A Deep Reinforcement Learning-Based Preemptive Approach for Cost-Aware Cloud Job Scheduling

doi:10.1109/TSUSC.2023.3303898

	A Deep Reinforcement Learning-Based Preemptive Approach for Cost-Aware Cloud Job Scheduling
	Cheng, Long 1; Wang, Yue 1; Cheng, Feng 2; Liu, Cheng 3; Zhao, Zhiming 4; Wang, Ying 3
	2024-05-01
发表期刊	IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING
ISSN	2377-3782
卷号	9 期号:3 页码:422-432
摘要	With some specific characteristics such as elastics and scalability, cloud computing has become the most promising technology for online business nowadays. However, how to efficiently perform real-time job scheduling in cloud still poses significant challenges. The reason is that those jobs are highly dynamic and complex, and it is always hard to allocate them to computing resources in an optimal way, such as to meet the requirements from both service providers and users. In recent years, various works demonstrate that deep reinforcement learning (DRL) can handle real-time cloud jobs well in scheduling. However, to our knowledge, none of them has ever considered extra optimization opportunities for the allocated jobs in their scheduling frameworks. Given this fact, in this work, we introduce a novel DRL-based preemptive method for further improve the performance of the current studies. Specifically, we try to improve the training of scheduling policy with effective job preemptive mechanisms, and on that basis to optimize job execution cost while meeting users' expected response time. We introduce the detailed design of our method, and our evaluations demonstrate that our approach can achieve better performance than other scheduling algorithms under different real-time workloads, including the DRL approach.
关键词	Cloud computing Processor scheduling Real-time systems Costs Quality of service Time factors Dynamic scheduling DRL job scheduling preemptive mechanism optimization
DOI	10.1109/TSUSC.2023.3303898
收录类别	SCI
语种	英语
资助项目	Fundamental Research Funds for the Central Universities
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Telecommunications
WOS记录号	WOS:001243025500020
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40037
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Cheng, Feng
作者单位	1.North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China 2.Southwest Jiaotong Univ, Sch Math, Chengdu 610032, Sichuan, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 4.Univ Amsterdam, Res Grp Multiscale Networked Syst, NL-1012WP Amsterdam, Netherlands
推荐引用方式 GB/T 7714	Cheng, Long,Wang, Yue,Cheng, Feng,et al. A Deep Reinforcement Learning-Based Preemptive Approach for Cost-Aware Cloud Job Scheduling[J]. IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING,2024,9(3):422-432.
APA	Cheng, Long,Wang, Yue,Cheng, Feng,Liu, Cheng,Zhao, Zhiming,&Wang, Ying.(2024).A Deep Reinforcement Learning-Based Preemptive Approach for Cost-Aware Cloud Job Scheduling.IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING,9(3),422-432.
MLA	Cheng, Long,et al."A Deep Reinforcement Learning-Based Preemptive Approach for Cost-Aware Cloud Job Scheduling".IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING 9.3(2024):422-432.