2022
DOI: 10.1016/j.jnca.2022.103385
|View full text |Cite
|
Sign up to set email alerts
|

A two-stage scheduler based on New Caledonian Crow Learning Algorithm and reinforcement learning strategy for cloud environment

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 19 publications
(3 citation statements)
references
References 38 publications
0
3
0
Order By: Relevance
“…Other DRL-based scheduling algorithms include HCDRL (Chen et al 2023a), DT (decision transformer) using GPT (Wang et al 2023), CORA (Huang et al 2023), DRAW (Chen et al 2023b), PRLCC (Zade et al 2022), ReCARL (Xu et al 2022), etc. These algorithms still belong to the DRL architecture of Fig.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Other DRL-based scheduling algorithms include HCDRL (Chen et al 2023a), DT (decision transformer) using GPT (Wang et al 2023), CORA (Huang et al 2023), DRAW (Chen et al 2023b), PRLCC (Zade et al 2022), ReCARL (Xu et al 2022), etc. These algorithms still belong to the DRL architecture of Fig.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Zade et.al [18] contributed a two-phase algorithm which resulted in improved performance with first phase dealing with meta scheduling that assigns the tasks to host machine and in the second phase the scheduling is rein enforced using parallel reinforcement learning caledonian crow for optimal local scheduling to present optimal mapping of tasks and VMs. Sudheer Mangalampalli et.al [19] proposed an optimal scheduler which targets reduced energy consumption and power costs at datacenters by considering the priorities of tasks and VM's.…”
Section: Related Workmentioning
confidence: 99%
“…Heuristic algorithms can be divided into two categories according to their characteristics: Static ones [3][4][5][6] are generally simple strategies and are suitable for tasks that are known before scheduling. Dynamic algorithms [7][8][9] consider the dynamics of cloud platforms, but there are some problems, such as a large number of iterations and long computation times [9][10][11]. In addition, though static and dynamic algorithms can both deal with tasks with dependency [5,6,8,[12][13][14], dependency also brings task validity issues [15].…”
Section: Introductionmentioning
confidence: 99%