Task Scheduling Based on Adaptive Priority Experience Replay on Cloud Platforms
Task scheduling algorithms based on reinforce learning (RL) have been important methods with which to improve the performance of cloud platforms; however, due to the dynamics and complexity of the cloud environment, the action space has a very high dimension. This not only makes agent training diffi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/6/1358 |
| _version_ | 1797612168700493824 |
|---|---|
| author | Cuixia Li Wenlong Gao Li Shi Zhiquan Shang Shuyan Zhang |
| author_facet | Cuixia Li Wenlong Gao Li Shi Zhiquan Shang Shuyan Zhang |
| author_sort | Cuixia Li |
| collection | DOAJ |
| description | Task scheduling algorithms based on reinforce learning (RL) have been important methods with which to improve the performance of cloud platforms; however, due to the dynamics and complexity of the cloud environment, the action space has a very high dimension. This not only makes agent training difficult but also affects scheduling performance. In order to guide an agent’s behavior and reduce the number of episodes by using historical records, a task scheduling algorithm based on adaptive priority experience replay (APER) is proposed. APER uses performance metrics as scheduling and sampling optimization objectives with which to improve network accuracy. Combined with prioritized experience replay (PER), an agent can decide how to use experiences. Moreover, this algorithm also considers whether a subtask is executed in a workflow to improve scheduling efficiency. Experimental results on Tpc-h, Alibaba cluster data, and scientific workflows show that a model with APER has significant benefits in terms of convergence and performance. |
| first_indexed | 2024-03-11T06:38:29Z |
| format | Article |
| id | doaj.art-10777014cc8849c19862bd5f10183f10 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T06:38:29Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-10777014cc8849c19862bd5f10183f102023-11-17T10:44:24ZengMDPI AGElectronics2079-92922023-03-01126135810.3390/electronics12061358Task Scheduling Based on Adaptive Priority Experience Replay on Cloud PlatformsCuixia Li0Wenlong Gao1Li Shi2Zhiquan Shang3Shuyan Zhang4School of Electrical Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Electrical Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, ChinaTask scheduling algorithms based on reinforce learning (RL) have been important methods with which to improve the performance of cloud platforms; however, due to the dynamics and complexity of the cloud environment, the action space has a very high dimension. This not only makes agent training difficult but also affects scheduling performance. In order to guide an agent’s behavior and reduce the number of episodes by using historical records, a task scheduling algorithm based on adaptive priority experience replay (APER) is proposed. APER uses performance metrics as scheduling and sampling optimization objectives with which to improve network accuracy. Combined with prioritized experience replay (PER), an agent can decide how to use experiences. Moreover, this algorithm also considers whether a subtask is executed in a workflow to improve scheduling efficiency. Experimental results on Tpc-h, Alibaba cluster data, and scientific workflows show that a model with APER has significant benefits in terms of convergence and performance.https://www.mdpi.com/2079-9292/12/6/1358reinforce learningadaptive priority experience replay (APER)task schedulingcloud platform |
| spellingShingle | Cuixia Li Wenlong Gao Li Shi Zhiquan Shang Shuyan Zhang Task Scheduling Based on Adaptive Priority Experience Replay on Cloud Platforms Electronics reinforce learning adaptive priority experience replay (APER) task scheduling cloud platform |
| title | Task Scheduling Based on Adaptive Priority Experience Replay on Cloud Platforms |
| title_full | Task Scheduling Based on Adaptive Priority Experience Replay on Cloud Platforms |
| title_fullStr | Task Scheduling Based on Adaptive Priority Experience Replay on Cloud Platforms |
| title_full_unstemmed | Task Scheduling Based on Adaptive Priority Experience Replay on Cloud Platforms |
| title_short | Task Scheduling Based on Adaptive Priority Experience Replay on Cloud Platforms |
| title_sort | task scheduling based on adaptive priority experience replay on cloud platforms |
| topic | reinforce learning adaptive priority experience replay (APER) task scheduling cloud platform |
| url | https://www.mdpi.com/2079-9292/12/6/1358 |
| work_keys_str_mv | AT cuixiali taskschedulingbasedonadaptivepriorityexperiencereplayoncloudplatforms AT wenlonggao taskschedulingbasedonadaptivepriorityexperiencereplayoncloudplatforms AT lishi taskschedulingbasedonadaptivepriorityexperiencereplayoncloudplatforms AT zhiquanshang taskschedulingbasedonadaptivepriorityexperiencereplayoncloudplatforms AT shuyanzhang taskschedulingbasedonadaptivepriorityexperiencereplayoncloudplatforms |