Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO Systems
Cell-free massive multiple-input multiple-output (CF-mMIMO) has been considered as one of the potential technologies for beyond-5G and 6G to meet the demand for higher data capacity and uniform service rate for user equipment. However, reusing the same pilot signals by several users, owing to limite...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9950058/ |
| _version_ | 1811189144018223104 |
|---|---|
| author | Mostafa Rahmani Mohammad Javad Dehghani Pei Xiao Manijeh Bashar Merouane Debbah |
| author_facet | Mostafa Rahmani Mohammad Javad Dehghani Pei Xiao Manijeh Bashar Merouane Debbah |
| author_sort | Mostafa Rahmani |
| collection | DOAJ |
| description | Cell-free massive multiple-input multiple-output (CF-mMIMO) has been considered as one of the potential technologies for beyond-5G and 6G to meet the demand for higher data capacity and uniform service rate for user equipment. However, reusing the same pilot signals by several users, owing to limited pilot resources, can result in the so-called pilot contamination problem, which can prevent CF-mMIMO from unlocking its full performance potential. It is challenging to employ classical pilot assignment (PA) methods to serve many users simultaneously with low complexity; therefore, a scalable and distributed PA scheme is required. In this paper, we utilize a learning-based approach to handle the pilot contamination problem by formulating PA as a multi-agent static game, developing a two-level hierarchical learning algorithm to mitigate the effects of pilot contamination, and presenting an efficient yet scalable PA strategy. We first model a PA problem as a static multi-agent game with P teams (agents), in which each team is represented by a specific pilot. We then define a multi-agent structure that can automatically determine the most appropriate PA policy in a distributed manner. The numerical results demonstrate that the proposed PA algorithm outperforms previous suboptimal algorithms in terms of the per-user spectral efficiency (SE). In particular, the proposed approach can increase the average SE and 95%-likely SE by approximately 2.2% and 3.3%, respectively, compared to the best state-of-the-art solution. |
| first_indexed | 2024-04-11T14:30:56Z |
| format | Article |
| id | doaj.art-789337838a8a478fa8fc110dbdc7cc0b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T14:30:56Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-789337838a8a478fa8fc110dbdc7cc0b2022-12-22T04:18:37ZengIEEEIEEE Access2169-35362022-01-011012049212050210.1109/ACCESS.2022.32219359950058Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO SystemsMostafa Rahmani0https://orcid.org/0000-0002-7943-9977Mohammad Javad Dehghani1https://orcid.org/0000-0003-0972-2352Pei Xiao2https://orcid.org/0000-0002-7886-5878Manijeh Bashar3Merouane Debbah4Department of Electrical and Electronic Engineering, Shiraz University of Technology, Shiraz, IranDepartment of Electrical and Electronic Engineering, Shiraz University of Technology, Shiraz, Iran5GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.KBritish Telecommunications (BT) Company, Ipswich, U.KTechnology Innovation Institute, Abu Dhabi, United Arab EmiratesCell-free massive multiple-input multiple-output (CF-mMIMO) has been considered as one of the potential technologies for beyond-5G and 6G to meet the demand for higher data capacity and uniform service rate for user equipment. However, reusing the same pilot signals by several users, owing to limited pilot resources, can result in the so-called pilot contamination problem, which can prevent CF-mMIMO from unlocking its full performance potential. It is challenging to employ classical pilot assignment (PA) methods to serve many users simultaneously with low complexity; therefore, a scalable and distributed PA scheme is required. In this paper, we utilize a learning-based approach to handle the pilot contamination problem by formulating PA as a multi-agent static game, developing a two-level hierarchical learning algorithm to mitigate the effects of pilot contamination, and presenting an efficient yet scalable PA strategy. We first model a PA problem as a static multi-agent game with P teams (agents), in which each team is represented by a specific pilot. We then define a multi-agent structure that can automatically determine the most appropriate PA policy in a distributed manner. The numerical results demonstrate that the proposed PA algorithm outperforms previous suboptimal algorithms in terms of the per-user spectral efficiency (SE). In particular, the proposed approach can increase the average SE and 95%-likely SE by approximately 2.2% and 3.3%, respectively, compared to the best state-of-the-art solution.https://ieeexplore.ieee.org/document/9950058/Cell-free massive MIMOdeep reinforcement learningpilot assignmentpilot contaminationspectral efficiency |
| spellingShingle | Mostafa Rahmani Mohammad Javad Dehghani Pei Xiao Manijeh Bashar Merouane Debbah Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO Systems IEEE Access Cell-free massive MIMO deep reinforcement learning pilot assignment pilot contamination spectral efficiency |
| title | Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO Systems |
| title_full | Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO Systems |
| title_fullStr | Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO Systems |
| title_full_unstemmed | Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO Systems |
| title_short | Multi-Agent Reinforcement Learning-Based Pilot Assignment for Cell-Free Massive MIMO Systems |
| title_sort | multi agent reinforcement learning based pilot assignment for cell free massive mimo systems |
| topic | Cell-free massive MIMO deep reinforcement learning pilot assignment pilot contamination spectral efficiency |
| url | https://ieeexplore.ieee.org/document/9950058/ |
| work_keys_str_mv | AT mostafarahmani multiagentreinforcementlearningbasedpilotassignmentforcellfreemassivemimosystems AT mohammadjavaddehghani multiagentreinforcementlearningbasedpilotassignmentforcellfreemassivemimosystems AT peixiao multiagentreinforcementlearningbasedpilotassignmentforcellfreemassivemimosystems AT manijehbashar multiagentreinforcementlearningbasedpilotassignmentforcellfreemassivemimosystems AT merouanedebbah multiagentreinforcementlearningbasedpilotassignmentforcellfreemassivemimosystems |