HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learning
Abstract Aerial base stations (AeBSs), as crucial components of air-ground integrated networks, are widely employed in cloud computing, disaster relief, and various applications. How to quickly and efficiently deploy multi-AeBSs for higher capacity gain has become a key research issue. In this paper...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-09-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-023-00512-9 |
| _version_ | 1797451473495261184 |
|---|---|
| author | Lei Liu Haoran He Fei Qi Yikun Zhao Weiliang Xie Fanqin Zhou Lei Feng |
| author_facet | Lei Liu Haoran He Fei Qi Yikun Zhao Weiliang Xie Fanqin Zhou Lei Feng |
| author_sort | Lei Liu |
| collection | DOAJ |
| description | Abstract Aerial base stations (AeBSs), as crucial components of air-ground integrated networks, are widely employed in cloud computing, disaster relief, and various applications. How to quickly and efficiently deploy multi-AeBSs for higher capacity gain has become a key research issue. In this paper, we address the 3D deployment optimization problem of multi-AeBSs with the objective of maximizing system capacity. To overcome communication overhead and privacy challenges in multi-agent deep reinforcement learning (MADRL), we propose a federated deep deterministic policy gradient (Fed-DDPG) algorithm for the multi-AeBS deployment decision. Specifically, a high-altitude platform (HAP)-assisted multi-AeBS deployment architecture is designed, in which low-altitude AeBS act as the local nodes to train its own deployment decision model, while the HAP acts as the global node to aggregate the weights of local models. In this architecture, AeBSs do not exchange raw data, addressing data privacy concerns and reducing communication overhead. Simulation results show that the proposed algorithm outperforms fully distributed MADRL algorithms and closely approximates the performance of multi-agent deep deterministic policy gradient (MADDPG), which requires global information during training, but with less training time. |
| first_indexed | 2024-03-09T14:55:10Z |
| format | Article |
| id | doaj.art-5e08997bfd5e45f090b81b8be2acaee3 |
| institution | Directory Open Access Journal |
| issn | 2192-113X |
| language | English |
| last_indexed | 2024-03-09T14:55:10Z |
| publishDate | 2023-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj.art-5e08997bfd5e45f090b81b8be2acaee32023-11-26T14:14:56ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2023-09-0112111310.1186/s13677-023-00512-9HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learningLei Liu0Haoran He1Fei Qi2Yikun Zhao3Weiliang Xie4Fanqin Zhou5Lei Feng6Beijing Research Institute, China Telecom Corporation LimitedState Key Laboratory of Networking and Switching Technology, Beijing University of Posts and TelecommunicationsBeijing Research Institute, China Telecom Corporation LimitedState Key Laboratory of Networking and Switching Technology, Beijing University of Posts and TelecommunicationsBeijing Research Institute, China Telecom Corporation LimitedState Key Laboratory of Networking and Switching Technology, Beijing University of Posts and TelecommunicationsState Key Laboratory of Networking and Switching Technology, Beijing University of Posts and TelecommunicationsAbstract Aerial base stations (AeBSs), as crucial components of air-ground integrated networks, are widely employed in cloud computing, disaster relief, and various applications. How to quickly and efficiently deploy multi-AeBSs for higher capacity gain has become a key research issue. In this paper, we address the 3D deployment optimization problem of multi-AeBSs with the objective of maximizing system capacity. To overcome communication overhead and privacy challenges in multi-agent deep reinforcement learning (MADRL), we propose a federated deep deterministic policy gradient (Fed-DDPG) algorithm for the multi-AeBS deployment decision. Specifically, a high-altitude platform (HAP)-assisted multi-AeBS deployment architecture is designed, in which low-altitude AeBS act as the local nodes to train its own deployment decision model, while the HAP acts as the global node to aggregate the weights of local models. In this architecture, AeBSs do not exchange raw data, addressing data privacy concerns and reducing communication overhead. Simulation results show that the proposed algorithm outperforms fully distributed MADRL algorithms and closely approximates the performance of multi-agent deep deterministic policy gradient (MADDPG), which requires global information during training, but with less training time.https://doi.org/10.1186/s13677-023-00512-9Aerial base station (AeBS)Capacity enhancementDeep reinforcement learning (DRL)Federated reinforcement learning |
| spellingShingle | Lei Liu Haoran He Fei Qi Yikun Zhao Weiliang Xie Fanqin Zhou Lei Feng HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learning Journal of Cloud Computing: Advances, Systems and Applications Aerial base station (AeBS) Capacity enhancement Deep reinforcement learning (DRL) Federated reinforcement learning |
| title | HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learning |
| title_full | HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learning |
| title_fullStr | HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learning |
| title_full_unstemmed | HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learning |
| title_short | HAP-assisted multi-aerial base station deployment for capacity enhancement via federated deep reinforcement learning |
| title_sort | hap assisted multi aerial base station deployment for capacity enhancement via federated deep reinforcement learning |
| topic | Aerial base station (AeBS) Capacity enhancement Deep reinforcement learning (DRL) Federated reinforcement learning |
| url | https://doi.org/10.1186/s13677-023-00512-9 |
| work_keys_str_mv | AT leiliu hapassistedmultiaerialbasestationdeploymentforcapacityenhancementviafederateddeepreinforcementlearning AT haoranhe hapassistedmultiaerialbasestationdeploymentforcapacityenhancementviafederateddeepreinforcementlearning AT feiqi hapassistedmultiaerialbasestationdeploymentforcapacityenhancementviafederateddeepreinforcementlearning AT yikunzhao hapassistedmultiaerialbasestationdeploymentforcapacityenhancementviafederateddeepreinforcementlearning AT weiliangxie hapassistedmultiaerialbasestationdeploymentforcapacityenhancementviafederateddeepreinforcementlearning AT fanqinzhou hapassistedmultiaerialbasestationdeploymentforcapacityenhancementviafederateddeepreinforcementlearning AT leifeng hapassistedmultiaerialbasestationdeploymentforcapacityenhancementviafederateddeepreinforcementlearning |