Scheduling framework based on reinforcement learning in online-offline colocated cloud environment
Some reinforcement learning-based scheduling algorithms for cloud computing platforms barely considered one scenario or ignored the resource constraints of jobs and treated all machines as the same type, which caused low resource utilization or insufficient scheduling efficiency.To address the sched...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-06-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023119/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841540062139908096 |
|---|---|
| author | Ling MA Qiliang FAN Ting XU Guanchen GUO Shenglin ZHANG Yongqian SUN Yuzhi ZHANG |
| author_facet | Ling MA Qiliang FAN Ting XU Guanchen GUO Shenglin ZHANG Yongqian SUN Yuzhi ZHANG |
| author_sort | Ling MA |
| collection | DOAJ |
| description | Some reinforcement learning-based scheduling algorithms for cloud computing platforms barely considered one scenario or ignored the resource constraints of jobs and treated all machines as the same type, which caused low resource utilization or insufficient scheduling efficiency.To address the scheduling problems in online-offline colocated cloud environment, a framework named JobFusion was proposed.Firstly, an efficient resource partitioning scheme was built in the cloud computing platform supporting virtualization technology by integrating the hierarchical clustering method with connectivity constraints.Secondly, a graph convolutional neural network was utilized to embed the attributes of elastic dimension with various constraints and the jobs with various numbers, to capture the critical path information of workflow.Finally, existing high-performance reinforcement learning methods were integrated for scheduling jobs.According to the results of evaluation experiments, JobFusion improves the resource utilization by 39.86% and reduces the average job completion time by up to 64.36% compared with baselines. |
| format | Article |
| id | doaj-art-a4d56bdbe644456a9211ed7f0327637e |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-06-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-a4d56bdbe644456a9211ed7f0327637e2025-01-14T06:22:57ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-06-01449010259386365Scheduling framework based on reinforcement learning in online-offline colocated cloud environmentLing MAQiliang FANTing XUGuanchen GUOShenglin ZHANGYongqian SUNYuzhi ZHANGSome reinforcement learning-based scheduling algorithms for cloud computing platforms barely considered one scenario or ignored the resource constraints of jobs and treated all machines as the same type, which caused low resource utilization or insufficient scheduling efficiency.To address the scheduling problems in online-offline colocated cloud environment, a framework named JobFusion was proposed.Firstly, an efficient resource partitioning scheme was built in the cloud computing platform supporting virtualization technology by integrating the hierarchical clustering method with connectivity constraints.Secondly, a graph convolutional neural network was utilized to embed the attributes of elastic dimension with various constraints and the jobs with various numbers, to capture the critical path information of workflow.Finally, existing high-performance reinforcement learning methods were integrated for scheduling jobs.According to the results of evaluation experiments, JobFusion improves the resource utilization by 39.86% and reduces the average job completion time by up to 64.36% compared with baselines.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023119/reinforcement learninggraph embeddinghierarchical clustercloud computingvirtualization |
| spellingShingle | Ling MA Qiliang FAN Ting XU Guanchen GUO Shenglin ZHANG Yongqian SUN Yuzhi ZHANG Scheduling framework based on reinforcement learning in online-offline colocated cloud environment Tongxin xuebao reinforcement learning graph embedding hierarchical cluster cloud computing virtualization |
| title | Scheduling framework based on reinforcement learning in online-offline colocated cloud environment |
| title_full | Scheduling framework based on reinforcement learning in online-offline colocated cloud environment |
| title_fullStr | Scheduling framework based on reinforcement learning in online-offline colocated cloud environment |
| title_full_unstemmed | Scheduling framework based on reinforcement learning in online-offline colocated cloud environment |
| title_short | Scheduling framework based on reinforcement learning in online-offline colocated cloud environment |
| title_sort | scheduling framework based on reinforcement learning in online offline colocated cloud environment |
| topic | reinforcement learning graph embedding hierarchical cluster cloud computing virtualization |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023119/ |
| work_keys_str_mv | AT lingma schedulingframeworkbasedonreinforcementlearninginonlineofflinecolocatedcloudenvironment AT qiliangfan schedulingframeworkbasedonreinforcementlearninginonlineofflinecolocatedcloudenvironment AT tingxu schedulingframeworkbasedonreinforcementlearninginonlineofflinecolocatedcloudenvironment AT guanchenguo schedulingframeworkbasedonreinforcementlearninginonlineofflinecolocatedcloudenvironment AT shenglinzhang schedulingframeworkbasedonreinforcementlearninginonlineofflinecolocatedcloudenvironment AT yongqiansun schedulingframeworkbasedonreinforcementlearninginonlineofflinecolocatedcloudenvironment AT yuzhizhang schedulingframeworkbasedonreinforcementlearninginonlineofflinecolocatedcloudenvironment |