Papers by Azizol Abdullah
—Sharing numerous computational and communication power from connected heterogeneous systems over... more —Sharing numerous computational and communication power from connected heterogeneous systems over the world are the two key points of Grid computing. Grid computing can also be referred as a computing platform for users to utilise the remote heterogeneous resources for solving their large scale jobs that require a huge amount of processing power or a huge data storage. Sharing these resources that way effectively requires a very good scheduling strategy, which is the focus of this research. This paper presents a new proposed grid based scheduling algorithm called Max-Average, inspired from Max-Min algorithm. In order to produce good quality solutions, the proposed algorithm is designed in two phases; firstly it uses an initial task queue like the traditional Max-Min for estimating task completion time for each of resources, and in the second phase choose the fitting resource for scheduling according to requirements. The results from our simulation showed that our proposed algorithm is performing better in producing good quality solutions, particularly in executing tasks fast and in balancing the load (resource utilisation) among the resources more effectively when compared to standard Minimum Execution Time (MET), Minimum Completion Time (MCT), Min-Min, and Max-Min heuristic approaches.
Most of the distributed systems such as a cloud environment have a nondeterministic structure, an... more Most of the distributed systems such as a cloud environment have a nondeterministic structure, and it would cause a serious problem to perform tasks with a time limit. Therefore, many prediction models and performance analyzes being used in the cloud to determine environment for users. Nevertheless, most of these models have a single objective for optimal resource absorption. Which means, they considered just one objective, such as a time limit and other issues are overlooked. In this paper, we proposed a novel model in Cloud to determine environment for the real-time workload. We applied a multi-objective model to absorb optimal resources under reasonable user cost and maximum user sharing. Performance evaluation on CloudSim proves that the new approach outperforms other existing, state-of-the-art methods.
The real-time system should guarantee that all critical timing constraints will be met in advance... more The real-time system should guarantee that all critical timing constraints will be met in advance. Many distributed systems such as a cloud environment have a nondeterministic structure and it would cause a serious problem for real time, but the user can access a large number of shared resources. Also launching a new resource in the IaaS layer of a Cloud is not instantaneous. Prediction model, risk management in PaaS and monitoring in IaaS are the most important parts that a real-time system should have because they must face a challenge in understanding the system and the behavior of workload completely. The results of analyzing, monitoring and prediction have serious impacts on system reaction. Understanding the workload is an important challenge in all systems and they use different models to identify the types or predict changes over the time. A prediction model must have the ability to produce and shape the pattern of workloads with low overhead. In this study, we propose an enhancement for profiling process with continues Markov chain to make hosts deterministic for users. The effectiveness and the accuracy of the proposed model measured in the evolution part. Also, the number of the failed tasks counted in this new model to show how proposed model is successful.
Http Dx Doi Org 10 1080 18756891 2009 9727670, Mar 12, 2012
International Review on Computers and Software, 2013
ABSTRACT Nowadays cloud computing is considered as the latest network infrastructure that support... more ABSTRACT Nowadays cloud computing is considered as the latest network infrastructure that supports large-scale decentralized computing. Its components rely on different design aspect of multiple mature networks structures (cluster commodity, utility computing, virtualization, Datacenters, and grid structure). The ultimate goal of cloud technology is to efficiently afford services to the users using the concept (Pay-for- Use) which implies cutting down the infrastructure costs when setting up a new business. It also makes the data that users need available and accessible in a way that does not require any kind of knowledge of the underlying infrastructure and meets the Service Level Agreement (SLA) requirements. One of the key problems in cloud computing is load balancing since it should ensure fair and dynamic distribution of loads among all computation nodes and harnesses the minimum power consumption. Load balancing facilitates resources utilization, sustains the minimum response time and guarantees data availability. This paper first, discusses and criticizes the strategies and policies of load balancing in cloud computing environment, then it compares them using different parameters such as throughput, availability, resources utilization, scalability etc. It also illustrates the multiple tools that have been used to implement and simulate these techniques under various experiments and environments. http://www.praiseworthyprize.org/jsm/index.php?journal=irecos&page=article&op=view&path[]=10300
Journal of Computer Science, 2014
Journal of Computer Science, 2014
Grid computing is a system that coordinates distributed resources using stan protocols and interf... more Grid computing is a system that coordinates distributed resources using stan protocols and interfaces to provide nontrivial quality of services emerging authorization framework that combined features of traditional access control, trust management and digital right management in one abstraction. Adoption of UCON improved the fine thorization policy. The major problem tion, the higher overhead will be impacted to the system. This is bec very complex policies to define rules accurately. the system needs to check rules by rules in each policy for each resource in order to produce the access r sult, resulting in lower authorization performance. ment like grid where user and resource keep increasing year by year. number of checking during authorization pro the number of rules checking by eliminating irrelevant set of rules. The irrelevant rules sets are d by the dependency of rules model proposed in this paper. The detail of our method i Our simulation result shows that our technique abl...
Proceedings Title: 2012 International Conference on Cyber Security, Cyber Warfare and Digital Forensic (CyberSec), 2012
ABSTRACT Nowadays cloud computing is considered as the latest network infrastructure that support... more ABSTRACT Nowadays cloud computing is considered as the latest network infrastructure that supports large-scale decentralized computing. Its components rely on different design aspect of multiple mature networks structures (cluster commodity, utility computing, virtualization, Datacenters, and grid structure). The ultimate goal of cloud technology is to efficiently afford services to the users using the concept (Pay-for- Use) which implies cutting down the infrastructure costs when setting up a new business. It also makes the data that users need available and accessible in a way that does not require any kind of knowledge of the underlying infrastructure and meets the Service Level Agreement (SLA) requirements. One of the key problems in cloud computing is load balancing since it should ensure fair and dynamic distribution of loads among all computation nodes and harnesses the minimum power consumption. Load balancing facilitates resources utilization, sustains the minimum response time and guarantees data availability. This paper first, discusses and criticizes the strategies and policies of load balancing in cloud computing environment, then it compares them using different parameters such as throughput, availability, resources utilization, scalability etc. It also illustrates the multiple tools that have been used to implement and simulate these techniques under various experiments and environments. http://www.praiseworthyprize.org/jsm/index.php?journal=irecos&page=article&op=view&path[]=10300
Lecture Notes in Computer Science, 2004
... Azizol Abdullah1, Mohamed Othman1, Md Nasir Sulaiman1, Hamidah Ibrahim1, and Abu Talib Othman... more ... Azizol Abdullah1, Mohamed Othman1, Md Nasir Sulaiman1, Hamidah Ibrahim1, and Abu Talib Othman2 ... Universiti Putra Malaysia 43400 Serdang, Selangor Malaysia {azizol, mothman,nasir, hamidah }@fsktm ... only concerned that the power is available to drive their appliances ...
Lecture Notes in Computer Science, 2013
Journal of Computer Science, 2014
Uploads
Papers by Azizol Abdullah