Research

Traditional relational databases cannot provide the scalability requirement of cloud computing. That is the cause to the movement of NoSQL data storage in distributed computing environment. However, NoSQL databases cannot fully support transaction oriented applications. The use of NoSQL databases raises the challenge to handle the application data that is perfectly relational as these databases are almost schema-less and does not support well for transactional operations and join operations. Therefore, there is a challenge to handle SQL and NoSQL data in a single application without knowing the user where and which type of database the needed data resides. This paper proposes a framework for Hybrid Query Processing System that can handle both SQL and NoSQL data by using data integration and data virtualization technology in retrieving both types of data. In HQPS, Resource Description Framework (RDF) is used for data integration from heterogeneous databases. Mapping between relational and RDF data is also proposed and implementation of relational to RDF mapping is carried out as a part of HQPS implementation.

Hadoop configuration optimization is very

challenging because of the complexity of its framework. And

optimized Hadoop parameter configuration settings depend

significantly on the performance of MapReduce applications in

the cluster. Although much research has been conducted on

Hadoop parameters configuration optimization, configuring its

resource setting parameters to minimize the execution time of

MapReduce jobs in clusters still needs a lot of continuing

researches. Further, determining the type of machine instances

that should be used to minimize the resource usage cost for

executing applications in clusters is also difficult. This paper

addresses these problems by optimizing the instance resource

usage and execution time of MapReduce tasks using a multi-
objective steady-state Non-dominated Sorting Genetic

Algorithm II (ssNSGA-II) approach. In this approach, the

instance resource usage cost of MapReduce tasks is calculated

based on the cost of machine instance types and the number of

machine instances in the Hadoop cluster. The optimized

configuration is identified by selecting an optimal setting that

satisfies two objective functions associated with instance

resource usage and execution time minimization, from Pareto

optimal front solutions. Although dynamic machine instance

type is considered within the search process in our system,

dynamic cluster size is out of consideration and intended to be

carried out in our future. Experiments conducting using

workloads from the HiBench benchmark on a high

specification 6-node Hadoop cluster verify the efficacy of our

proposed approach.

In this study, we conducted level wise workflow makespan

optimization and virtual machine deployment cost

minimization for multi-objective workflow optimization in

the cloud. Further, during workflow execution, to ensure load

balancing among different virtual machine instances at each

workflow level, balanced task clustering was also carried out.

Optimization was conducted using the popular non-
dominated sorting genetic algorithm II (NSGA-II), with only

homogeneous machine instances being considered.

Experimental results obtained show Pareto front solutions for

our multi-objective optimization on makespan time and

virtual machine deployment cost for several scientific

workflow applications and verify the efficiency of our system.

In this study, we implemented three steady-state versions of NSGA-III that differ by the manner in which the offspring combined with the parent population is selected. These three schemes were then evaluated on the standard problem sets DTLZ1-4 in terms of four popular criteria: inverse generational distance (IGD), hypervolume (HV), convergence, and diversity. The results obtained suggest that utilizing a selection scheme in which the offspring is selected from the first non-dominated rank results in better solutions than other steady-state offspring selection schemes.

Over the past decade, cloud computing has grown in popularity for the processing of scientific applications as a result of the scalability of the cloud and the ready availability of on-demand computing and storage resources. It is also a cost-effective alternative for scientific workflow executions with a pay-per-use paradigm. However, providing services with optimal performance at the lowest financial resource deployment cost is still challenging. Several fine-grained tasks are included in scientific workflow applications, and efficient execution of these tasks according to their processing dependency to minimize the overall makespan during workflow execution is an important research area. In this paper, a system for level-wise workflow makespan optimization and virtual machine deployment cost minimization for overall workflow optimization in cloud infrastructure is proposed. Further, balanced task clustering, to ensure load balancing in different virtual machine instances at each workflow level during workflow execution, is also considered. The system retrieves the necessary workflow information from a directed acyclic graph and uses the non-dominated sorting genetic algorithm II (NSGA-II) to carry out multiobjective optimization. Pareto front solutions obtained for makespan time and instance resource deployment cost for several scientific workflow applications verify the efficacy of our system.

Hadoop configuration optimization is very challenging because of the complexity of its framework. And optimized Hadoop parameter configuration settings depend significantly on the performance of MapReduce applications in the cluster. Although much research has been conducted on Hadoop parameters configuration optimization, configuring its resource setting parameters to minimize the execution time of MapReduce jobs in clusters still needs a lot of continuing researches. Further, determining the type of machine instances that should be used to minimize the resource usage cost for executing applications in clusters is also difficult. This paper addresses these problems by optimizing the instance resource usage and execution time of MapReduce tasks using a multi-objective steady-state Non-dominated Sorting Genetic Algorithm II (ssNSGA-II) approach. In this approach, the instance resource usage cost of MapReduce tasks is calculated based on the cost of machine instance types and the numb...

Today, cloud computing has become important research area and more enterprises are adopting the Cloud based strategy for their businesses. In this case, user access control is the primary concern for cloud users and cloud service providers. User accesses are key factor in determining how much they have to pay to the service provider (SP). So, SP needs to deploy secure access control mechanism in provisioning the services to the users. In cloud computing, services are delivered as web services using Simple Object Access Protocol (SOAP) message format. And to protect service provisioning to unauthorized users, many security access control mechanisms have been proposed. This paper intends to examine how Attribute Based Encryption mechanism used to control users' accesses among cluster based private cloud and data center private cloud in our university campus. By using this mechanism, service providers can ensure that secure services are delivered only to the authorized users.

In this study, we implemented three steady-state versions of NSGA-III that differ by the manner in which the offspring combined with the parent population is selected. These three schemes were then evaluated on the standard problem sets DTLZ1–4 in terms of four popular criteria: inverse generational distance (IGD), hypervolume (HV), convergence, and diversity. The results obtained suggest that utilizing a selection scheme in which the offspring is selected from the first non-dominated rank results in better solutions than other steady-state offspring selection schemes.

Over the past decade, cloud computing has grown in popularity for the processing of scientific applications as a result of the scalability of the cloud and the ready availability of on-demand computing and storage resources. It is also a cost-effective alternative for scientific workflow executions with a pay-per-use paradigm. However, providing services with optimal performance at the lowest financial resource deployment cost is still challenging. Several fine-grained tasks are included in scientific workflow applications, and efficient execution of these tasks according to their processing dependency to minimize the overall makespan during workflow execution is an important research area. In this paper, a system for level-wise workflow makespan optimization and virtual machine deployment cost minimization for overall workflow optimization in cloud infrastructure is proposed. Further, balanced task clustering, to ensure load balancing in different virtual machine instances at each workflow level during workflow execution, is also considered. The system retrieves the necessary workflow information from a directed acyclic graph and uses the non-dominated sorting genetic algorithm II (NSGA-II) to carry out multiobjective optimization. Pareto front solutions obtained for makespan time and instance resource deployment cost for several scientific workflow applications verify the efficacy of our system.