Earticle

With the growing number of alternative services in the cloud environment, users have put forward new requirements to solve the service dynamic selection problem quickly and efficiently. In this paper, an evaluation model of service process which considers concurrent requests and service association is proposed. This model evaluates the service process from three dimensions which are functional quality dimension, non-functional quality dimension and transactional dimension. To solve the service selection problem efficiently, we first design a novel coding strategy of particle, and then propose an approach based on hybrid particle swarm optimization algorithm which combines the crossover and mutation operators of genetic algorithm. The experimental results show that our proposed approach is feasible and effective.

Cloud computing is one of the fastest growing internet based technology that facilitates users to utilize services by making use of large poll of resources without installation of any software. Adoption of this technology is increasing rapidly because of many advantages including reduction of cost and IT load. Despite the popularity of cloud computing, it faces many difficulties such as security that is one of the major inhibitors in the growth of cloud computing. Data confidentiality is at the top of the list of security concern for this technology. Many methods have been introduced to overcome this issue; encryption is one of them and widely used method to ensure the data confidentiality in cloud environment. In this study, an attempt is made to review the encryption techniques used for the data confidentiality. The results of review are classified on the basis of type of approach and the type of validation used to validate the approach.

SaaS application is becoming more and more popular with the development of the cloud computing. In order to use the cloud service, the tenants should upload their data to the databases of cloud service provider, so how to protect the tenants’ privacy information from snooping or leaking by DBA while keeping a good application performance is a big challenge. Therefore, we address this challenge by proposing a novel cloud data fragmentation cluster-based privacy preserving mechanism in this paper, the mechanism could give an optimal privacy preserving strategy by clustering relevancy matrix using Bond Energy Algorithm and partitioning the clustered matrix according to the privacy constraints proposed by the tenants.

Information technology plays vital role to enhance our knowledge and improve social life. Information presentation is as important as information itself, and interaction with these information enable one to understand these information quickly and easily. In this article, the information is explore up to one level granularity by introducing single level drill down interactive technique for descriptive data mining tasks results in order to convey inside of the data quickly, easily and effectively. The experimentation being done on Amazon dataset and two information visualization techniques i.e. column charts and bar charts. The interactive technique is comprehensively analyzing in both visualization techniques with respect to the visualization features. The drill down approach in column chart shows better performance comparatively.

Improving the fault tolerance ability of a cluster system is an important technology. Using a checkpoint in a multi-machine system is a hot topic in China and abroad. This study introduces common checkpoint technologies and algorithms, as well as presents a common improvement strategy and a comparative analysis.

Recently, OSGi has been used in many areas of smart phones, software applications, and home network. However, it cannot be used for enterprise distributed systems because it does not have auto-managing schema for them and does not provide a backup strategy. A service location protocol which is a dynamic configurations protocol can be used to auto-manage the distributed systems, but the protocol cannot ensure the stability of distributed systems. In this paper, we present a technique of automated service discovery in distributed systems based on OSGi. The proposed technique defines four components and four type profiles to achieve automated service discovery and backup functions. By using the technique, OSGi could be widely used for developing enterprise distributed systems.

In virtualized environments, physical resources are abstracted as resource pool for provisioning, services consolidation, and service on demand. Traditional virtual machines are often over-provisioned to provide peak performance guarantees and thus waste a lot of memory resources. In this paper we propose a novel Initiatively Share Based Memory Overcommitting scheme, namely, IMR, to improve the memory utilization further. In IMR, guest virtual machine kernels are hacked with initiatively share functionality such that the guests can cooperatively share unused memory with the hypervisor, and consequently some of the possible page swapping and merging in such virtual machines are eliminated. The experimental results in shadow page tables and extended page tables scenarios show that our IMR approach not only improves the memory utilization but also has microsecond-level time overheads for shared memory reclaim, which outperforms the memory optimization schemes such as millisecond-level KSM (Kernel Same-page Merging) in best cases and millisecond-level page swapping at average.

Massive MIMO can boost the capacity and increase the coverage, however the pilot overhead of its channel estimation will linearly increase with the antenna increasing. In order to reduce pilot overhead and improve the quality of channel estimation, a multi-dimension Wiener filtering channel estimation algorithm was put forward. First we analyzed Massive MIMO system model and channel model in which Base station configured a two-dimension antenna array; then accomplished channel estimation applying the correlation function of time, frequency, the row and column of the antenna array, and presented a simple closed-form solution of the space-time-frequency correlation function to reduce the complexity of the algorithm. The proposed algorithm extends one-dimension space filtering to two-dimension, so doesn’t need to transmit pilots in every raw of the two-dimension antenna array contrast with 3D-Wiener and can reduce beyond 50% pilot overhead. Based on the simulation results, this algorithm can achieve 8dB performance gain over 2D-Winner and 3dB over 3D-Wiener with same pilot overhead and can acquires the optimal throughput with considering both the channel estimation quality and pilot overhead.

Computational Grid is a high performance computing environment that participating machines resources are used through software layer as transparent and reliable. Task assignment problem in Grid Computing is a NP-Complete problem that has been studied by several researchers. The most common objective functions of task scheduling problems are Makespan and Flowtime. This paper gives a classification of meta-heuristic scheduling algorithms in distributed computing that are applicable to grid environment and addresses scheduling problem of independent tasks on Computational Grids. A Hybrid Discrete Particle Swarm Optimization and Min-min algorithm (HDPSO) is presented to reduce overall Completion Time of task.

In order to remove redundant data and resolve conflicts in point clouds, we proposed fuzzy clustering reduction strategy in this paper. Original point clouds are decreased before computing other pretreatments. The proposed method involves three processes: reduction of the original data using fuzzy clustering while the point clouds are divided into sub-domains using octree structure, generation of the sub-surface that is fitted the sub-surface by implicit function in each sub-domain, the normal alignment that are computed normal of sub-surface and inference the global normal of surface using iteratively propagate algorithm. The method is suitable to reduce mass point clouds to reconstruct surface that can keep the property of surface. The experimental results show that the model with less sharp feature is more effective than complex model to reduce point clouds by fuzzy clustering.

Now day’s transaction failure is a common issue in mobile environment. There are various cause of transaction failure in mobile environment, some of them most common are failure of coordinator (normally which is base station in case of mobile environment), disconnection of mobile device, low battery, handoff. This paper proposes the new transaction commit protocol, Fault Tolerant Transaction Commit Protocol with Timeout Constraint (FTCOT).It support coordinator failure, handoff (in case of mobility) which reduce transaction failure. This paper extends the feature of TCOT.

With the development of cloud computing, more and more service providers deploy multi-tenant applications to the cloud. Multi-tenant data is stored by non-fully trusted SaaS service providers, and the protection of data privacy attracts more attention. This paper proposes a privacy protection strategy customization framework. This framework considers the privacy protection needs, SaaS application performance, the interests of both tenants and SaaS service providers, and analyzes the whole privacy protection strategy formulation process based on the Nash equilibrium, then establishes the game model of privacy protection, finally obtains the privacy protection strategy by analyzing of the game model. The experiments show that the privacy protection game model has better feasibility and effectiveness.

Distributed computing accomplished broad appropriation because of consequently parallelizing and transparently executing tasks in distributed environments. Straggling tasks is an essential test confronted by all Big Data Processing Frameworks for example MapReduce, Dryad, and Spark. Stragglers are the assignments that run much slower than different tasks and since a job completes just when it’s last undertaking completions, stragglers postponement work fruition. Stragglers extraordinarily impact little occupations such that employments comprising of a couple of undertakings. Such occupations are fundamentally deferred regardless of the fact that a solitary undertaking is moderate .This paper survey stragglers recognition and rescheduling systems proposed so far and brings up their strengths and shortcomings. This paper additionally displays wise attributes and impediments of the existing state- of-the- craftsmanship calculations to take care of the issue of stragglers relief.

Adopting focused crawler to search web sites is the trend of next generation search engines. Design and implementation of a focused crawler - TargetCrawler is introduced in detail, including its overall architecture, main modules, working processes and two key algorithms, duplicate removing algorithm based on the Bloom filter and ranking algorithm based on priority which are designed to ensure accuracy and efficiency of web search. Experimental results show the effectiveness of the scheme.

Using SAPF (shunt active power filter) has been proved as an effective way for harmonic compensation. In practical applications, the performance of SAPF will be impacted by inter-harmonics and non-periodic disturbances. This paper analyzed the CPT (conservative power theory) definition of power theory and the application method for SAPF. Repetitive controller and PI controller were used as a combination way for the harmonic and inter-harmonic compensation. By the EID (equivalent input-disturbance) controller, the performance for non-periodic interference suppression of SAPF can be improved. By simulation with MATLAB, the models of SAPF system, repetitive controller and EID controller were built. Through the computer simulation method, we can verify the designed system performance.

Cloud storage is the development direction of data storage nowadays, and MooseFS provides a good solution for cloud storage. But as a kind of typical distributed file system, the problem of load balancing among chunk servers affects the use of MooseFS. Though MooseFS has provided certain load balancing capability, but it takes into account only the consumed space, and which causes the chunk servers with larger space were overburdened. In this study, we analyzed the load balancing algorithm among chunk servers in MooseFS, and proposed an improved load balancing algorithm. Through the experiment and comparative analysis, the improved algorithm enhances the load balancing performance of MooseFS obviously.

It is difficult to deeply develop computing ability of supercomputer through programming. There are two approaches to resolve this problem. The first is that programmer masters advanced knowledge about architecture of the supercomputer. The second is to construct a friendly programming environment to ease the difficulties in parallel programming. Julia is a scripting language which supports language-level high performance computing. It is easier to implement parallel algorithm in Julia language. So, we develop a programming supporting environment for Julia to edit and debug source code, and prepare a set of portable function library for heterogeneous supercomputers. These programs are sent to supercomputers through a message system. As job description, these Julia codes are scheduled to proper nodes and executed based on the portable function library. In the computing case of bus-line statistics, the parallel Julia program on 4 nodes achieved a speed up of 3.15x.