A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling
With more businesses are running online, the scale of data centers is increasing dramatically. The task-scheduling operation with traditional heuristic algorithms is facing the challenges of uncertainty and complexity of the data center environment. It is urgent to use new technology to optimize the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/3046769 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551272051376128 |
|---|---|
| author | Haiying Che Zixing Bai Rong Zuo Honglei Li |
| author_facet | Haiying Che Zixing Bai Rong Zuo Honglei Li |
| author_sort | Haiying Che |
| collection | DOAJ |
| description | With more businesses are running online, the scale of data centers is increasing dramatically. The task-scheduling operation with traditional heuristic algorithms is facing the challenges of uncertainty and complexity of the data center environment. It is urgent to use new technology to optimize the task scheduling to ensure the efficient task execution. This study aimed at building a new scheduling model with deep reinforcement learning algorithm, which integrated the task scheduling with resource-utilization optimization. The proposed scheduling model was trained, tested, and compared with classical scheduling algorithms on real data center datasets in experiments to show the effectiveness and efficiency. The experiment report showed that the proposed algorithm worked better than the compared classical algorithms in the key performance metrics: average delay time of tasks, task distribution in different delay time levels, and task congestion degree. |
| format | Article |
| id | doaj-art-aae0842a1dc84b7d84b4b6cd5245cfad |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-aae0842a1dc84b7d84b4b6cd5245cfad2025-02-03T06:04:37ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/30467693046769A Deep Reinforcement Learning Approach to the Optimization of Data Center Task SchedulingHaiying Che0Zixing Bai1Rong Zuo2Honglei Li3Beijing Institute of Technology, Zhongguancun South Street No. 5, Beijing 100081, ChinaBeijing Institute of Technology, Zhongguancun South Street No. 5, Beijing 100081, ChinaBeijing Institute of Technology, Zhongguancun South Street No. 5, Beijing 100081, ChinaLiaoning Normal University, Huanghelu 850, Dalian 116029, ChinaWith more businesses are running online, the scale of data centers is increasing dramatically. The task-scheduling operation with traditional heuristic algorithms is facing the challenges of uncertainty and complexity of the data center environment. It is urgent to use new technology to optimize the task scheduling to ensure the efficient task execution. This study aimed at building a new scheduling model with deep reinforcement learning algorithm, which integrated the task scheduling with resource-utilization optimization. The proposed scheduling model was trained, tested, and compared with classical scheduling algorithms on real data center datasets in experiments to show the effectiveness and efficiency. The experiment report showed that the proposed algorithm worked better than the compared classical algorithms in the key performance metrics: average delay time of tasks, task distribution in different delay time levels, and task congestion degree.http://dx.doi.org/10.1155/2020/3046769 |
| spellingShingle | Haiying Che Zixing Bai Rong Zuo Honglei Li A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling Complexity |
| title | A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling |
| title_full | A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling |
| title_fullStr | A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling |
| title_full_unstemmed | A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling |
| title_short | A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling |
| title_sort | deep reinforcement learning approach to the optimization of data center task scheduling |
| url | http://dx.doi.org/10.1155/2020/3046769 |
| work_keys_str_mv | AT haiyingche adeepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling AT zixingbai adeepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling AT rongzuo adeepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling AT hongleili adeepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling AT haiyingche deepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling AT zixingbai deepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling AT rongzuo deepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling AT hongleili deepreinforcementlearningapproachtotheoptimizationofdatacentertaskscheduling |