Deep Q-Learning-Based Resource Allocation in NOMA Visible Light Communications
Visible light communication (VLC) has been introduced as a key enabler for high-data rate wireless services in future wireless communication networks. In addition to this, it was also demonstrated recently that non-orthogonal multiple access (NOMA) can further improve the spectral efficiency of mult...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9946301/ |
| _version_ | 1811321485876264960 |
|---|---|
| author | Ahmed Al hammadi Lina Bariah Sami Muhaidat Mahmoud Al-Qutayri Paschalis C. Sofotasios Merouane Debbah |
| author_facet | Ahmed Al hammadi Lina Bariah Sami Muhaidat Mahmoud Al-Qutayri Paschalis C. Sofotasios Merouane Debbah |
| author_sort | Ahmed Al hammadi |
| collection | DOAJ |
| description | Visible light communication (VLC) has been introduced as a key enabler for high-data rate wireless services in future wireless communication networks. In addition to this, it was also demonstrated recently that non-orthogonal multiple access (NOMA) can further improve the spectral efficiency of multi-user VLC systems. In this context and owing to the significantly promising potential of artificial intelligence in wireless communications, the present contribution proposes a deep Q-learning (DQL) framework that aims to optimize the performance of an indoor NOMA-VLC downlink network. In particular, we formulate a joint power allocation and LED transmission angle tuning optimization problem, in order to maximize the average sum rate and the average energy efficiency. The obtained results demonstrate that our algorithm offers a noticeable performance enhancement into the NOMA-VLC systems in terms of average sum rate and average energy efficiency, while maintaining the minimum convergence time, particularly for higher number of users. Furthermore, considering a realistic downlink VLC network setup, the simulation results have shown that our algorithm outperforms the genetic algorithm (GA) and the differential evolution (DE) algorithm in terms of average sum rate, and offers considerably less run-time complexity. |
| first_indexed | 2024-04-13T13:17:36Z |
| format | Article |
| id | doaj.art-a2f30adb8f0846479be876d061d143f6 |
| institution | Directory Open Access Journal |
| issn | 2644-125X |
| language | English |
| last_indexed | 2024-04-13T13:17:36Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj.art-a2f30adb8f0846479be876d061d143f62022-12-22T02:45:24ZengIEEEIEEE Open Journal of the Communications Society2644-125X2022-01-0132284229710.1109/OJCOMS.2022.32190149946301Deep Q-Learning-Based Resource Allocation in NOMA Visible Light CommunicationsAhmed Al hammadi0Lina Bariah1https://orcid.org/0000-0001-7244-1663Sami Muhaidat2https://orcid.org/0000-0003-4649-9399Mahmoud Al-Qutayri3https://orcid.org/0000-0002-9600-8036Paschalis C. Sofotasios4https://orcid.org/0000-0001-8389-0966Merouane Debbah5Department of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, UAETechnology Innovation Institute, Abu Dhabi, UAEDepartment of Electrical Engineering and Computer Science, Center for Cyber-Physical Systems, Khalifa University, Abu Dhabi, UAEDepartment of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, UAEDepartment of Electrical Engineering and Computer Science, Center for Cyber-Physical Systems, Khalifa University, Abu Dhabi, UAETechnology Innovation Institute, Abu Dhabi, UAEVisible light communication (VLC) has been introduced as a key enabler for high-data rate wireless services in future wireless communication networks. In addition to this, it was also demonstrated recently that non-orthogonal multiple access (NOMA) can further improve the spectral efficiency of multi-user VLC systems. In this context and owing to the significantly promising potential of artificial intelligence in wireless communications, the present contribution proposes a deep Q-learning (DQL) framework that aims to optimize the performance of an indoor NOMA-VLC downlink network. In particular, we formulate a joint power allocation and LED transmission angle tuning optimization problem, in order to maximize the average sum rate and the average energy efficiency. The obtained results demonstrate that our algorithm offers a noticeable performance enhancement into the NOMA-VLC systems in terms of average sum rate and average energy efficiency, while maintaining the minimum convergence time, particularly for higher number of users. Furthermore, considering a realistic downlink VLC network setup, the simulation results have shown that our algorithm outperforms the genetic algorithm (GA) and the differential evolution (DE) algorithm in terms of average sum rate, and offers considerably less run-time complexity.https://ieeexplore.ieee.org/document/9946301/Deep reinforcement learningmultiple accessresource allocationsum-ratevisible light communications |
| spellingShingle | Ahmed Al hammadi Lina Bariah Sami Muhaidat Mahmoud Al-Qutayri Paschalis C. Sofotasios Merouane Debbah Deep Q-Learning-Based Resource Allocation in NOMA Visible Light Communications IEEE Open Journal of the Communications Society Deep reinforcement learning multiple access resource allocation sum-rate visible light communications |
| title | Deep Q-Learning-Based Resource Allocation in NOMA Visible Light Communications |
| title_full | Deep Q-Learning-Based Resource Allocation in NOMA Visible Light Communications |
| title_fullStr | Deep Q-Learning-Based Resource Allocation in NOMA Visible Light Communications |
| title_full_unstemmed | Deep Q-Learning-Based Resource Allocation in NOMA Visible Light Communications |
| title_short | Deep Q-Learning-Based Resource Allocation in NOMA Visible Light Communications |
| title_sort | deep q learning based resource allocation in noma visible light communications |
| topic | Deep reinforcement learning multiple access resource allocation sum-rate visible light communications |
| url | https://ieeexplore.ieee.org/document/9946301/ |
| work_keys_str_mv | AT ahmedalhammadi deepqlearningbasedresourceallocationinnomavisiblelightcommunications AT linabariah deepqlearningbasedresourceallocationinnomavisiblelightcommunications AT samimuhaidat deepqlearningbasedresourceallocationinnomavisiblelightcommunications AT mahmoudalqutayri deepqlearningbasedresourceallocationinnomavisiblelightcommunications AT paschaliscsofotasios deepqlearningbasedresourceallocationinnomavisiblelightcommunications AT merouanedebbah deepqlearningbasedresourceallocationinnomavisiblelightcommunications |