A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G Networks
The use of Reinforcement Learning (RL) techniques has been widely addressed in the literature to cope with capacity sharing in 5G Radio Access Network (RAN) slicing. These algorithms consider a training process to learn an optimal capacity sharing decision-making policy, which is later applied to th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/16/12/434 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846104563213402112 |
|---|---|
| author | Irene Vilà Jordi Pérez-Romero Oriol Sallent |
| author_facet | Irene Vilà Jordi Pérez-Romero Oriol Sallent |
| author_sort | Irene Vilà |
| collection | DOAJ |
| description | The use of Reinforcement Learning (RL) techniques has been widely addressed in the literature to cope with capacity sharing in 5G Radio Access Network (RAN) slicing. These algorithms consider a training process to learn an optimal capacity sharing decision-making policy, which is later applied to the RAN environment during the inference stage. When relevant changes occur in the RAN, such as the deployment of new cells in the network, RL-based capacity sharing solutions require a re-training process to update the optimal decision-making policy, which may require long training times. To accelerate this process, this paper proposes a novel Transfer Learning (TL) approach for RL-based capacity sharing solutions in multi-cell scenarios that is implementable following the Open-RAN (O-RAN) architecture and exploits the availability of computing resources at the edge for conducting the training/inference processes. The proposed approach allows transferring the weights of the previously learned policy to learn the new policy to be used after the addition of new cells. The performance assessment of the TL solution highlights its capability to reduce the training process duration of the policies when adding new cells. Considering that the roll-out of 5G networks will continue for several years, TL can contribute to enhancing the practicality and feasibility of applying RL-based solutions for capacity sharing. |
| format | Article |
| id | doaj-art-53b8e5189f564981b3214e1d0b472bc2 |
| institution | Kabale University |
| issn | 1999-5903 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj-art-53b8e5189f564981b3214e1d0b472bc22024-12-27T14:27:17ZengMDPI AGFuture Internet1999-59032024-11-01161243410.3390/fi16120434A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G NetworksIrene Vilà0Jordi Pérez-Romero1Oriol Sallent2Signal Theory and Communications Department (TSC), Universitat Politècnica de Catalunya (UPC), 08034 Barcelona, SpainSignal Theory and Communications Department (TSC), Universitat Politècnica de Catalunya (UPC), 08034 Barcelona, SpainSignal Theory and Communications Department (TSC), Universitat Politècnica de Catalunya (UPC), 08034 Barcelona, SpainThe use of Reinforcement Learning (RL) techniques has been widely addressed in the literature to cope with capacity sharing in 5G Radio Access Network (RAN) slicing. These algorithms consider a training process to learn an optimal capacity sharing decision-making policy, which is later applied to the RAN environment during the inference stage. When relevant changes occur in the RAN, such as the deployment of new cells in the network, RL-based capacity sharing solutions require a re-training process to update the optimal decision-making policy, which may require long training times. To accelerate this process, this paper proposes a novel Transfer Learning (TL) approach for RL-based capacity sharing solutions in multi-cell scenarios that is implementable following the Open-RAN (O-RAN) architecture and exploits the availability of computing resources at the edge for conducting the training/inference processes. The proposed approach allows transferring the weights of the previously learned policy to learn the new policy to be used after the addition of new cells. The performance assessment of the TL solution highlights its capability to reduce the training process duration of the policies when adding new cells. Considering that the roll-out of 5G networks will continue for several years, TL can contribute to enhancing the practicality and feasibility of applying RL-based solutions for capacity sharing.https://www.mdpi.com/1999-5903/16/12/434RAN slicingcapacity sharingreinforcement learningtransfer learningtransfer reinforcement learning |
| spellingShingle | Irene Vilà Jordi Pérez-Romero Oriol Sallent A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G Networks Future Internet RAN slicing capacity sharing reinforcement learning transfer learning transfer reinforcement learning |
| title | A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G Networks |
| title_full | A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G Networks |
| title_fullStr | A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G Networks |
| title_full_unstemmed | A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G Networks |
| title_short | A Transfer Reinforcement Learning Approach for Capacity Sharing in Beyond 5G Networks |
| title_sort | transfer reinforcement learning approach for capacity sharing in beyond 5g networks |
| topic | RAN slicing capacity sharing reinforcement learning transfer learning transfer reinforcement learning |
| url | https://www.mdpi.com/1999-5903/16/12/434 |
| work_keys_str_mv | AT irenevila atransferreinforcementlearningapproachforcapacitysharinginbeyond5gnetworks AT jordiperezromero atransferreinforcementlearningapproachforcapacitysharinginbeyond5gnetworks AT oriolsallent atransferreinforcementlearningapproachforcapacitysharinginbeyond5gnetworks AT irenevila transferreinforcementlearningapproachforcapacitysharinginbeyond5gnetworks AT jordiperezromero transferreinforcementlearningapproachforcapacitysharinginbeyond5gnetworks AT oriolsallent transferreinforcementlearningapproachforcapacitysharinginbeyond5gnetworks |