A high-performance scheduling algorithm using greedy strategy toward quality of service in the cloud environments
- PDF / 729,681 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 31 Downloads / 196 Views
A high-performance scheduling algorithm using greedy strategy toward quality of service in the cloud environments Zhou Zhou 1 & Hongmin Wang 2 & Huailing Shao 3 & Lifeng Dong 3 & Junyang Yu 4 Received: 23 August 2019 / Accepted: 12 February 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Effectively resource management in the cloud environment can improve the utilization of resource and reduce resource costs and overheads.Task scheduling and optimization within the cloud computing environment are one of the main concerns that need to be handled to increase resource utilization and QoS (Quality of Service). Although there are some algorithms have been proposed to handle the problem of task scheduling, existing methods mainly focus on reducing the task execution time while ignoring the other factors such as workload balance and QoS. In this paper, we put forward a novel algorithm named ITSA (Improved Task Schedule Algorithm), which is based on the gain value of task swap and performs “task pair” scheduling by utilizing the greedy strategy. The main idea of ITSA can be concluded as follows: Firstly, we present the concept of the gain value of task swap; then, we bind task with the minimum gain value and task with the maximum gain value together to form a “task pair”, and perform scheduling by adopting the greedy strategy. Finally, we evaluate the proposed algorithm by extensive experiment, and the data obtained from the experiment shows that the proposed algorithm has a better performance compared with other algorithms in terms of the workload balance and QoS. Keywords Cloud computing . Big data . Greedy strategy . Resource management . QoS
1 Introduction Cloud computing is a new computing paradigm that has integrated multiple technologies including utility computing, distributed computing, parallel computing, and so on. The users within the cloud environment can access related resources (such as computing source and storage source) in a pay-asyou-use way according to personal requirements, and get a response at a low price. In cloud computing, a variety of problems occur in the task schedule that attempts to select the best resource. Also, the task scheduling problem in heterogeneous computing (HC) systems is more complex, because the execution speed of different processors is different, and the communication speed * Junyang Yu [email protected] 1
Department of Mathematics and Computer Science, Changsha University, Changsha 410083, China
2
Henan electric power company, Zhengzhou 450000, China
3
Henan Jiuyu Tenglong Information Engineering Company, Zhengzhou 450000, China
4
Software School, Henan University, Kaifeng 475001, China
between different processors may also be different. To meet the requirements of end-users, the fundamental goal within the cloud environment is designing a system that could improve efficiency and provide a platform for enterprises or companies to expand the rational utilization of all computing resources [1, 2]. However, the heterogeneity and decen
Data Loading...
