Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement Learning
This article presents a learning-based interference management mechanism for multiple unmanned aerial vehicles mounted small cells (ASCs), called HAPPIER, standing for <underline>h</underline>ybrid <underline>a</underline>ffinity <underline>p</underline>ro<unde...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Open Journal of Vehicular Technology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9537620/ |
| _version_ | 1819129746521325568 |
|---|---|
| author | Shao-Hung Cheng Jia-Ling Liu Li-Chun Wang |
| author_facet | Shao-Hung Cheng Jia-Ling Liu Li-Chun Wang |
| author_sort | Shao-Hung Cheng |
| collection | DOAJ |
| description | This article presents a learning-based interference management mechanism for multiple unmanned aerial vehicles mounted small cells (ASCs), called HAPPIER, standing for <underline>h</underline>ybrid <underline>a</underline>ffinity <underline>p</underline>ro<underline>p</underline>agation cluster<underline>i</underline>ng (APC) and r<underline>e</underline>inforcement lea<underline>r</underline>ning (RL) power control. The proposed HAPPIER interference management mechanism consists of two main algorithms: APC and RL. First, from the macroscopic viewpoint, the APC explores the interference structure of multiple ASCs and then changes the most serious interfering ASCs into sleeping mode. As such, we can shift the complicated interference structure into the one with fewer interfering sources and thus speed up the learning process of interference management. Secondly, from the microscopic viewpoint, based on the interference structure suggested by HAPPIER, the RL is applied to adjust the transmission power of active ASCs to optimize the total throughput further. HAPPIER can achieve the optimal trade-off between system throughput and complexity. From our numerical results, subject to the same complexity constraint, our proposed HAPPIER outperforms all the existing approaches and can achieve 93% of the system throughput of the exhaustive searching algorithm. |
| first_indexed | 2024-12-22T08:48:37Z |
| format | Article |
| id | doaj.art-cc0d57ccf2a04e778b058fa4a2b0e115 |
| institution | Directory Open Access Journal |
| issn | 2644-1330 |
| language | English |
| last_indexed | 2024-12-22T08:48:37Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Vehicular Technology |
| spelling | doaj.art-cc0d57ccf2a04e778b058fa4a2b0e1152022-12-21T18:32:02ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302021-01-01241241810.1109/OJVT.2021.31124689537620Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement LearningShao-Hung Cheng0https://orcid.org/0000-0001-6013-1676Jia-Ling Liu1Li-Chun Wang2https://orcid.org/0000-0002-7883-6217Department of Electrical and Electronic Engineering, Chung Cheng Institute of Technology, National Defense University, Taoyuan, TaiwanDepartment of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, TaiwanDepartment of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, TaiwanThis article presents a learning-based interference management mechanism for multiple unmanned aerial vehicles mounted small cells (ASCs), called HAPPIER, standing for <underline>h</underline>ybrid <underline>a</underline>ffinity <underline>p</underline>ro<underline>p</underline>agation cluster<underline>i</underline>ng (APC) and r<underline>e</underline>inforcement lea<underline>r</underline>ning (RL) power control. The proposed HAPPIER interference management mechanism consists of two main algorithms: APC and RL. First, from the macroscopic viewpoint, the APC explores the interference structure of multiple ASCs and then changes the most serious interfering ASCs into sleeping mode. As such, we can shift the complicated interference structure into the one with fewer interfering sources and thus speed up the learning process of interference management. Secondly, from the microscopic viewpoint, based on the interference structure suggested by HAPPIER, the RL is applied to adjust the transmission power of active ASCs to optimize the total throughput further. HAPPIER can achieve the optimal trade-off between system throughput and complexity. From our numerical results, subject to the same complexity constraint, our proposed HAPPIER outperforms all the existing approaches and can achieve 93% of the system throughput of the exhaustive searching algorithm.https://ieeexplore.ieee.org/document/9537620/Aerial small cellsaffinity propagation clusteringreinforcement learninginterference mitigationpower control |
| spellingShingle | Shao-Hung Cheng Jia-Ling Liu Li-Chun Wang Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement Learning IEEE Open Journal of Vehicular Technology Aerial small cells affinity propagation clustering reinforcement learning interference mitigation power control |
| title | Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement Learning |
| title_full | Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement Learning |
| title_fullStr | Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement Learning |
| title_full_unstemmed | Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement Learning |
| title_short | Controlling Interference Structure and Transmit Power of Aerial Small Cells by Hybrid Affinity Propagation Clustering and Reinforcement Learning |
| title_sort | controlling interference structure and transmit power of aerial small cells by hybrid affinity propagation clustering and reinforcement learning |
| topic | Aerial small cells affinity propagation clustering reinforcement learning interference mitigation power control |
| url | https://ieeexplore.ieee.org/document/9537620/ |
| work_keys_str_mv | AT shaohungcheng controllinginterferencestructureandtransmitpowerofaerialsmallcellsbyhybridaffinitypropagationclusteringandreinforcementlearning AT jialingliu controllinginterferencestructureandtransmitpowerofaerialsmallcellsbyhybridaffinitypropagationclusteringandreinforcementlearning AT lichunwang controllinginterferencestructureandtransmitpowerofaerialsmallcellsbyhybridaffinitypropagationclusteringandreinforcementlearning |