data query authentication protocol and data updating authentication protocol of the model was presented.The crucial problems when the authenticated data structures are being used were analyzed.With designing the new extended coherence proof generation algorithm and the new extended verifying algorithm,authenticated data structures in the model very well was used.Finally the model with others through the performance analysis including the security and efficiency,the results of which show that:the model is more efficient than others as well as the con and correctness requirements are also guaranteed.

    Trust transitivity algorithm based on multiple influencing factors for grid environment
    Lin ZHANG,Ru-chuan WANG,Hai-yan WANG
    2011, 32(7):  161-168.  doi:1000-436X(2011)07-0161-08
    Asbtract ( 71 )   HTML ( 3)   PDF (131KB) ( 112 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    A trust deployment scheme based on layered idea was given for grid environment,which reduced the management costs of system.The fine-grain trust model was proposed which was based on interaction capability and honesty ability.It enhanced the rationality of the model.At e same time,4 influencing factors about trust transitivity were discussed,such as cycle path,path length threshold,node honesty threshold and further trust information.On this condition,the trust transitivity algorithm for grid was studied which was based on depth-first traversal.Example and experimental results show that the model and algorithm are feasible and correct.

    Roles query algorithm in cloud computing environment based on user require
    Liu YANG,Zhuo TANG,Ren-fa LI,Zong-li ZHANG
    2011, 32(7):  169-175.  doi:1000-436X(2011)07-0169-07
    Asbtract ( 65 )   HTML ( 0)   PDF (369KB) ( 89 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Roles based access control model CARBAC for cloud computing environment was proposed.Roles in the model include user roles and resources owner roles,the latter were called administrator roles.For the resources owner roles assigning the roles to the users,roles query algorithm in the hybrid hierarchies based on users' access require was proposed.Through this algorithm,for the certain privileges set,this model could choose the least roles set to be assigned to the users.The simulation experiment indicates that for the mass user access,this algorithm can reduce the roles quantity,shorten the authorization procedure,and advance the system efficiency.

    Review of cloud based trust model
    Xin GU,Zheng-quan XU,Jin LIU
    2011, 32(7):  176-181.  doi:1000-436X(2011)07-0176-06
    Asbtract ( 58 )   HTML ( 0)   PDF (108KB) ( 152 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics
    Application of cloud computing
    Intelligent ubiquitous network
    Xiao-yu TONG,Yun-yong ZHANG,Lei XU
    2011, 32(7):  182-188.  doi:1000-436X(2011)07-0182-07
    Asbtract ( 64 )   HTML ( 1)   PDF (429KB) ( 346 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The first overview of ubiquitous computing,cloud computing and ubiquitous network technology was made.Then a new concept of Intelligent ubiquitous network,its concrete realization of the distributed intelligent open system and business data system were proposed.Finally,the network topology,architecture and key technologies of DIOS were discussed in detail.Intelligent ubiquitous network is the trend of future telecommunication network and can provide“everywhere,all-powerful”service.

    Applying MapReduce frameworks to a virtualization platform for Deep Web data source discovery
    Jie XIN,Zhi-ming CUI,Peng-peng ZHAO,Guang-ming ZHANG,Xue-feng XIAN
    2011, 32(7):  189-195.  doi:1000-436X(2011)07-0189-07
    Asbtract ( 46 )   HTML ( 2)   PDF (160KB) ( 79 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In order to improve the performance of Deep Web crawler in discovering and searching data sources interfaces,a new method was raised to parallel processing the mass data within the Deep Web compromising MapReduce programming model and virtualization technology.The new crawling architecture was designed with three producers,the link classified MapReduce,the page classified MapReduce and the form classified MapReduce.Server virtualization was adopted to simulate the cluster environment in order to test the performance.Experiment results indicate that this method is capable for large-scale data parallel computing,can improve the crawling efficiency and avoid wasteful expenditure,which prove the feasibility of applying cloudy technologies into Deep Web data min g field.

    Record matching method based on local CON model in distributed database
    Jiao LI,Quan LIU,Qi-ming FU,Ting-gang WANG
    2011, 32(7):  196-202.  doi:1000-436X(2011)07-0196-07
    Asbtract ( 46 )   HTML ( 0)   PDF (133KB) ( 82 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    For existing record matching methods needed much artificial participation of experts or depend on heuristic rules heavily,and they could not handle the problem of large-scale data,A record matching method based on the local CON model was proposed.The approach used algorithm of association rules to get the match dependence,then took both match dependence and data instances as the input of the improved tableau,finally got the result by match detection.Experimental results and theoretical analysis show that the method can quickly identify whether the distributed records matched,and it doesn’t require artificial participation,much better than previous methods.

Copyright Information
Authorized by: China Association for Science and Technology
Sponsored by: China Institute of Communications
Editor-in-Chief: Zhang Ping
Associate Editor-in-Chief:
Zhang Yanchuan, Ma Jianfeng, Yang Zhen, Shen Lianfeng, Tao Xiaofeng, Liu Hualu
Editorial Director: Wu Nada, Zhao Li
Address: F2, Beiyang Chenguang Building, Shunbatiao No.1 Courtyard, Fengtai District, Beijing, China
Post: 100079
Tel: 010-53933889、53878169、
53859522、010-53878236
Email: xuebao@ptpress.com.cn
Email: txxb@bjxintong.com.cn
ISSN 1000-436X
CN 11-2102/TN
Visited
Total visitors:
Visitors of today:
Now online: