Gaochao Xu

Scheduling Algorithm with Potential Behaviors

Scheduling algorithm for batch-mode data-intensive jobs is a key issue in data-intensive Grid applications. It focuses on how to minimize the overhead of transferring the required data set to the executing grid site. Existing approaches pay attention to the access cost of a data-intensive job at each executing grid site for replicating the required data set. However, they neglect the influence from potential behaviors of jobs in the waiting queue at each grid site when the access cost is evaluated. In this paper, we consider the influence of potential behaviors on the access cost, and propose a data-intensive job scheduling algorithm with potential behaviors. Furthermore, the causation of potential behaviors is analyzed. The simulation result in OptorSim shows that it has better performance in mean job time of all jobs, total number of replications, total number of local files accesses and effective network usage than the scheduling algorithm based on access cost.

A Teaching Model Based on Schema Theory in Data Mining Curriculum

Mining hidden valuable knowledge from financial data is more and more important to students in universities of finance and economics. However, data mining curriculum learning is difficult for them because of the lack of computer special skills. This paper proposes a teaching model based on schema theory to teach data mining curriculum. It introduces characteristics of data mining curriculum, and then it depicts data mining teaching model from teaching and practice perspectives based on schema theory. Teaching experiment shows that there is a significant difference in final exam and practice exam between the proposed model and a regular teaching model.

An Enhanced Data-aware Scheduling Algorithm for Batch-mode Dataintensive Jobs on Data Grid

This paper aims to propose an enhanced data-aware scheduling algorithm for batch-mode data-intensive job on Gfarm data grid by using LSF plug-in mechanism. The batch-mode data-intensive job is categorized into two types. These two types of batch-mode jobs are analyzed in details and implemented by our scheduling algorithm. Finally, an example is given to evaluate this algorithm and some conclusions have been drawn by analysis

LMCM: Layered Multiple Chaining Model for Authenticating Multicast Streams

Multicast authentication is a vital component in secure group communications, but authenticating real-time multicast streams over lossy channels or unreliable networks is very difficult due to the packet losses, expensive overheads and high delays. So this paper introduces a novel approach to multicast authentication based on LMCM (Layered Multiple Chaining Model). By the theoretical analyses, it is robust enough against packet losses, has low delays on the senderpsilas side and the receiverpsilas side. Both computation and communication overheads are in the reasonable scopes if its parameter values are determined systematically. And the high authentication probability can be achieved by increasing the number of packets that contain the hash of a previous packet and the number of hashes that are appended to the signature packets. Hence LMCM is secure, efficient and practical to more multicast applications than many previously proposed approaches.

Survey on multicast data origin authentication

Multicast is an efficient and natural way of communicating information via Internet, but its security is identified as one of the most important problems to solve for the successful deployment of group communication applications. First of all, in secure multicast group members must be able to verify that the data received is indeed sent by an authorized sender, and this is called dasiadata origin authenticationpsila. This paper introduces the main schemes for authenticating multicast data origin, and evaluates their performances with computation overhead, communication overhead and some other parameters. The result shows there are no ideal solutions to satisfy all multicast applications.

A Positive Preprocessing Framework for Mapping Traditional Replica Selection Algorithms

Replica selection algorithms in data grid have been proposed to improve the processing capability of data intensive jobs. However, the processing time of these algorithms is increased rapidly with the increase of grid sites and replicas in data grid. To solve this problem, a positive preprocessing framework for mapping traditional replica selection algorithms based on OLAP, named as OLAP4RS, is proposed. Its architecture, processing procedure, and mapping mechanism are discussed.

Application of Schema Theory to Data Communications Teaching of E-Commerce Major

Data Communications is a core course for ECommerce majors. The major workflows in E-Commerce are implemented based on Data Communications technology. However, it is hard for E-Commerce major students to master data communications technology. To solve this issue, teaching environment and schema theory are discussed in summary firstly, a teaching model based on schema theory is proposed secondly, and teaching experiment design is performed to determine the teaching effect which turned out to be good finally.

3rd Party E-business Architechure and Model in Grid Computing Environment

More and more E-business services of enterprises are performed by the 3rd party E-business platform, which leads to bad system performance. To solve the performance issue, an E-business architecture based on grid computing is proposed. The major architecture is depicted and discussed in detail, and some features of our proposed architecture are outlined. To verify the feasibility of E-business application in grid environment, an E-business model is proposed and discussed.