Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable masking
The paper addresses the challenges of task migration and resource allocation in heterogeneous cloud–edge environments, where dynamic and stochastic conditions complicate efficient scheduling. To tackle this, the authors propose a novel scheduling algorithm combining soft actor–critic (SAC) agent wit...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824011724 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524932386750464 |
|---|---|
| author | Yang Wang Juan Chen Zongling Wu Peng Chen Xi Li Junfeng Hao |
| author_facet | Yang Wang Juan Chen Zongling Wu Peng Chen Xi Li Junfeng Hao |
| author_sort | Yang Wang |
| collection | DOAJ |
| description | The paper addresses the challenges of task migration and resource allocation in heterogeneous cloud–edge environments, where dynamic and stochastic conditions complicate efficient scheduling. To tackle this, the authors propose a novel scheduling algorithm combining soft actor–critic (SAC) agent with masked layer and graph convolutional network (GCN), namely MGSAC algorithm. MGSAC utilizes GCN to extract hidden structural features from the environment, enabling better adaptation to dynamic changes. Additionally, a learnable mask layer filters out ineffective actions, refining the selection of scheduling strategies and improving overall performance. By evaluating MGSAC on the real-world Bit-Brain dataset and simulating it using Cloud-Sim, experimental results demonstrate its superiority over existing algorithms in energy consumption, task response time, task migration time, and task Service-Level-Agreement violations rate, showcasing its effectiveness in real-world scenarios. |
| format | Article |
| id | doaj-art-d5623dcc53094d69a1244b0f0bf067c1 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-d5623dcc53094d69a1244b0f0bf067c12025-01-18T05:03:33ZengElsevierAlexandria Engineering Journal1110-01682025-01-01111107122Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable maskingYang Wang0Juan Chen1Zongling Wu2Peng Chen3Xi Li4Junfeng Hao5School of Computer and Software Engineering, XiHua University, Chengdu, 610039, Sichuan, ChinaSchool of Computer and Software Engineering, XiHua University, Chengdu, 610039, Sichuan, China; Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, 300387, Tianjin, China; Corresponding author at: School of Computer and Software Engineering, XiHua University, Chengdu, 610039, Sichuan, China.School of Information Science and Technology, Southwest Jiaotong University, Chengdu, 611756, Sichuan, ChinaSchool of Computer and Software Engineering, XiHua University, Chengdu, 610039, Sichuan, ChinaSchool of Computer and Software Engineering, XiHua University, Chengdu, 610039, Sichuan, ChinaSchool of Computer and Software Engineering, XiHua University, Chengdu, 610039, Sichuan, ChinaThe paper addresses the challenges of task migration and resource allocation in heterogeneous cloud–edge environments, where dynamic and stochastic conditions complicate efficient scheduling. To tackle this, the authors propose a novel scheduling algorithm combining soft actor–critic (SAC) agent with masked layer and graph convolutional network (GCN), namely MGSAC algorithm. MGSAC utilizes GCN to extract hidden structural features from the environment, enabling better adaptation to dynamic changes. Additionally, a learnable mask layer filters out ineffective actions, refining the selection of scheduling strategies and improving overall performance. By evaluating MGSAC on the real-world Bit-Brain dataset and simulating it using Cloud-Sim, experimental results demonstrate its superiority over existing algorithms in energy consumption, task response time, task migration time, and task Service-Level-Agreement violations rate, showcasing its effectiveness in real-world scenarios.http://www.sciencedirect.com/science/article/pii/S1110016824011724Cloud–edge computingDeep reinforcement learningResource allocationTask migration |
| spellingShingle | Yang Wang Juan Chen Zongling Wu Peng Chen Xi Li Junfeng Hao Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable masking Alexandria Engineering Journal Cloud–edge computing Deep reinforcement learning Resource allocation Task migration |
| title | Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable masking |
| title_full | Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable masking |
| title_fullStr | Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable masking |
| title_full_unstemmed | Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable masking |
| title_short | Efficient task migration and resource allocation in cloud–edge collaboration: A DRL approach with learnable masking |
| title_sort | efficient task migration and resource allocation in cloud edge collaboration a drl approach with learnable masking |
| topic | Cloud–edge computing Deep reinforcement learning Resource allocation Task migration |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824011724 |
| work_keys_str_mv | AT yangwang efficienttaskmigrationandresourceallocationincloudedgecollaborationadrlapproachwithlearnablemasking AT juanchen efficienttaskmigrationandresourceallocationincloudedgecollaborationadrlapproachwithlearnablemasking AT zonglingwu efficienttaskmigrationandresourceallocationincloudedgecollaborationadrlapproachwithlearnablemasking AT pengchen efficienttaskmigrationandresourceallocationincloudedgecollaborationadrlapproachwithlearnablemasking AT xili efficienttaskmigrationandresourceallocationincloudedgecollaborationadrlapproachwithlearnablemasking AT junfenghao efficienttaskmigrationandresourceallocationincloudedgecollaborationadrlapproachwithlearnablemasking |