Two Approaches for Workflow Scheduling with Quality of Service in the Grid

2012 ◽  
pp. 1265-1288
Author(s):  
Fangpeng Dong ◽  
Selim G. Akl
Keyword(s):  
Resource Sharing ◽  
Completion Time ◽  
Scheduling Algorithm ◽  
Workflow Scheduling ◽  
Performance Change ◽  
Probability Mass ◽  
Grid Resources ◽  
Mass Functions ◽  
Algorithm Level

Over the past decade, Grid Computing has earned its reputation by facilitating resource sharing in larger communities and providing non-trivial services. However, for Grid users, Grid resources are not usually dedicated, which results in fluctuations of available performance. This situation raises concerns about the quality of services (QoS). The meaning of QoS varies with different concerns of different users. Objective functions that drive job schedulers in the Grid may be different from each other as well. Some are system-oriented, which means they make schedules to favor system metrics such as throughput, load-balance, resource revenue and so on. To narrow the scope of the problem to be discussed in this chapter and to make the discussion substantial, the scheduling objective function considered is minimizing the total completion time of all tasks in a workflow (also known as the makespan). Correspondingly, the meaning of QoS is restricted to the ability that scheduling algorithms can shorten the makespan of a workflow in an environment where resource performance is vibrant. This chapter introduces two approaches that can provide QoS features at the workflow scheduling algorithm level in the Grid. One approach is based on a workflow rescheduling technique, which can reallocate resources for tasks when a resource performance change is observed. The other copes with the stochastic performance change using pre-acquired probability mass functions (PMF) and produces a probability distribution of the final schedule length, which will then be used to handle the different QoS concerns of the users.

Two Approaches of Workflow Scheduling with QoS in the Grid

2011 ◽  
pp. 1-27
Author(s):  
Fangpeng Dong ◽  
Selim G. Akl
Keyword(s):  
Resource Sharing ◽  
Completion Time ◽  
Scheduling Algorithm ◽  
Workflow Scheduling ◽  
Performance Change ◽  
Probability Mass ◽  
Grid Resources ◽  
Mass Functions ◽  
Algorithm Level

Over the past decade, Grid Computing has earned its reputation by facilitating resource sharing in larger communities and providing non-trivial services. However, for Grid users, Grid resources are not usually dedicated, which results in fluctuations of available performance. This situation raises concerns about the quality of services (QoS). The meaning of QoS varies with different concerns of different users. Objective functions that drive job schedulers in the Grid may be different from each other as well. Some are system-oriented, which means they make schedules to favor system metrics such as throughput,load-balance, resource revenue and so on. To narrow the scope of the problem to be discussed in this chapter and to make the discussion substantial, the scheduling objective function considered is minimizing the total completion time of all tasks in a workflow (also known as the makespan). Correspondingly, the meaning of QoS is restricted to the ability that scheduling algorithms can shorten the makespan of a workflow in an environment where resource performance is vibrant. This chapter introduces two approaches that can provide QoS features at the workflow scheduling algorithm level in the Grid. One approach is based on a workflow rescheduling technique, which can reallocate resources for tasks when a resource performance change is observed. The other copes with the stochastic performance change using pre-acquired probability mass functions (PMF) and produces a probability distribution of the final schedule length, which will then be used to handle the different QoS concerns of the users.

LoBa-Min-Min: The Grid Resources Scheduling Algorithm Based on Load Balance

2013 ◽  
Vol 321-324 ◽  
pp. 2507-2513
Author(s):  
Zhong Ping Zhang ◽  
Li Juan Wen
Keyword(s):  
Resource Utilization ◽  
Load Balance ◽  
Completion Time ◽  
Scheduling Algorithm ◽  
Scheduling Algorithms ◽  
Utilization Rate ◽  
Grid Environment ◽  
Low Resource ◽  
Grid Resources

In the grid environment, there are a large number of grid resources scheduling algorithms. According to the existing Min-Min scheduling algorithm in uneven load, and low resource utilization rate, we put forward the LoBa-Min-Min algorithm, which is based on load balance. This algorithm first used Min-Min algorithm preliminary scheduling, then according to the standard of reducing Makespan, the tasks on heavy-loaded resources would be assigned to resources that need less time to load balance, raise resource utilization rate, and achieve lesser completion time. At last, we used benchmark of instance proposed by Braun et al. to prove feasibility and effectiveness of the algorithm.

scholarly journals Load Balancing Technique with an Efficient Method

2019 ◽  
Vol 8 (6) ◽  
pp. 1257-1262
Keyword(s):  
Cloud Computing ◽  
Load Balancing ◽  
Efficient Method ◽  
Load Balance ◽  
Completion Time ◽  
Scheduling Algorithm ◽  
Quality Of Services ◽  
Huge Number ◽  
Task Scheduling Algorithm

There are a huge number of nodes connected to web computing to offer various types of web services to provide cloud clients. Limited numbers of nodes connected to cloud computing have to execute more than a thousand or a million tasks at the same time. So it is not so simple to execute all tasks at the same particular time. Some nodes execute all tasks, so there is a need to balance all the tasks or loads at a time. Load balance minimizes the completion time and executes all the tasks in a particular way.There is no possibility to keep an equal number of servers in cloud computing to execute an equal number of tasks. Tasks that are to be performed in cloud computing would be more than the connected servers. Limited servers have to perform a great number of tasks.We propose a task scheduling algorithm where few nodes perform the jobs, where jobs are more than the nodes and balance all loads to the available nodes to make the best use of the quality of services with load balancing.

scholarly journals Bandwidth-Aware Scheduling of Workflow Application on Multiple Grid Sites

2014 ◽  
Vol 2014 ◽  
pp. 1-15 ◽  
Author(s):  
Harshadkumar B. Prajapati ◽  
Vipul A. Shah
Keyword(s):  
Open Source ◽  
Scheduling Algorithm ◽  
Scientific Workflows ◽  
Workflow Scheduling ◽  
Grid Environment ◽  
Data Movement ◽  
Workflow Mapping ◽  
Workflow Application ◽  
Algorithm Level ◽  
Better Than

Bandwidth-aware workflow scheduling is required to improve the performance of a workflow application in a multisite Grid environment, as the data movement cost between two low-bandwidth sites can adversely affect the makespan of the application. Pegasus WMS, an open-source and freely available WMS, cannot fully utilize its workflow mapping capability due to unavailability of integration of any bandwidth monitoring infrastructure in it. This paper develops the integration of Network Weather Service (NWS) in Pegasus WMS to enable the bandwidth-aware mapping of scientific workflows. Our work demonstrates the applicability of the integration of NWS by making existing Heft site-selector of Pegasus WMS bandwidth aware. Furthermore, this paper proposes and implements a new workflow scheduling algorithm—Level based Highest Input and Processing Weight First. The results of the performed experiments indicate that the bandwidth-aware workflow scheduling algorithms perform better than bandwidth-unaware algorithms: Random and Heft of Pegasus WMS. Moreover, our proposed workflow scheduling algorithm performs better than the bandwidth-aware Heft algorithms. Thus, the proposed bandwidth-aware workflow scheduling enhances capability of Pegasus WMS and can increase performance of workflow applications.

Task Scheduling Algorithm Based on Improved Min-Min Algorithm in Cloud Computing Environment

2013 ◽  
Vol 303-306 ◽  
pp. 2429-2432 ◽  
Author(s):  
Guan Wang ◽  
Hai Cun Yu
Keyword(s):  
Cloud Computing ◽  
Task Scheduling ◽  
Completion Time ◽  
Scheduling Algorithm ◽  
Total Completion Time ◽  
Computing Environment ◽  
Cloud Computing Environment ◽  
Task Schedule ◽  
Task Scheduling Algorithm

Task schedule algorithms directly related to the speed and quality of schedule. Min-Min algorithm always completes the shortest total completion time task first, and has the characteristic of simple and shortest completion time. This paper research scheduling algorithm based on Min—Min algorithm. The result shows that the proposed algorithm is efficient in the cloud computing environment.

Automata for Modeling Reversible Probabilistic Processes

2013 ◽  
Vol 422 ◽  
pp. 185-190
Author(s):  
Arpit ◽  
Afza Shafie ◽  
Wan Fatima Wan Ahmad
Keyword(s):  
Probability Distribution ◽  
Automata Theory ◽  
Testing Methods ◽  
Probabilistic Process ◽  
Probability Mass ◽  
Probabilistic Processes ◽  
Mass Functions

This paper presents a construction of an automaton that aids the modeling of probabilistic processes which exhibit reversibility during their computations. A probabilistic process defines a probability distribution over the uncertainties of its computations. This characteristic also makes them distinct from nondeterministic processes. But, uncertainties hinder the assurance about the quality of such systems gained by the traditional testing methods. Further, reversibility acts as a catalyst in such scenarios by raising the possibility of achieving the states which were inaccessible in past. Thus, the verification of such systems is necessary and this requires the system to be formally specified. In this respect, proposed work provides the constructs for modeling probabilistic environments and reversibility. Former is achieved by the introduction of discrete probabilities in classical automata theory, and later is implemented by giving the constructs of memory. It also provides the constructs for representing non-determinism by specifying the choices over several probability mass functions for a state.

scholarly journals Workflow Scheduling in Cloud Environment Using Firefly Optimization Algorithm

2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Shahin Ghasemi ◽  
Asra Kheyrolahi ◽  
Abdusalam Abdulla Shaltooki
Keyword(s):  
Load Balancing ◽  
Scheduling Algorithm ◽  
Workflow Scheduling ◽  
Application Management ◽  
Efficiency Measures ◽  
Firefly Optimization ◽  
Np Complete ◽  
The Cost ◽  
Firefly Optimization Algorithm

One of the issues in cloud computing is workflow scheduling. A workflow models the process of executing an application comprising a set of steps and its objective is to simplify the complexity of application management. Workflow scheduling maps each task to a proper resource and sorts tasks on each resource to meet some efficiency measures such as processing and transmission costs, load balancing, quality of service, and etc. Task scheduling is an NP-Complete problem. In this study, meta-heuristic firefly algorithm (FA) is used to present a workflow scheduling algorithm. The purpose of the proposed scheduling algorithm is to explore optimal schedules such that the cost of processing and transmission of the whole workflow are minimized while there will be load balancing among the processing stations. The proposed algorithm is implemented in MATLAB and its efficiency is compared with cat swarm optimization (CSO) algorithm. The evaluations show that the proposed algorithm outperforms CSO in finding better solutions.

scholarly journals Data Mining Association Rules using Probabilistic Functions without Predefined Weights

2020 ◽  
Vol 9 (6) ◽  
pp. 486-494
Keyword(s):  
Data Mining ◽  
Probability Density Function ◽  
Normal Distribution ◽  
Poisson Distribution ◽  
Association Rules ◽  
Heterogeneous Databases ◽  
Considerable Decrease ◽  
Probability Mass ◽  
Mass Functions

Data mining is the procedure of identifying the important and relevant data from large heterogeneous databases. Data mining plays an important role because of its usage in various domains. The transaction in the data mining defines the profit of the items associated with it. Earlier algorithms were proposed to measure the w-support without assigning predefined weights to determine the important transactions using the HITS model. Significant items are extracted from the databases using the quality of the transactions. However, there is considerable overhead in computing the w-support, as it requires four to five iterations. In this paper, two algorithms are proposed which uses the Poisson distribution and Normal distribution while computing the w-support without using the pre-assigned weights. The Poisson distribution uses the probability mass functions whereas the Normal distribution uses the probability density function to compute the w-support. The experiments were executed on various standard datasets. The results of our proposed algorithms show a considerable decrease in normalization time to compute the w-support as compared to the HITS model. Hence our algorithms provide better performance with respect to execution time and a number of significant items.

scholarly journals Hybrid scheduling algorithms in cloud computing: a review

2022 ◽  
Vol 12 (1) ◽  
pp. 880
Author(s):  
Neeraj Arora ◽  
Rohitash Kumar Banyal
Keyword(s):  
Cloud Computing ◽  
Quality Of Service ◽  
Resource Sharing ◽  
Scheduling Algorithm ◽  
Scheduling Algorithms ◽  
Hybrid Algorithms ◽  
Hybrid Scheduling ◽  
Processing Resource ◽  
Quality Of Service Parameters

<p><span>Cloud computing is one of the emerging fields in computer science due to its several advancements like on-demand processing, resource sharing, and pay per use. There are several cloud computing issues like security, quality of service (QoS) management, data center energy consumption, and scaling. Scheduling is one of the several challenging problems in cloud computing, where several tasks need to be assigned to resources to optimize the quality of service parameters. Scheduling is a well-known NP-hard problem in cloud computing. This will require a suitable scheduling algorithm. Several heuristics and meta-heuristics algorithms were proposed for scheduling the user's task to the resources available in cloud computing in an optimal way. Hybrid scheduling algorithms have become popular in cloud computing. In this paper, we reviewed the hybrid algorithms, which are the combinations of two or more algorithms, used for scheduling in cloud computing. The basic idea behind the hybridization of the algorithm is to take useful features of the used algorithms. This article also classifies the hybrid algorithms and analyzes their objectives, quality of service (QoS) parameters, and future directions for hybrid scheduling algorithms.</span></p>

Sign in / Sign up

Export Citation Format

Share Document