AI based power allocation for NOMA
Novel methods using artificial intelligence for downlink power allocation problem in non-orthogonal multiple access networks are presented. The proposed machine learning and deep learning based methods achieved performance close to the optimum in terms of sum capacity with significantly lower comput...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Springer
2022
|
| _version_ | 1825938317848346624 |
|---|---|
| author | Manglayev, Talgat Kizilirmak, Refik Caglar Kho, Yau Hee Abdul Hamid, Nor Asilah Wati Tian, Yue |
| author_facet | Manglayev, Talgat Kizilirmak, Refik Caglar Kho, Yau Hee Abdul Hamid, Nor Asilah Wati Tian, Yue |
| author_sort | Manglayev, Talgat |
| collection | UPM |
| description | Novel methods using artificial intelligence for downlink power allocation problem in non-orthogonal multiple access networks are presented. The proposed machine learning and deep learning based methods achieved performance close to the optimum in terms of sum capacity with significantly lower computational costs. The numerical results also demonstrated up to 120 times a boost in computation time as compared to the conventional exhaustive search approach. Furthermore, the training and testing accuracy of the deep learning model reached 0.92 and 0.93 with the loss value dropping up to 0.002. |
| first_indexed | 2024-09-25T03:36:09Z |
| format | Article |
| id | upm.eprints-100156 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-09-25T03:36:09Z |
| publishDate | 2022 |
| publisher | Springer |
| record_format | dspace |
| spelling | upm.eprints-1001562024-07-17T04:18:52Z http://psasir.upm.edu.my/id/eprint/100156/ AI based power allocation for NOMA Manglayev, Talgat Kizilirmak, Refik Caglar Kho, Yau Hee Abdul Hamid, Nor Asilah Wati Tian, Yue Novel methods using artificial intelligence for downlink power allocation problem in non-orthogonal multiple access networks are presented. The proposed machine learning and deep learning based methods achieved performance close to the optimum in terms of sum capacity with significantly lower computational costs. The numerical results also demonstrated up to 120 times a boost in computation time as compared to the conventional exhaustive search approach. Furthermore, the training and testing accuracy of the deep learning model reached 0.92 and 0.93 with the loss value dropping up to 0.002. Springer 2022-01-27 Article PeerReviewed Manglayev, Talgat and Kizilirmak, Refik Caglar and Kho, Yau Hee and Abdul Hamid, Nor Asilah Wati and Tian, Yue (2022) AI based power allocation for NOMA. Wireless Personal Communications, 124. pp. 3253-3261. ISSN 0929-6212; ESSN: 0929-6212 https://link.springer.com/article/10.1007/s11277-022-09511-6 10.1007/s11277-022-09511-6 |
| spellingShingle | Manglayev, Talgat Kizilirmak, Refik Caglar Kho, Yau Hee Abdul Hamid, Nor Asilah Wati Tian, Yue AI based power allocation for NOMA |
| title | AI based power allocation for NOMA |
| title_full | AI based power allocation for NOMA |
| title_fullStr | AI based power allocation for NOMA |
| title_full_unstemmed | AI based power allocation for NOMA |
| title_short | AI based power allocation for NOMA |
| title_sort | ai based power allocation for noma |
| work_keys_str_mv | AT manglayevtalgat aibasedpowerallocationfornoma AT kizilirmakrefikcaglar aibasedpowerallocationfornoma AT khoyauhee aibasedpowerallocationfornoma AT abdulhamidnorasilahwati aibasedpowerallocationfornoma AT tianyue aibasedpowerallocationfornoma |