AN OPTIMIZED MAX-MIN SCHEDULING ALGORITHM IN CLOUD COMPUTING

—Cloudlet scheduling seems to be the most fundamental problem of cloud computing as per Infrastructure as a Service (IaaS). Proper scheduling in cloud lead to load balancing, minimization of makespan, and adequate resources utilization. To meet consumers' expectations, the execution of cloudlet simultaneously is required. Many algorithms have been implemented to solve the cloud scheduling problem. This include Min-Min which gave priority to cloudlet with minimum completion time. Min-Min scheduling algorithm has two clear weaknesses; a high value of makespan being generated and low resource utilization. To address these problems, this research proposes an Extended Min-Min Algorithm which assign cloudlet base on the differences between maximum and minimum execution time of cloudlets. Cloudsim was used to implement and compare the performances of the proposed algorithm with the benchmarks. The results of the extensive experiments show that the proposed algorithm is able to performed better in terms of makespan minimization in compare to the existing heuristics.

International Journal of Computer Applications, 2016

Cloud computing is a new archetype that provides dynamic computing services to cloud users through the support of datacenters that employs the services of datacenter brokers which discover resources and assign them Virtually. The focus of this research is to efficiently optimize resource allocation in the cloud by exploiting the Max-Min scheduling algorithm and enhancing it to increase efficiency in terms of completion time (makespan). This is key to enhancing the performance of cloud scheduling and narrowing the performance gap between cloud service providers and cloud resources consumers/users. The current Max-Min algorithm selects tasks with maximum execution time on a faster available machine or resource that is capable of giving minimum completion time. The concern of this algorithm is to give priority to tasks with maximum execution time first before assigning those with the minimum execution time for the purpose of minimizing makespan. The drawback of this algorithm is that, the execution of tasks with maximum execution time first may increase the makespan, and leads to a delay in executing tasks with minimum execution time if the number of tasks with maximum execution time exceeds that of tasks with minimum execution time, hence the need to improve it to mitigate the delay in executing tasks with minimum execution time. CloudSim is used to compare the effectiveness of the improved Max-Min algorithm with the traditional one. The experimented results show that the improved algorithm is efficient and can produce better makespan than Max-Min and DataAware.

In cloud computing, the user can access the shared resources over the network in a service-based environment. The on-request access to computing resources such as networks, servers, and applications is the major idea of cloud computing. With the development in computing technologies, cloud computing has added a new paradigm to user services that permits accessing Information Technology services on the bottom of pay-per-use at any time as well as any location. Owing to flexibility in cloud services, many organizations are shifting their business to the cloud and service providers are creating more data centers to offer services to users. However, it is vital to provide cost-effective execution of tasks and appropriate utilization of resources. Cloud computing manages a variability of virtualized resources, which makes scheduling a serious component. In the cloud, a client may utilize numerous thousand virtualized assets for all task. Consequently, manual scheduling is not a possible solution. Task scheduling is one of the vital techniques in the cloud computing environment. It is essential for allocating tasks to the appropriate resources and optimizing the overall system performance. The simple idea behind task scheduling is to slate tasks to minimalize execution time and maximize performance as well as resource utilization. In this paper we have surveyed Min-Min, Max-Min and Hybrid algorithm to analyse which algorithm gives better makespan and resource utilization.

Regular

Nowadays, with the huge development of information and computing technologies, the cloud computing is becoming the highly scalable and widely computing technology used in the world that bases on pay-per-use, remotely access, Internet-based and on-demand concepts in which providing customers with a shared of configurable resources. But, with the highly incoming user’s requests, the task scheduling and resource allocation are becoming major requirements for efficient and effective load balancing of a workload among cloud resources to enhance the overall cloud system performance. For these reasons, various types of task scheduling algorithms are introduced such as traditional, heuristic, and meta-heuristic. A heuristic task scheduling algorithms like MET, MCT, Min-Min, and Max-Min are playing an important role for solving the task scheduling problem. This paper proposes a new hybrid algorithm in cloud computing environment that based on two heuristic algorithms; Min-Min and Max-Min alg...

International Journal of Computer Applications, 2012

In this paper, a unique modification of Max-min algorithm is proposed. The algorithm is built based on comprehensive study of the impact of RASA algorithm in scheduling tasks and the atom concept of Max-min strategy. An Improved version of Max-min algorithm is proposed to outperform scheduling map at least similar to RASA map in total complete time for submitted jobs. Improved Max-min is based on the expected execution time instead of complete time as a selection basis. Experimental results show availability of load balance in small cloud computing environment and total small makespan in large-scale distributed system; cloud computing. In turn scheduling tasks within cloud computing using Improved Max-min demonstrates achieving schedules with comparable lower makespan rather than RASA and original Max-min.

International Journal for Research in Applied Science and Engineering Technology IJRASET, 2020

Cloud computing is an information technology paradigm that enables access to various shared pools of configurable system resources and higher level services. It provides delivery of computing services like storage, servers, database etc. Task scheduling is an important part in cloud computing for limited number of heterogeneous resources and increasing number of user tasks. In case of great cloudlets with high Size may lead fail in load balancing, increased makes pan and decreased average resource utilization. This paper provides an efficient algorithm to solve the above issues in task scheduling. Index Terms: HCA, EHCA, OCT, EDCB I. INTRODUCTION Cloud computing is the on-demand availability of computer system resources, especially data storage (cloud storage) and computing power, without direct active management by the user. The term is generally used to describe data centers available to many users over the Internet. Large clouds, predominant today, often have functions distributed over multiple locations from central servers. If the connection to the user is relatively close, it may be designated an edge server. Clouds may be limited to a single organization (enterprise clouds), or be available to many organizations (public cloud).Cloud computing relies on sharing of resources to achieve coherence and economies of scale. Advocates of public and hybrid clouds note that cloud computing allows companies to avoid or minimize up-front IT infrastructure costs. Proponents also claim that cloud computing allows enterprises to get their applications up and running faster, with improved manageability and less maintenance, and that it enables IT teams to more rapidly adjust resources to meet fluctuating and unpredictable demand, providing the burst computing capability: high computing power at certain periods of peak demand. Cloud providers typically use a "pay-as-you-go" model, which can lead to unexpected operating expenses if administrators are not familiarized with cloud-pricing models. The availability of high-capacity networks, low-cost computers and storage devices as well as the widespread adoption of hardware virtualization, service-oriented architecture and autonomic and utility computing has led to growth in cloud computing. In recent years, cloud computing has emerged as heterogeneous distributed computing system to manage and allocate computing resources to user applications over the Internet in a self-service, dynamically scalable and metered manner[1]. User application can be divided in small size or high size of tasks (cloudlets). The advantage of high size is that the number of cloudlets is more reduced than with small size. However, a great number of large cloudlets whose cloudlet corresponds to high size lead the cloud system to fail in good load balancing and lower completion time. This is caused by their high execution time and delay during their execution on virtual machine (VM). Due to the security issues related to virtualization [7], all these VMs are distributed among increasing number of cloud users to complete running of their cloudlets. This means that the number of these VMs is much more reduced per single user Optimizing task scheduling with good load balancing and minimum makespan which takes into account of large and small cloudlets under resources capacity constraints, such as number of VMs and processing speed, still remains the major challenging issue not well solved in cloud computing[1]. Therefore, task scheduling being an NP-hard problem, then a best optimal heuristic cloudlet allocation is required for managing high number of large and small cloudlets submitted by a single user to maximize both load balancing and resource utilization and to minimize overall completion time. Based on task scheduling, many heuristic algorithms have been proposed to minimize the execution time of a task and finish time such as first strategy algorithm [1], round robin (RR) [1] and standard deviation based modified cuckoo optimization algorithm (SDMCOA). FSA is based on a deadline, length of cloudlets and speed of execution of VMs, and vector that defines the number of cloudlets per VM, is distributed to each VM. FSA lacks in considering the completion time of VM and size of large cloudlets. As a result, this lack leads to higher completion time and improper load balancing. RR uses the ring as its queue to store cloudlets, and it allocates resources in circular order without using priority of the cloudlets. Each cloudlet in a queue has a same fixed unit of time, called quantum, allocated by scheduler and it

IOSR Journal of Computer Engineering, 2016

The main content of Cloud Computing is to manage Software application, data storage and processing capacity which are assigned to external users on demand through the internet and pay only for what they use. Task scheduling in cloud computing is the biggest challenges because many tasks need to be executed by the available resources in order to meet user's requirements. To achieve best performance, minimize total completion time, minimize response time and maximize resources utilization there is need to address these challenges. This paper studies different task scheduling algorithms and an Enhanced Min-min algorithm is developed. The algorithm uses the advantages of Min-min and avoids its drawbacks. The main idea of the proposed algorithm is to allocate tasks to resources appropriately in order to achieve an effective load balancing and decrease completion time. The experimental results indicate that the proposed algorithm compared to Min-min and Max-min produces better Makespan and improved resources utilization.

Menoufia Journal of Electronic Engineering Research

This paper presents a new hybrid approach, called ACOSA, for cloudlets scheduling to enhance the scheduler behavior in Cloud computing (CC) environment and to overcome the results oscillation problem of the existing meta-heuristic scheduling algorithms. The proposed approach combines both the Ant Colony Optimization (ACO) and Simulated Annealing (SA) algorithm to improve both quality of solutions and time complexity of the scheduling algorithm. The proposed approach is evaluated by using the well-known CloudSim, and the results are compared with the ant colony and simulated annealing separately in terms of schedule length, load balancing, and time complexity. It decreases the schedule length by 29.75% with SA and 12.25% with ACO. The ACOSA provides higher load balancing degree. It improves the balancing degree ratio by 36.36% than SA and 12.13% than ACO algorithms.

2019

Management of cloud computing resources is critical, especially when several cloudlets are submitted simultaneously to cloud computing. Therefore, it is very important to use high efficient cloudlet scheduling techniques to guarantee efficient utilization of computing resources. This paper presents a two-phase approach, called SAAC , for scheduling cloudlets onto Virtual Machines ( VMs ) of cloud computing environment to balance workload on the available VMs and minimize makespan (i.e., the completion time at the maximum loaded VM ). In the first phase, the SAAC approach applies the Simulated Annealing ( SA ) to find a near optimal scheduling of the cloudlets. While, in the second phase, the SAAC approach improves the cloudlets distribution by applying the Ant Colony Optimization ( ACO ) considering the solution obtained by the SA as the initial solution. The SAAC approach overcomes the computational time complexity of the ACO algorithm and low solutions quality of the SA . The prop...

International journal of engineering research and technology, 2018

Cloud Computing is one of the emerging technology based upon on demand pay per use model. It is a platform where various services like applications, bandwidth and data are provided to its users using Internet. The main objective of Job Scheduling Algorithms in Cloud Computing is to optimize the resource allocation and utilization to meet user requirements and for cloud service providers it is the efficient use of resources and thus attaining maximum profit. All this leads us right to the requirement of Job Scheduling in Cloud Computing. Scheduling is the method of deciding how to provide resources amongst the various available tasks or processes so as to achieve the maximum throughput efficiently. In this paper various Job Scheduling algorithms have been presented on the basis of different parameters which provide efficient cloud services.