[1]王钰童,顾进广*.边缘场景下基于DDQN的容器组调度策略[J].计算机技术与发展,2024,34(09):16-22.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0163]
　WANG Yu-tong,GU Jin-guang*.Container Group Scheduling Optimization Strategy Based on DDQN in Edge Scenarios[J].,2024,34(09):16-22.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0163]
点击复制

边缘场景下基于DDQN的容器组调度策略()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年09期
页码:
16-22
栏目:
大数据与云计算
出版日期:
2024-09-10

文章信息/Info

Title:
Container Group Scheduling Optimization Strategy Based on DDQN in Edge Scenarios
文章编号:
1673-629X(2024)09-0016-07
作者:
王钰童1; 2; 3; 4; 顾进广1; 2; 3; 4*
1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065;2. 武汉科技大学 智能信息处理与实时工业系统湖北省重点实验室,湖北 武汉 430065;3. 武汉科技大学 大数据科学与工程研究院,湖北 武汉 430065;4. 国家新闻出版署富媒体数字出版内容组织与知识服务重点实验室,北京 100038
Author(s):
WANG Yu-tong1; 2; 3; 4; GU Jin-guang1; 2; 3; 4*
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;2. Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-time Industrial Systems,Wuhan University of Science and Technology,Wuhan 430065,China;3. Research Institute of Big Data Science and Engineering,Wuhan University of Science and Technology,Wuhan 430065,China;4. Key Laboratory of Rich Media Digital Publishing Content Organization and Knowledge Service of the National Pressand Publication Administration,Beijing 100038,China
关键词:
调度优化; 深度强化学习; 容器聚类; 集群; 容器依赖开销
Keywords:
scheduling optimization; deep reinforcement learning; container clustering; cluster; container dependency overhead
分类号:
TP181
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0163
摘要:
工业互联网中存在大量部署于边缘服务器上的在/ 离线容器服务,这些容器服务一方面承载着低延时,高响应的需求,另一方面又具有错综复杂的调用关系。 通常边缘集群的调度策略并未考虑到容器服务之间的依赖关系,这导致具有依赖关系容器服务可能在调度过程中被分散到不同的边缘节点上,并由此产生大量跨节点调用造成额外资源损耗。 针对具有依赖关系的容器,该文提出面向边缘场景的容器组调度优化策略。 首先通过容器聚类算法 CDSC( Container Dependency Spectral Clustering)将有依赖关系的容器划分为一个或多个容器组,使得组内容器依赖强度尽可能的大,组间依赖强度尽可能的小,以减少其进行跨节点调用的频率;再通过引入双深度 Q 网络模型(Double DQN)将容器组作为基本调度单位,以容器依赖开销,集群和节点内部负载为优化目标,根据边缘节点实际情况自适应学习优化调度策略,使其能应对复杂多变的边缘集群情况。 经实验表明,相比于传统的启发式算法和其他深度强化学习算法,该算法在容器服务响应时间、集群和节点负载方面具有明显的优势。
Abstract:
The industrial Internet is populated with a large number of on / offline container services deployed on edge servers. On the one hand,these container services bear the demand for low latency and high response,and on the other hand,they have intricate invocation re-lationships. The usual scheduling strategies for edge clusters do not take into account the dependencies between container services,leading to dependent container services possibly being dispersed across different edge nodes during scheduling,thereby generating a large number of cross-node calls and causing additional resource loss. We propose an optimization strategy for container group scheduling in edge scenarios for containers with dependencies. Firstly,the CDSC (Container Dependency Spectral Clustering) is used to divide dependent containers into one or more container groups,maximizing the dependency strength within groups and minimizing it between groups,to reduce the frequency of cross-node calls. Then,by introducing the Double Deep Q-Network model (Double DQN),the container group is used as the basic scheduling unit,with container dependency overhead,cluster and intra-node load as optimization targets. The strategy adaptively learns and optimizes scheduling strategies according to the actual situation of edge nodes,enabling it to cope with complex and changing edge cluster situations. Experimental results show that compared to traditional heuristic algorithms and deep reinforcement learning algorithms,the proposed algorithm has significant advantages in terms of container service response time,cluster and node load.

相似文献/References:

[1]赵 纯,董小明.基于深度 Q-Learning 的信号灯配时优化研究[J].计算机技术与发展,2021,31(08):198.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 034]
　ZHAO Chun,DONG Xiao-ming.Research on Signal Timing Optimization Based on Deep Q-Learning[J].,2021,31(09):198.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 034]
[2]况立群,冯 利,韩 燮,等.基于双深度 Q 网络的智能决策系统研究[J].计算机技术与发展,2022,32(02):137.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 022]
　KUANG Li-qun,FENG Li,HAN Xie,et al.Research on Intelligent Decision-making System Based on Double Deep Q-Network[J].,2022,32(09):137.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 022]
[3]高文斌,王 睿,王田丰,等.基于深度强化学习的 QoS 感知 Web 服务组合[J].计算机技术与发展,2022,32(06):92.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 016]
　GAO Wen-bin,WANG Rui,WANG Tian-feng,et al.QoS-aware Service Composition Based on Deep Reinforcement Learning[J].,2022,32(09):92.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 016]
[4]詹 御,张郭健,彭麟杰,等.基于 DRL 的 MEC 卸载网络竞争窗口优化[J].计算机技术与发展,2022,32(06):99.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 017]
　ZHAN Yu,ZHANG Guo-jian,PENG Lin-jie,et al.Optimization of Contention Window of MEC Offloading Network Based on DRL[J].,2022,32(09):99.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 017]
[5]牟轩庭,张宏军,廖湘琳,等.规则引导的智能体决策框架[J].计算机技术与发展,2022,32(10):156.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 026]
　MU Xuan-ting,ZHANG Hong-jun,LIAO Xiang-lin,et al.Rule-guided Agent Decision-Making Framework[J].,2022,32(09):156.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 026]
[6]林泽阳,赖 俊,陈希亮.基于课程学习的深度强化学习研究综述[J].计算机技术与发展,2022,32(11):16.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 003]
　LIN Ze-yang,LAI Jun,CHEN Xi-liang.An Overview of Deep Reinforcement Learning Based on Curriculum Learning[J].,2022,32(09):16.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 003]
[7]吕相霖,臧兆祥,李思博,等.基于注意力的循环 PPO 算法及其应用[J].计算机技术与发展,2024,34(01):136.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 020]
　LYU Xiang-lin,ZANG Zhao-xiang,LI Si-bo,et al.Attention-based Recurrent PPO Algorithm and Its Application[J].,2024,34(09):136.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 020]
[8]龚亮亮,张 影,张俊尧,等.基于深度强化学习的任务卸载和资源分配优化[J].计算机技术与发展,2024,34(04):116.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 018]
　GONG Liang-liang,ZHANG Ying,ZHANG Jun-yao,et al.Joint Optimization of Task Offloading and Resource Allocation Based on Deep Reinforcement Learning[J].,2024,34(09):116.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 018]
[9]聂雷,张明萱,黄庆涵,等.基于Double DQN的双模式多目标信号配时方法[J].计算机技术与发展,2024,34(08):143.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0124]
　NIE Lei,ZHANG Ming-xuan,HUANG Qing-han,et al.A Dual-mode Multi-objective Signal Timing Method Based on Double DQN[J].,2024,34(09):143.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0124]
[10]王宇轩,鲍海洲*,喻国荣,等.基于PER-MATD3的任务卸载和资源优化方法[J].计算机技术与发展,2024,34(12):57.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0254]
　WANG Yu-xuan,BAO Hai-zhou*,YU Guo-rong,et al.Task Offloading and Resource Optimization Method Based on PER-MATD3[J].,2024,34(09):57.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0254]

更新日期/Last Update: 2024-09-10