A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation
The existing research on dependent task offloading and resource allocation assumes that edge servers can provide computational and communication resources free of charge. This paper proposes a two-stage resource allocation method to address this issue. In the first stage, users incentivize edge serv...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/15/12/395 |
| _version_ | 1827574758511738880 |
|---|---|
| author | Zuopeng Li Hengshuai Ju Zepeng Ren |
| author_facet | Zuopeng Li Hengshuai Ju Zepeng Ren |
| author_sort | Zuopeng Li |
| collection | DOAJ |
| description | The existing research on dependent task offloading and resource allocation assumes that edge servers can provide computational and communication resources free of charge. This paper proposes a two-stage resource allocation method to address this issue. In the first stage, users incentivize edge servers to provide resources. We formulate the incentive problem in this stage as a multivariate Stackelberg game, which takes into account both computational and communication resources. In addition, we also analyze the uniqueness of the Stackelberg equilibrium under information sharing conditions. Considering the privacy issues of the participants, the research is extended to scenarios without information sharing, where the multivariable game problem is modeled as a partially observable Markov decision process (POMDP). In order to obtain the optimal incentive decision in this scenario, a reinforcement learning algorithm based on the learning game is designed. In the second stage, we propose a greedy-based deep reinforcement learning algorithm that is aimed at minimizing task execution time by optimizing resource and task allocation strategies. Finally, the simulation results demonstrate that the algorithm designed for non-information sharing scenarios can effectively approximate the theoretical Stackelberg equilibrium, and its performance is found to be better than that of the other three benchmark methods. After the allocation of resources and sub-tasks by the greedy-based deep reinforcement learning algorithm, the execution delay of the dependent task is significantly lower than that in local processing. |
| first_indexed | 2024-03-08T20:44:41Z |
| format | Article |
| id | doaj.art-4f5986d06caa44fc909b5ec57ab2504b |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-03-08T20:44:41Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-4f5986d06caa44fc909b5ec57ab2504b2023-12-22T14:10:12ZengMDPI AGFuture Internet1999-59032023-12-01151239510.3390/fi15120395A Learning Game-Based Approach to Task-Dependent Edge Resource AllocationZuopeng Li0Hengshuai Ju1Zepeng Ren2School of Information and Electrical Engineering, Hebei University of Engineering, Handan 056038, ChinaSchool of Information and Electrical Engineering, Hebei University of Engineering, Handan 056038, ChinaSchool of Information and Electrical Engineering, Hebei University of Engineering, Handan 056038, ChinaThe existing research on dependent task offloading and resource allocation assumes that edge servers can provide computational and communication resources free of charge. This paper proposes a two-stage resource allocation method to address this issue. In the first stage, users incentivize edge servers to provide resources. We formulate the incentive problem in this stage as a multivariate Stackelberg game, which takes into account both computational and communication resources. In addition, we also analyze the uniqueness of the Stackelberg equilibrium under information sharing conditions. Considering the privacy issues of the participants, the research is extended to scenarios without information sharing, where the multivariable game problem is modeled as a partially observable Markov decision process (POMDP). In order to obtain the optimal incentive decision in this scenario, a reinforcement learning algorithm based on the learning game is designed. In the second stage, we propose a greedy-based deep reinforcement learning algorithm that is aimed at minimizing task execution time by optimizing resource and task allocation strategies. Finally, the simulation results demonstrate that the algorithm designed for non-information sharing scenarios can effectively approximate the theoretical Stackelberg equilibrium, and its performance is found to be better than that of the other three benchmark methods. After the allocation of resources and sub-tasks by the greedy-based deep reinforcement learning algorithm, the execution delay of the dependent task is significantly lower than that in local processing.https://www.mdpi.com/1999-5903/15/12/395edge computingStackelberg gamedeep reinforcement learningdependent taskresource allocation |
| spellingShingle | Zuopeng Li Hengshuai Ju Zepeng Ren A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation Future Internet edge computing Stackelberg game deep reinforcement learning dependent task resource allocation |
| title | A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation |
| title_full | A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation |
| title_fullStr | A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation |
| title_full_unstemmed | A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation |
| title_short | A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation |
| title_sort | learning game based approach to task dependent edge resource allocation |
| topic | edge computing Stackelberg game deep reinforcement learning dependent task resource allocation |
| url | https://www.mdpi.com/1999-5903/15/12/395 |
| work_keys_str_mv | AT zuopengli alearninggamebasedapproachtotaskdependentedgeresourceallocation AT hengshuaiju alearninggamebasedapproachtotaskdependentedgeresourceallocation AT zepengren alearninggamebasedapproachtotaskdependentedgeresourceallocation AT zuopengli learninggamebasedapproachtotaskdependentedgeresourceallocation AT hengshuaiju learninggamebasedapproachtotaskdependentedgeresourceallocation AT zepengren learninggamebasedapproachtotaskdependentedgeresourceallocation |