Dr. Fawzy Torkey - Academia.edu (original) (raw)
Uploads
Papers by Dr. Fawzy Torkey
IJCI. International Journal of Computers and Information, 2015
Cloud computing services are becoming ubiquitous, and are becoming the primary source of computin... more Cloud computing services are becoming ubiquitous, and are becoming the primary source of computing power for both enterprises and personal computing applications. One of the fundamental issues in this environment is related to task scheduling. The scheduler should do the scheduling process efficiently in order to utilize the available resources. In this paper a cloud task scheduling policy based on artificial bee colony algorithm compared with different scheduling algorithms has been proposed. The main goal of the proposed algorithm is minimizing the makespan of a given tasks set. Artificial bee colony algorithm models the behavior of honey bees and can be used to find solutions for difficult or impossible combinatorial problems. Algorithms have been simulated using Cloudsim toolkit package. Experimental results showed that the artificial bee colony algorithm outperformed ACO, FPLTF and FCFS algorithms. Keywords-cloud computing; task scheduling; makespan; artificial bee colony I. INTRODUCTION Cloud computing platform can provide a variety of resources, including infrastructure, software, and services, to users in an on-demand fashion. Cloud computing services eliminate the costs of purchasing and maintaining the infrastructures for cloud users, and allow the users to dynamically scale up and down computing resources in real time based on their needs [1]. To access these resources, a cloud user submits requests for resources. The cloud provider then provides the requested resources from a common resource pool, and allows the user to use these resources for a required time period. The customer is interested in reducing the overall execution time of tasks on the machines [2]. The processing units in cloud environments are called as virtual machines (VMs). The VMs should execute the tasks as early as possible and these VMs run in parallel. Because hundreds of thousands of VMs are used, it is difficult to manually assign tasks to computing resources in clouds [3]. So, efficient algorithms are needed for task scheduling in the cloud environment. A good task scheduler should adapt its scheduling strategy to the changing environment and the types of tasks [4]. Therefore, dynamic task scheduling algorithms that are based on metaheuristics, such as Artificial Bee Colony (ABC), ant colony optimization (ACO) and Particle Swarm Optimization (PSO) are preferred for clouds. ABC algorithm simulates the foraging behavior of honey bees [5]. It shows good performance in many application problems and large scale optimization problems. ABC algorithm has been applied to various problems including training of neural networks, Traveling Salesman Problem (TSP), clustering and image segmentation [6]. In this paper, we use ABC algorithm to find the near-optimal resource allocation for tasks in the dynamic cloud system to minimize the makespan of tasks on the entire system. Then, this scheduling strategy was simulated using the Cloudsim toolkit package. Experimental results compared to Ant Colony Optimization (ACO) in [7], Fastest Processor to Largest Task First (FPLTF) in [8] and First Come First Served (FCFS) in [9] showed that ABC algorithm satisfies expectation. The remainder of this paper is organized as follows. Section 2 introduces background and scans the some of the important related work. Section 3 covers the basics of honey bee Colonies and the details of cloud scheduling based ABC algorithm. The implementation and simulation results are seen in section 4. Finally, Section 5 concludes this paper. II. BACKGROUND & RELATED WORK A. Cloud Computing Environment and Combinatorial Optimization Problem Cloud computing is a virtual pool of resources which are provided to users. It gives users virtually unlimited pay-per-use computing resources without the burden of managing the underlying infrastructure. The goal of cloud computing service providers is to use the resources efficiently and gain maximum profit [10]. This leads to task scheduling as a core and challenging issue in cloud computing. Scheduling of tasks in cloud computing is a combinatorial optimization problems. In combinatorial optimization problems, we are looking for an object from a finite or possibly infinite set. This object is typically an integer number, a subset, a permutation, or a graph structure [11]. Due to the practical importance of combinatorial optimization problems, many algorithms to tackle them have been developed. These algorithms can be classified as either complete or approximate algorithms. Complete algorithms are guaranteed to find for every finite size instance of a combinatorial optimization problem an optimal solution in bounded time. In approximate methods we sacrifice the guarantee of finding optimal solutions for the sake of getting good solutions in a significantly reduced amount of time especially for combinatorial optimization problems
2007 ITI 5th International Conference on Information and Communications Technology, 2007
Abstract As Web sites becoming a fundamental component of businesses, quality of service will be... more Abstract As Web sites becoming a fundamental component of businesses, quality of service will be one of the top management concerns. Users, normally, does not care about site failures, traffic jams, network bandwidth [1], or other indicators of system failures. To an ...
2013 8th International Conference on Computer Engineering & Systems (ICCES), 2013
Cloud computing is the development of distributed computing, parallel computing and grid computin... more Cloud computing is the development of distributed computing, parallel computing and grid computing, or defined as the commercial implementation of these computer science concepts. One of the fundamental issues in this environment is related to task scheduling. Cloud task scheduling is an NP-hard optimization problem and many meta-heuristic algorithms have been proposed to solve it. A good task scheduler should adapt its scheduling strategy to the changing environment and the types of tasks. In this paper, a cloud task scheduling policy based on Ant Colony Optimization (ACO) algorithm compared with different scheduling algorithms First Come First Served (FCFS) and Round-Robin (RR), has been presented. The main goal of these algorithms is minimizing the makespan of a given tasks set. ACO is random optimization search approach that will be used for allocating the incoming jobs to the virtual machines. Algorithms have been simulated using cloudsim toolkit package. Experimental results showed that cloud task scheduling based on ACO outperformed FCFS and RR algorithms.
IJCI. International Journal of Computers and Information, 2015
Cloud computing services are becoming ubiquitous, and are becoming the primary source of computin... more Cloud computing services are becoming ubiquitous, and are becoming the primary source of computing power for both enterprises and personal computing applications. One of the fundamental issues in this environment is related to task scheduling. The scheduler should do the scheduling process efficiently in order to utilize the available resources. In this paper a cloud task scheduling policy based on artificial bee colony algorithm compared with different scheduling algorithms has been proposed. The main goal of the proposed algorithm is minimizing the makespan of a given tasks set. Artificial bee colony algorithm models the behavior of honey bees and can be used to find solutions for difficult or impossible combinatorial problems. Algorithms have been simulated using Cloudsim toolkit package. Experimental results showed that the artificial bee colony algorithm outperformed ACO, FPLTF and FCFS algorithms. Keywords-cloud computing; task scheduling; makespan; artificial bee colony I. INTRODUCTION Cloud computing platform can provide a variety of resources, including infrastructure, software, and services, to users in an on-demand fashion. Cloud computing services eliminate the costs of purchasing and maintaining the infrastructures for cloud users, and allow the users to dynamically scale up and down computing resources in real time based on their needs [1]. To access these resources, a cloud user submits requests for resources. The cloud provider then provides the requested resources from a common resource pool, and allows the user to use these resources for a required time period. The customer is interested in reducing the overall execution time of tasks on the machines [2]. The processing units in cloud environments are called as virtual machines (VMs). The VMs should execute the tasks as early as possible and these VMs run in parallel. Because hundreds of thousands of VMs are used, it is difficult to manually assign tasks to computing resources in clouds [3]. So, efficient algorithms are needed for task scheduling in the cloud environment. A good task scheduler should adapt its scheduling strategy to the changing environment and the types of tasks [4]. Therefore, dynamic task scheduling algorithms that are based on metaheuristics, such as Artificial Bee Colony (ABC), ant colony optimization (ACO) and Particle Swarm Optimization (PSO) are preferred for clouds. ABC algorithm simulates the foraging behavior of honey bees [5]. It shows good performance in many application problems and large scale optimization problems. ABC algorithm has been applied to various problems including training of neural networks, Traveling Salesman Problem (TSP), clustering and image segmentation [6]. In this paper, we use ABC algorithm to find the near-optimal resource allocation for tasks in the dynamic cloud system to minimize the makespan of tasks on the entire system. Then, this scheduling strategy was simulated using the Cloudsim toolkit package. Experimental results compared to Ant Colony Optimization (ACO) in [7], Fastest Processor to Largest Task First (FPLTF) in [8] and First Come First Served (FCFS) in [9] showed that ABC algorithm satisfies expectation. The remainder of this paper is organized as follows. Section 2 introduces background and scans the some of the important related work. Section 3 covers the basics of honey bee Colonies and the details of cloud scheduling based ABC algorithm. The implementation and simulation results are seen in section 4. Finally, Section 5 concludes this paper. II. BACKGROUND & RELATED WORK A. Cloud Computing Environment and Combinatorial Optimization Problem Cloud computing is a virtual pool of resources which are provided to users. It gives users virtually unlimited pay-per-use computing resources without the burden of managing the underlying infrastructure. The goal of cloud computing service providers is to use the resources efficiently and gain maximum profit [10]. This leads to task scheduling as a core and challenging issue in cloud computing. Scheduling of tasks in cloud computing is a combinatorial optimization problems. In combinatorial optimization problems, we are looking for an object from a finite or possibly infinite set. This object is typically an integer number, a subset, a permutation, or a graph structure [11]. Due to the practical importance of combinatorial optimization problems, many algorithms to tackle them have been developed. These algorithms can be classified as either complete or approximate algorithms. Complete algorithms are guaranteed to find for every finite size instance of a combinatorial optimization problem an optimal solution in bounded time. In approximate methods we sacrifice the guarantee of finding optimal solutions for the sake of getting good solutions in a significantly reduced amount of time especially for combinatorial optimization problems
2007 ITI 5th International Conference on Information and Communications Technology, 2007
Abstract As Web sites becoming a fundamental component of businesses, quality of service will be... more Abstract As Web sites becoming a fundamental component of businesses, quality of service will be one of the top management concerns. Users, normally, does not care about site failures, traffic jams, network bandwidth [1], or other indicators of system failures. To an ...
2013 8th International Conference on Computer Engineering & Systems (ICCES), 2013
Cloud computing is the development of distributed computing, parallel computing and grid computin... more Cloud computing is the development of distributed computing, parallel computing and grid computing, or defined as the commercial implementation of these computer science concepts. One of the fundamental issues in this environment is related to task scheduling. Cloud task scheduling is an NP-hard optimization problem and many meta-heuristic algorithms have been proposed to solve it. A good task scheduler should adapt its scheduling strategy to the changing environment and the types of tasks. In this paper, a cloud task scheduling policy based on Ant Colony Optimization (ACO) algorithm compared with different scheduling algorithms First Come First Served (FCFS) and Round-Robin (RR), has been presented. The main goal of these algorithms is minimizing the makespan of a given tasks set. ACO is random optimization search approach that will be used for allocating the incoming jobs to the virtual machines. Algorithms have been simulated using cloudsim toolkit package. Experimental results showed that cloud task scheduling based on ACO outperformed FCFS and RR algorithms.