A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach
Abstract Vehicular edge computing (VEC) is emerging as a new computing paradigm to improve the quality of vehicular services and enhance the capabilities of vehicles. It enables performing tasks with low latency by deploying computing and storage resources close to vehicles. However, the traditional...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-10-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-022-00340-3 |
| _version_ | 1811336283610415104 |
|---|---|
| author | Guozhi Liu Fei Dai Bi Huang Zhenping Qiang Shuai Wang Lecheng Li |
| author_facet | Guozhi Liu Fei Dai Bi Huang Zhenping Qiang Shuai Wang Lecheng Li |
| author_sort | Guozhi Liu |
| collection | DOAJ |
| description | Abstract Vehicular edge computing (VEC) is emerging as a new computing paradigm to improve the quality of vehicular services and enhance the capabilities of vehicles. It enables performing tasks with low latency by deploying computing and storage resources close to vehicles. However, the traditional task offloading schemes only focus on one-shot offloading, taking less into consideration task dependency. Furthermore, the continuous action space problem during task offloading should be considered. In this paper, an efficient dependency-aware task offloading scheme for VEC with vehicle-edge-cloud collaborative computation is proposed, where subtasks can be processed locally or can be offloaded to an edge server, or a cloud server for execution. Specifically, first, the directed acyclic graph (DAG) is utilized to model the dependency of subtasks. Second, a task offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) was proposed to obtain the optimal offloading strategy in a vehicle-edge-cloud environment, which efficiently solves the continuous control problem and helps reach fast convergence. Finally, extensive simulation experiments have been conducted, and the experimental results show that the proposed scheme can improve performance by about 13.62% on average against three baselines. |
| first_indexed | 2024-04-13T17:37:12Z |
| format | Article |
| id | doaj.art-ab464975cc60408db5cd4763131a8e68 |
| institution | Directory Open Access Journal |
| issn | 2192-113X |
| language | English |
| last_indexed | 2024-04-13T17:37:12Z |
| publishDate | 2022-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj.art-ab464975cc60408db5cd4763131a8e682022-12-22T02:37:19ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2022-10-0111111510.1186/s13677-022-00340-3A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approachGuozhi Liu0Fei Dai1Bi Huang2Zhenping Qiang3Shuai Wang4Lecheng Li5School of Big Data and Intelligent Engineering, Southwest Forestry UniversitySchool of Big Data and Intelligent Engineering, Southwest Forestry UniversitySchool of Big Data and Intelligent Engineering, Southwest Forestry UniversitySchool of Big Data and Intelligent Engineering, Southwest Forestry UniversitySchool of Big Data and Intelligent Engineering, Southwest Forestry UniversitySchool of Big Data and Intelligent Engineering, Southwest Forestry UniversityAbstract Vehicular edge computing (VEC) is emerging as a new computing paradigm to improve the quality of vehicular services and enhance the capabilities of vehicles. It enables performing tasks with low latency by deploying computing and storage resources close to vehicles. However, the traditional task offloading schemes only focus on one-shot offloading, taking less into consideration task dependency. Furthermore, the continuous action space problem during task offloading should be considered. In this paper, an efficient dependency-aware task offloading scheme for VEC with vehicle-edge-cloud collaborative computation is proposed, where subtasks can be processed locally or can be offloaded to an edge server, or a cloud server for execution. Specifically, first, the directed acyclic graph (DAG) is utilized to model the dependency of subtasks. Second, a task offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) was proposed to obtain the optimal offloading strategy in a vehicle-edge-cloud environment, which efficiently solves the continuous control problem and helps reach fast convergence. Finally, extensive simulation experiments have been conducted, and the experimental results show that the proposed scheme can improve performance by about 13.62% on average against three baselines.https://doi.org/10.1186/s13677-022-00340-3Task offloadingTask dependencyVehicular edge computingVehicle-edge-cloud collaborative computingDeep deterministic policy gradientDeep reinforcement learning |
| spellingShingle | Guozhi Liu Fei Dai Bi Huang Zhenping Qiang Shuai Wang Lecheng Li A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach Journal of Cloud Computing: Advances, Systems and Applications Task offloading Task dependency Vehicular edge computing Vehicle-edge-cloud collaborative computing Deep deterministic policy gradient Deep reinforcement learning |
| title | A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach |
| title_full | A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach |
| title_fullStr | A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach |
| title_full_unstemmed | A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach |
| title_short | A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach |
| title_sort | collaborative computation and dependency aware task offloading method for vehicular edge computing a reinforcement learning approach |
| topic | Task offloading Task dependency Vehicular edge computing Vehicle-edge-cloud collaborative computing Deep deterministic policy gradient Deep reinforcement learning |
| url | https://doi.org/10.1186/s13677-022-00340-3 |
| work_keys_str_mv | AT guozhiliu acollaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT feidai acollaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT bihuang acollaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT zhenpingqiang acollaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT shuaiwang acollaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT lechengli acollaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT guozhiliu collaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT feidai collaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT bihuang collaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT zhenpingqiang collaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT shuaiwang collaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach AT lechengli collaborativecomputationanddependencyawaretaskoffloadingmethodforvehicularedgecomputingareinforcementlearningapproach |