الگوریتم زمان بندی شغلی بر اساس مدل برگر در محیط ابری
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|20187||2011||7 صفحه PDF||سفارش دهید||محاسبه نشده|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Advances in Engineering Software, Volume 42, Issue 7, July 2011, Pages 419–425
Considered the commercialization and the virtualization characteristics of cloud computing, the paper proposed for the first time an algorithm of job scheduling based on Berger model. In the job scheduling process, the algorithm establishes dual fairness constraint. The first constraint is to classify user tasks by QoS preferences, and establish the general expectation function in accordance with the classification of tasks to restrain the fairness of the resources in selection process. The second constraint is to define resource fairness justice function to judge the fairness of the resources allocation. We have expanded simulation platform CloudSim, and have implemented the job scheduling algorithm proposed in this paper. The experimental results show that the algorithm can effectively execute the user tasks and manifests better fairness.
Cloud computing is the development of grid computing, parallel computing and distributed computing. It is a new pattern of business computing. Compared with grid computing, cloud computing has some new features, such as (1) grid computing is in general the integration of fragmented, heterogeneous distribution resources; cloud computing is the large-scale data center resources which are more concentrated. In addition, virtualization technology hides the heterogeneity of the resources in cloud computing, (2) grid is generally used in science computation, and for solving special-purpose domain problem; cloud computing is user-oriented design which provides varied services to meet the needs of different users. It is more commercialized, and (3) the resources in cloud computing are packed into virtual resources by using virtualization technology. This causes its resource allocation process, the interaction with user tasks and so on are different with grid computation. The basic mechanism of cloud computing is to dispatch the computing tasks to resource pooling which constitutes by massive computers. It enables a variety of applications to gain computing power, storage and a variety of software services according to their needs  and . The commercialization and the virtualization technology adopted by cloud computing has poured into new features for cloud architecture. For example, it leaves the job scheduling complexity of cloud computing to the virtual machine layer through resource virtualization. Further, it raised a number of new features for job scheduling, such as cloud computing needs pay more attention to the fairness of resources allocation. The paper, from the fairness point of view, for the first time proposed and implemented the algorithm of job scheduling based on Berger model in cloud computing. The paper is organized as follows: Section 2 gives related work. Section 3 gives some background knowledge. Section 4 gives detailed description of the algorithm of job scheduling based on Berger model. Section 5 describes the simulation experiment and experimental results. Section 6 gives the conclusions.
نتیجه گیری انگلیسی
In this paper, Berger model theory on distributive justice in the field of social distribution was first introduced into the job scheduling algorithm in cloud computing. Through the expansion of CloudSim platform, job scheduling algorithm based on Berger model is implemented. The validity of the algorithm is verified on the extended simulation platform. By comparing of simulation results with the optimal completion time algorithm, the proposed algorithm in this paper is effective implementation of user tasks, and with better fairness. As to the initial value of general expectation vector, what the paper gives is empirical value. In the future, we will build a fuzzy neural network of QoS feature vector of task and parameter vector of resource based on the non-linear mapping relationship between QoS and resource. Through learning, more accurate vector value of the general expectation can be obtained.