A priority based job scheduling algorithm using IBA and EASY algorithm for cloud metaschedular

Dubey, Kalka; Kumar, Mithilesh; Chandra, Mayank Arya

doi:10.1109/icacea.2015.7164647

Cited by 13 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further research is conducted to remove the compromises between QoS parameters and load balancing. [83][84][85][86] Table 3 enlists the QoS parameters that are considered by proposed algorithms and frameworks. It can be observed that none of the studies has considered every parameter in their frameworks.…”

Section: Existing Solutions To Overcome the Mentioned Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Journey from cloud of things to fog of things: Survey, new trends, and research directions

et al. 2022

Self Cite

View full text Add to dashboard Cite

With the advent of the Internet of Things (IoT) paradigm, the cloud model is unable to offer satisfactory services for latency-sensitive and real-time applications due to high latency and scalability issues. Hence, an emerging computing paradigm named as fog/edge computing was evolved, to offer services close to the data source and optimize the quality of services (QoS) parameters such as latency, scalability, reliability, energy, privacy, and security of data. This article presents the evolution in the computing paradigm from the client-server model to edge computing along with their objectives and limitations. A state-of-the-art review of Cloud Computing and Cloud of Things (CoT) is presented that addressed the techniques, constraints, limitations, and research challenges. Further, we have discussed the role and mechanism of fog/edge computing and Fog of Things (FoT), along with necessitating amalgamation with CoT. We reviewed the several architecture, features, applications, and existing research challenges of fog/edge computing. The comprehensive survey of these computing paradigms offers the depth knowledge about the various aspects, trends, motivation, vision, and integrated architectures. In the end, experimental tools and future research directions are discussed with the hope that this study will work as a stepping-stone in the field of emerging computing paradigms. K E Y W O R D Scloud computing, internet of things, cloud of things, fog computing, latency INTRODUCTIONDifferent computing paradigms have evolved over the decades as per the needs in various situations. The concept of the Cloud computing paradigm has evolved from distributed systems and it has gained attention by offering a plethora of services to end-users anywhere and anytime on pay per use basis. It has also become the business model in the last decade due to well-known characteristics like scalability, multi-tenant environment, virtualization, and resource pooling. It is observed that a large number of industries, government, as well as private organization, have shifted their applications and data to the cloud platform. Further, the Cloud is also playing a significant role in the advancement of Internet of Things (IoT) applications. As per the transformation and movement in ubiquitous computing, we need the integration

show abstract

Section: Existing Solutions To Overcome the Mentioned Challengesmentioning

confidence: 99%

“…Both the mentioned algorithms result in efficient resource scheduling at the cost of not considering security and privacy. Further research is conducted to remove the compromises between QoS parameters and load balancing 83‐86 …”

Section: Cloud Computingmentioning

confidence: 99%

Journey from cloud of things to fog of things: Survey, new trends, and research directions

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Heuristic, meta-heuristic, and optimization-based are three categories of task scheduling schemes. Heuristic task scheduling schemes can be divided into quite a few sub categories based on their objectives such as load balancing [27], [28], [29], priority-based scheduling [30], [31], [32], , task duplication [33], and clustering [34].…”

Section: Prior Workmentioning

confidence: 99%

Bottleneck Time Minimization for Distributed Iterative Processes: Speeding Up Gossip-Based Federated Learning on Networked Computers

Kiamari,

Krishnamachari

2021

Preprint

View full text Add to dashboard Cite

We present a novel task scheduling scheme for accelerating computational applications involving distributed iterative processes that are executed on networked computing resources. Such an application consists of multiple tasks, each of which outputs data at each iteration to be processed by neighboring tasks; these dependencies between the tasks can be represented as a directed graph. We first mathematically formulate the problem as a Binary Quadratic Program (BQP), accounting for both computation and communication costs. We show that the problem is NP-hard. We then relax the problem as a Semi-Definite Program (SDP) and utilize a randomized rounding technique based on sampling from a suitably-formulated multi-variate Gaussian distribution. Furthermore, we derive the expected value of bottleneck time. Finally, we apply our proposed scheme on gossip-based federated learning as an application of iterative processes. Through numerical evaluations on the MNIST and CIFAR-10 datasets, we show that our proposed approach outperforms well-known scheduling techniques from distributed computing. In particular, for arbitrary settings, we show that it reduces bottleneck time by 91% compared to HEFT and 84% compared to throughput HEFT.

show abstract

“…Dubey et.al [5] proposed a dynamic algorithm that is based upon the priority of task using the combined approach of IBA and EASY algorithm. There are various dynamic job scheduling algorithm also exist in cloud environment but the entire algorithm have some pros and cons.…”

Section: Fig1 Metascheduler Architecturementioning

confidence: 99%

“…After applying IBA algorithm all queues are combined to form a intermediate sequence. 5. Now applying the EASY algorithm on this intermediate sequence for better utilization of resources.…”

mentioning

confidence: 99%

A New Scheduling Algorithm for Job Scheduler in Cloud Environment Considering the Priority and Cost as Constraint

Kumar¹

2017

IJARCSSE

Self Cite

View full text Add to dashboard Cite

Abstract-Cloud computing provides the different types of services (availability, scalability, on demand service etc.) to the user on the basis of pay per use basis over the internet. Number of users and application are increasing day by day in cloud environment due to which assignment of task to best virtual machine among the available virtual machine become the difficult problem because it is not easy to predict the task execution time at run time. Therefore cloud task (job) scheduler should be dynamic in nature and distribute the all the task among all the virtual machine in such a manner that no virtual machine should be in under loaded or overloaded. We proposed and developed a task scheduling algorithm considering the priority of jobs and cost as a constraint. Proposed algorithm shows that IBA minimize the idle time of resources but does not provide the guarantee for handling job priority and cost of the resource. So there is a need of job scheduling algorithm that considers job priority and recourse cost. Keywords-virtual machine, task scheduling, cloud job scheduler, metascheduler I. INTRODUCTIONCloud computing becoming the emerging technology in the field of IT within last few years. It provides the scalability, flexibility and virtualization type of services over the internet to the user. There are three type of basic service provided by the cloud computing, software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS). Cloud user uses the services of cloud on the pay per use basis and cloud service provider try to provide the satisfactory level of services to the user. Elasticity property of cloud computing, user can expand and contract his service on demand basis. If done correctly, it is less expensive than running to a regular hardware. Cloud provides the service to store and retrieve the data easy and flexible way without worrying the hardware configuration needed. As the number of user is increasing day-by-day on cloud, all the user need services from cloud infrastructure. User send request to cloud for service, there is a possibility that some node of cloud computing can be overloaded or under loaded condition. To overcome this type of problem, many algorithms have been proposed by researcher, but all algorithms have their advantages and limitation. So load balancing has been become a challenging problem for cloud service provider.There are two types of scheduler exist in cloud computing: first one is local scheduler that works with host i.e assigned the job to the virtual machine and monitor the status of virtual machine after a time interval. Second one is called global scheduler or meta scheduler. User submits all through the web interface in cloud environment after that all the jobs are checked by gatekeeper that request are coming from legitimate user or not [9]. If request are coming from legitimate user then job are directed to meta scheduler otherwise request is rejected. Meta scheduler contains the information about all the virtual machine. Meta sched...

show abstract

A priority based job scheduling algorithm using IBA and EASY algorithm for cloud metaschedular

Cited by 13 publications

References 9 publications

Journey from cloud of things to fog of things: Survey, new trends, and research directions

Journey from cloud of things to fog of things: Survey, new trends, and research directions

Bottleneck Time Minimization for Distributed Iterative Processes: Speeding Up Gossip-Based Federated Learning on Networked Computers

A New Scheduling Algorithm for Job Scheduler in Cloud Environment Considering the Priority and Cost as Constraint

Contact Info

Product

Resources

About