Mohamed Othman

Adaptive Divisible Load Model for Scheduling Data-Intensive Grid Applications

In many data grid applications, data can be decomposed into multiple independent sub datasets and schedule for parallel execution and analysis. Divisible Load Theory (DLT) is a powerful tool for modelling data-intensive grid problems where both communication and computation load is partitionable. This paper presents an Adaptive DLT (ADLT) model for scheduling data-intensive grid applications. This model reduces the expected processing time approximately 80% for communication intensive applications and 60% for computation intensive applications compared to the previous DLT model. Experimental results show that this model can balance the loads efficiently.

An integrated approach for scheduling divisible load on large scale data grids

In many data grid applications, data can be decomposed into multiple independent sub datasets and distributed for parallel execution and analysis. This property has been successfully exploited for scheduling divisible load on large scale data grids by Genetic Algorithm (GA). However, the main disadvantages of this approach are its large choromosome length and execution time required. In this paper, we concentrated on developing an Adaptive GA (AGA) approach by improving the choromosome representation and the initial population. A new chromosome representation scheme that reduces the chromosome length is proposed. The main idea of AGA approach is to integrate an Adaptive Divisible Load Theory (ADLT) model in GA to generate a good initial population in a minimal time. Experimental results show that the proposed AGA approach obtains better performance than Standard GA (SGA) approach in both total completion time and execution time required.

Fast Discovery Of Long Patterns For Association Rules

The most time consuming process in discovering association rules is identifying the frequent patterns especially in the cases when the database contains long patterns. An algorithm called Flex for identifying frequent patterns especially efficient when the patterns are long is proposed by successive construction of the nodes lexicographic tree. The vertical counting strategy to facilitate fast discovery is used in support computation. The experimental result shows that Flex outperform Apriori, a well-known and widely used algorithm for patterns discovery.

Propositional satisfiability algorithm to find minimal reducts for data mining

A fundamental problem in data mining is whether the whole information available is always necessary to represent the information system (IS). Reduct is a rough set approach in data mining that determines the set of important attributes to represent the IS. The search for minimal reduct is based on the assumption that within the dataset in an IS, there are attributes that are more important than the rest. An algorithm in finding minimal reducts based on Propositional Satisfiability (SAT) algorithm is proposed. A branch and bound algorithm is presented to solve the proposed SAT problem. The experimental result shows that the proposed algorithm has significantly reduced the number of rules generated from the obtained reducts with high percentage of classification accuracy.

Decentralized replication strategies for P2P based Scientific Data Grid

Scientific Data Grid provides geographically distributed resources for large-scale data-intensive applications that generate large scientific data sets and it mostly deals with large computational problems. Research in the area of grid has given various ideas and solutions to address these requirements. However, since the number of participants (scientists and institutes) that involve in this kind of environment is increasing tremendously, scalability, availability and reliability have been the core problem for such system. Peer-to-peer (P2P) is one of the architecture that promising scale and dynamism environment. In this paper, we present a P2P model for Scientific Data Grid that utilizes the P2P services to address those problems. For the purpose of this study, we have developed and used our own data grid simulation written using PARSEC. In this paper, we illustrate our P2P Scientific Data Grid model, our data grid simulation and the design of proposed data replication strategies. We then analyze the performance of data discovery service with and without the existence of replication strategies relative to their success rates, response time, average number of hop and bandwidth consumption. The results from simulation study that show how the proposed replication strategies promote high data availability in the proposed Scientific Data Grid model and how these strategies improve the discovery process are presented.

Multi-class Bandwidth Reservation Scheme Based on Mobility Prediction for Handoff in Multimedia Wireless/Mobile Cellular Networks

Next generation of wireless cellular networks aim at supporting a diverse range of multimedia services to Mobile Terminal (MT) with guaranteed Quality of Service (QoS). The challenge is to maintain the playing continuity of multimedia streams during handoff. In this paper, a bandwidth reservation scheme based on mobility prediction is proposed, to enable high accurate prediction of next crossing cell (target cell) which a MT is going to, in order to avoid too early or over reservation resulting in a waste of resources. The amount of bandwidth to be reserved is dynamically adjusted according to (a) the current position (location) and the extrapolated direction of MT and; (b) the sector and zones of the cell. A Call Admission Control scheme (CAC) is also considered to further guarantee the QoS of real time traffic. The performance of the system is evaluated through discrete event simulation of the wireless cellular environment. Simulation results show that the proposed scheme as compared to several existing schemes is able to reduce the Handoff Call Dropping Probability (HCDP) of real time traffic and the number of terminated ongoing calls of non-real time traffic. In addition, it is efficient to reduce the number of cancelled reservation and subsequently increase the system bandwidth utilization.

Progress in various TCP variants (February 2009)

Transport Control Protocol (TCP), a basic communication language, consists of a set of rules that control communication. There are many versions of TCP which modified time to time as per need. Initially we discuss the basic functions of TCP and their role to control the congestion then graphically examine slow start, congestion avoidance, fast retransmission and fast recovery. This paper compares the performance of different TCP variants specifically Tahoe, Reno, New Reno, Westwood, Selective Acknowledgment (SACK), Forward Acknowledgement (FACK) and Vegas. TCP Vegas algorithm is explained with new structure mechanism and new congestion avoidance and modified slow start mechanisms. Subsequently, a table derived evaluates TCP variants on the basis of algorithm. We conversed the progress, and evaluated advantages and disadvantages of above TCP variants.

A Network Selection Algorithm Based on Enhanced Access Router Discovery in Heterogeneous Wireless Networks

The management process between different wireless technologies for mobile devices is very important to complete the handover operations. The handover operation needs to determine the delay and packet loss in order to be the quality of service within a certain level. Selecting the best available network at the appropriate time is very significant in the direction of realizing ubiquitous networks. In this paper a network selection approach named enhanced access router discovery (EARD) is proposed. The approach is developed to work in a heterogeneous environment including of WiMAX and WLAN networks. The EARD method utilizes the prioritized rating for multiple criteria (PRMC) proposed for selecting the target network. The proposed approach is evaluated with respect to various conditions with different traffic types. The simulation results show that our proposed approach outperform the traditional network selection methods is selecting the most appropriate network.

Reliability performance of shuffle exchange omega network

Multistage Interconnection Networks (MINs) are design to provide an effective communication in switching. In optical MIN, optical signal are routed through the connecting path by electronically controlled switching element using directional coupler. Shuffle-exchange networks (SENs) have been widely considered as practical interconnection systems due to their size of it switching elements (SEs) and uncomplicated configuration. In this paper, the relationship between reliability performance and number of network size are compared in shuffle exchange network (SEN), SEN with minus one stages (SEN-) and SEN with additional stage (SEN+). There are three parameters used to measure the reliability performance on these networks which is terminal reliability, broadcast reliability and network reliability. From the results the proposed SEN- have a better reliability performance compared to SEN and SEN+.

Towards a scalable Scientific Data Grid model and services

Scientific data grid mostly deals with large computational problems. It provides geographically distributed resources for large-scale data-intensive applications that generate large scientific data sets. This required the scientist in modern scientific computing communities involve in managing massive amounts of a very large data collections that geographically distributed. Research in the area of grid has given various ideas and solutions to address these requirements. However, nowadays the number of participants (scientists and institutes) that involve in this kind of environment is increasing tremendously. This situation has leads to a problem of scalability. In order to overcome this problem we need a data grid model that can scale well with the increasing of user. Peer-to-peer (P2P) is one of the architecture that promising scale and dynamism environment. In this paper, we present a P2P model for scientific data grid that utilizes the P2P services to address the scalability problem. By using this model, we study and propose various decentralized discovery strategies that intend to address the problem of scalability. We also investigate the impact of data replication that addressing the data distribution and reliability problem for our scientific data grid model on the propose discovery strategies. For the purpose of this study, we have developed and used our own data grid simulation written using PARSEC. In this paper, we illustrate our P2P scientific data grid model and our data grid simulation which is used in this study. We then analyze the performance of the discovery strategies with and without the existence of replication strategies relative to their success rates, bandwidth consumption and average number of hop.