Zhengquan Xu

Prefetching scheme for massive spatiotemporal data in a smart city

Employing user access patterns to develop a prefetching scheme can effectively improve system I/O performance and reduce user access latency. For massive spatiotemporal data, traditional pattern mining methods fail to directly reflect the spatiotemporal correlation and transition rules of user access, resulting in poor prefetching performance. This paper proposed a prefetching scheme based on spatial-temporal attribute prediction, named STAP. It maps the history of user access requests to the spatiotemporal attribute domain by analyzing the characteristics of spatiotemporal data in a smart city. According to the spatial locality and time stationarity of user access, correlation analysis is performed and variation rules are identified for the history of user access requests. Further, the STAP scheme mines the user access patterns and constructs a predictive function to predict the users next access request. Experimental results show that the prefetching scheme is simple yet effective; it achieves a prediction accuracy of 84.3% for access requests and reduces the average data access response time by 44.71% compared with the nonprefetching scheme.

DCCP: an effective data placement strategy for data-intensive computations in distributed cloud computing systems

Cloud computing systems provide high-performance computing resources and distributed storage space to deal with data-intensive computations. Data scheduling between data centers is becoming indispensable for the cloud computing systems in which a mass of large datasets is stored at different data centers and inter-center data accesses are needed in data analytics. However, the performance of data scheduling is highly dependent upon the rationality of data placement. Data placement is a key optimization method for reducing data scheduling between data centers and realizing statistical I/O load balancing, accordingly reducing the mean computation execution time. This paper proposes a data placement strategy, DCCP, which is developed based on dynamic computation correlation. DCCP places the datasets with high dynamic computation correlations at the same data center considering the I/O load and the capacity load of data centers; when computations are scheduled for this data center, most of the datasets they process are stored locally, and thus the mean computation execution time can be reduced. Evidence from a large number of experiments proves that the DCCP can achieve the statistical I/O load balancing and the capacity load balancing of data centers, thus reducing the total data scheduling between data centers as much as possible at a very low time complexity, even as the numbers of datasets and data centers increase.

An Effective Strategy for Improving Small File Problem in Distributed File System

Distributed file systems, such as HDFS, DFS, etc, are adopted to support cloud storage and are designed for optimizing large files access. But unfortunately, the problem of massive small files is neglected and seriously restricts the performance of distributed file systems. To improve and even solve the small file problem, in this paper, user access task is defined. The correlations among the access tasks, applications and access files are constructed by the improved PLSA, and the research object is transferred from file-level to task-level. Then, an effective strategy is proposed to improving small file problem in distributed file system. The strategy merges small files in term of access tasks and selects perfecting targets based on the transition probability of the tasks. Finally, the system efficiency analysis model is established and experimental results, compared with original HDFS, HAR and the schemes of Dong, demonstrate that the proposed strategy effectively reduce the MDS workload and the request response delay.

Trusted Service Application Framework on Mobile Network

With the development of information technology and secure applications in key departments (such as national security department, medical establishment), existing mobile network was not dependable enough for service-oriented applications. Facing to the secure requirements in mobile network, a new trusted service application framework was proposed, which included applications analysis, network services, security protocols, error detection and fault tolerance. Combined with natural attribute of trust, trust evaluation model was built. It enhanced reliability and security of mobile network applications. Our experimental results showed this framework not only had advantages but also had a good reference value.

Dynamic replication to reduce access latency based on fuzzy logic system

The model of access latency optimization rectifies the lack of theoretical analysis on the replications and the data access latency reduction.FLSDR always selects the optimal replica and places replicas onto the optimal node.FLSDR uses a fuzzy logic system to realize the accurate and prudent replica replacement. Display Omitted In a distributed environment, limited available bandwidth resources lead a high data access latency. Replication is a popular method that can upgrade the access performance and increase the data availability. However, unreasonable replication would cause over-consumption of system resources and finally a further deterioration on data access latency. So, In this paper, a theoretical model of access latency optimization with replication is presented firstly, which complement the blank space, and then a well-designed dynamic replication strategy is proposed, which consists of three algorithms: replica selection algorithm, replica layout algorithm and replica replacement algorithm. Replica selection algorithm selects the optimal replica with a hierarchical time cost based on the derivation of the theoretical model. Replica layout algorithm selects the optimal node for placing the replica based on the spatio-temporal locality of data access. Replica replacement algorithm, in which the fuzzy logic system is introduced originally, deletes replica when the available storage space is insufficient. FLSDR is tested by OptorSim and experimental results show that FLSDR achieves better performance in comparison with other algorithms in terms of mean job execution time, computing resource usage, number of data scheduling between clusters and number of replicas.

A Data Placement Strategy for Big Data Based on DCC in Cloud Computing Systems

In complex and data-intensive applications, data scheduling between data centers must occur when multiple datasets stored in distributed data centers are processed by one computation. To store massive datasets effectively and reduce data scheduling between data centers during the execution of computations, a mathematical model of data scheduling between data centers in cloud computing is built and dynamic computation correlation (DCC) between datasets is defined. Then a data placement strategy for big data based on DCC is proposed. Datasets with high DCC are placed into the same data center, and new datasets are dynamically distributed into the most appropriate data center. Comprehensive experiments show that the proposed strategy can effectively reduce the number of data scheduling between data centers and has a considerably low and almost constant computational complexity when the number of data centers increases and the datasets are massive. It can be expected that the proposed strategy will be applicable to the practical large-scale distributed storage systems for big data management.

Conducting Correlated Laplace Mechanism for Differential Privacy

Recently, differential privacy achieves good trade-offs between data publishing and sensitive information hiding. But in data publishing for correlated data, the independent Laplace noise implemented in current differential privacy preserving methods can be detected and sanitized, reducing privacy level. In prior work, we have proposed a correlated Laplace mechanism (CLM) to remedy this problem. But the concrete steps and detailed parameters to imply CLM and the complete proof has not been discussed. In this paper, we provide the complete proof and specific steps to conduct CLM. Also, we have verified the error of our implement method. Experimental results show that our method can retain small error to generate correlated Laplace noise for large quantities of queries.

Cluster-Indistinguishability: A practical differential privacy mechanism for trajectory clustering

An important method of spatial-temporal data mining, trajectory clustering can mine valuable information in trajectories. However, cluster results without special sanitization pose serious threats to individual location privacy. Existing privacy preserving mechanisms for trajectory clustering still contend with the problems of narrow applicability, low-level utility, and difficulty in being applied to real scenarios. In this paper, we therefore propose a differential privacy preserving mechanism, Cluster-Indistinguishability, to support trajectory clustering. Firstly, a general model of typical trajectory clustering algorithms is given, and the definition of differential privacy is introduced according to the model. Then, we derive the probability density function of two-dimensional Laplace noise, which satisfies the above definition. Finally, we transform the noise from a Cartesian coordinate system to a Polar coordinate system to efficiently apply it in real scenarios. Experimental results show that Cluster-Indistinguishability has general applicability and better performance compared to existing methods.

Influence of data errors on differential privacy

The rapid development of data sharing applications brings a serious problem of privacy disclosure. As an effective privacy-preserving method, the differential privacy, which strictly defines the privacy-preserving degree and data utility mathematically, can balance the privacy and data utility. However, the differential privacy has a hypothesis premise that the raw data are accurate without any error, so it could not limit the privacy security and the data utility to the expected range when processing data with errors. Hence, this paper focuses on the study on the influence of data errors on differential privacy. Taking the random error as an example, we analyze the influence mode and mechanism of data errors on differential privacy, especially on the privacy budget