Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning
Multiple Input Multiple Output (MIMO) systems have been gaining significant attention from the research community due to their potential to improve data rates. However, a suitable scheduling mechanism is required to efficiently distribute available spectrum resources and enhance system capacity. Thi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/21/8278 |
| _version_ | 1797466515717488640 |
|---|---|
| author | Muddasar Naeem Antonio Coronato Zaib Ullah Sajid Bashir Giovanni Paragliola |
| author_facet | Muddasar Naeem Antonio Coronato Zaib Ullah Sajid Bashir Giovanni Paragliola |
| author_sort | Muddasar Naeem |
| collection | DOAJ |
| description | Multiple Input Multiple Output (MIMO) systems have been gaining significant attention from the research community due to their potential to improve data rates. However, a suitable scheduling mechanism is required to efficiently distribute available spectrum resources and enhance system capacity. This paper investigates the user selection problem in Multi-User MIMO (MU-MIMO) environment using the multi-agent Reinforcement learning (RL) methodology. Adopting multiple antennas’ spatial degrees of freedom, devices can serve to transmit simultaneously in every time slot. We aim to develop an optimal scheduling policy by optimally selecting a group of users to be scheduled for transmission, given the channel condition and resource blocks at the beginning of each time slot. We first formulate the MU-MIMO scheduling problem as a single-state Markov Decision Process (MDP). We achieve the optimal policy by solving the formulated MDP problem using RL. We use aggregated sum-rate of the group of users selected for transmission, and a <inline-formula><math display="inline"><semantics><mrow><mn>20</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher sum-rate performance over the conventional methods is reported. |
| first_indexed | 2024-03-09T18:39:55Z |
| format | Article |
| id | doaj.art-2f7036812cbf4b038f11c029d0579290 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:39:55Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2f7036812cbf4b038f11c029d05792902023-11-24T06:45:31ZengMDPI AGSensors1424-82202022-10-012221827810.3390/s22218278Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement LearningMuddasar Naeem0Antonio Coronato1Zaib Ullah2Sajid Bashir3Giovanni Paragliola4Institute of High Performance Computing and Networking, National Research Council of Italy, 80131 Naples, ItalyCentro di Ricerche sulle Tecnologie ICT per la Salute ed il Benessere, Università Giustino Fortunato, 82100 Benevento, ItalyInstitute of High Performance Computing and Networking, National Research Council of Italy, 80131 Naples, ItalyDepartment of Electrical Engineering, National University of Sciences & Technology, Islamabad 44000, PakistanInstitute of High Performance Computing and Networking, National Research Council of Italy, 80131 Naples, ItalyMultiple Input Multiple Output (MIMO) systems have been gaining significant attention from the research community due to their potential to improve data rates. However, a suitable scheduling mechanism is required to efficiently distribute available spectrum resources and enhance system capacity. This paper investigates the user selection problem in Multi-User MIMO (MU-MIMO) environment using the multi-agent Reinforcement learning (RL) methodology. Adopting multiple antennas’ spatial degrees of freedom, devices can serve to transmit simultaneously in every time slot. We aim to develop an optimal scheduling policy by optimally selecting a group of users to be scheduled for transmission, given the channel condition and resource blocks at the beginning of each time slot. We first formulate the MU-MIMO scheduling problem as a single-state Markov Decision Process (MDP). We achieve the optimal policy by solving the formulated MDP problem using RL. We use aggregated sum-rate of the group of users selected for transmission, and a <inline-formula><math display="inline"><semantics><mrow><mn>20</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher sum-rate performance over the conventional methods is reported.https://www.mdpi.com/1424-8220/22/21/8278reinforcement learninguser schedulingchannel capacityMIMOMU-MIMOnext-generation networks |
| spellingShingle | Muddasar Naeem Antonio Coronato Zaib Ullah Sajid Bashir Giovanni Paragliola Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning Sensors reinforcement learning user scheduling channel capacity MIMO MU-MIMO next-generation networks |
| title | Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning |
| title_full | Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning |
| title_fullStr | Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning |
| title_full_unstemmed | Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning |
| title_short | Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning |
| title_sort | optimal user scheduling in multi antenna system using multi agent reinforcement learning |
| topic | reinforcement learning user scheduling channel capacity MIMO MU-MIMO next-generation networks |
| url | https://www.mdpi.com/1424-8220/22/21/8278 |
| work_keys_str_mv | AT muddasarnaeem optimaluserschedulinginmultiantennasystemusingmultiagentreinforcementlearning AT antoniocoronato optimaluserschedulinginmultiantennasystemusingmultiagentreinforcementlearning AT zaibullah optimaluserschedulinginmultiantennasystemusingmultiagentreinforcementlearning AT sajidbashir optimaluserschedulinginmultiantennasystemusingmultiagentreinforcementlearning AT giovanniparagliola optimaluserschedulinginmultiantennasystemusingmultiagentreinforcementlearning |