Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement Learning
This research introduces an innovative model-free framework for Intelligent Reflecting Surface (IRS) control in multi-user wireless communication systems using Multi-Agent Reinforcement Learning (MARL). Departing from traditional methods that rely heavily on detailed channel state information (CSI),...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10947690/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849738153464692736 |
|---|---|
| author | Sakhshra Monga Abhishake Bansal Ibrahim Aljubayri Nitin Saluja Chander Prabha Shivani Malhotra Prakash Srivastava Mohammad Zubair Khan |
| author_facet | Sakhshra Monga Abhishake Bansal Ibrahim Aljubayri Nitin Saluja Chander Prabha Shivani Malhotra Prakash Srivastava Mohammad Zubair Khan |
| author_sort | Sakhshra Monga |
| collection | DOAJ |
| description | This research introduces an innovative model-free framework for Intelligent Reflecting Surface (IRS) control in multi-user wireless communication systems using Multi-Agent Reinforcement Learning (MARL). Departing from traditional methods that rely heavily on detailed channel state information (CSI), this approach emphasizes the dynamic adaptation of IRS phase shifts to optimize overall system performance, measured in bits per second per Hertz (bps/Hz). The MARL framework enables decentralized decision-making among multiple agents, offering superior adaptability to complex and rapidly evolving channel conditions. Comparative analyses with established methods, including Multi-Armed Bandit (MAB), Random Selection, Deep Q-Network (DQN), and Hierarchical Reinforcement Learning (HRL), reveal substantial improvements in system performance. In particular, for a base station (BS) configuration with two antennas (<inline-formula> <tex-math notation="LaTeX">$N_{B} = 2$ </tex-math></inline-formula>), MARL achieves superior performance compared to baseline methods, demonstrating its robustness in limited-antenna settings. Similarly, an IRS deployment with 32 elements enhances MARL’s efficiency by leveraging improved signal reflections, leading to significant performance gains. Furthermore, the impact of batch size and K-factor on MARL’s adaptability is evaluated, confirming its ability to optimize phase shift adjustments across diverse network conditions. Simulation results confirm MARL’s efficacy in optimizing resource allocation and phase shift adjustments, demonstrating its scalability and potential for real-time deployment in large-scale wireless networks. |
| format | Article |
| id | doaj-art-2f3df54da90a4d2585dd50642b8b0159 |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-2f3df54da90a4d2585dd50642b8b01592025-08-20T03:06:42ZengIEEEIEEE Access2169-35362025-01-0113620716208710.1109/ACCESS.2025.355700810947690Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement LearningSakhshra Monga0Abhishake Bansal1Ibrahim Aljubayri2https://orcid.org/0000-0002-8011-1549Nitin Saluja3https://orcid.org/0000-0001-6570-8606Chander Prabha4https://orcid.org/0000-0002-2322-7289Shivani Malhotra5Prakash Srivastava6https://orcid.org/0000-0002-6793-8939Mohammad Zubair Khan7https://orcid.org/0000-0002-2409-7172Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, IndiaChitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, IndiaDepartment of Computer Science and Information, Taibah University, Madinah, Saudi ArabiaChitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, IndiaChitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, IndiaChitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, IndiaDepartment of Computer Science and Engineering, Graphic Era (Deemed to be University), Dehradun, Uttarakhand, IndiaDepartment of Computer Science and Information, Taibah University, Madinah, Saudi ArabiaThis research introduces an innovative model-free framework for Intelligent Reflecting Surface (IRS) control in multi-user wireless communication systems using Multi-Agent Reinforcement Learning (MARL). Departing from traditional methods that rely heavily on detailed channel state information (CSI), this approach emphasizes the dynamic adaptation of IRS phase shifts to optimize overall system performance, measured in bits per second per Hertz (bps/Hz). The MARL framework enables decentralized decision-making among multiple agents, offering superior adaptability to complex and rapidly evolving channel conditions. Comparative analyses with established methods, including Multi-Armed Bandit (MAB), Random Selection, Deep Q-Network (DQN), and Hierarchical Reinforcement Learning (HRL), reveal substantial improvements in system performance. In particular, for a base station (BS) configuration with two antennas (<inline-formula> <tex-math notation="LaTeX">$N_{B} = 2$ </tex-math></inline-formula>), MARL achieves superior performance compared to baseline methods, demonstrating its robustness in limited-antenna settings. Similarly, an IRS deployment with 32 elements enhances MARL’s efficiency by leveraging improved signal reflections, leading to significant performance gains. Furthermore, the impact of batch size and K-factor on MARL’s adaptability is evaluated, confirming its ability to optimize phase shift adjustments across diverse network conditions. Simulation results confirm MARL’s efficacy in optimizing resource allocation and phase shift adjustments, demonstrating its scalability and potential for real-time deployment in large-scale wireless networks.https://ieeexplore.ieee.org/document/10947690/Multi-agent reinforcement learningchannel state informationDeep Q-Networkhierarchical reinforcement learningmulti-armed banditrandom selection |
| spellingShingle | Sakhshra Monga Abhishake Bansal Ibrahim Aljubayri Nitin Saluja Chander Prabha Shivani Malhotra Prakash Srivastava Mohammad Zubair Khan Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement Learning IEEE Access Multi-agent reinforcement learning channel state information Deep Q-Network hierarchical reinforcement learning multi-armed bandit random selection |
| title | Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement Learning |
| title_full | Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement Learning |
| title_fullStr | Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement Learning |
| title_full_unstemmed | Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement Learning |
| title_short | Adaptive Intelligent Reflecting Surfaces for Enhanced Wireless Communication via Multi-Agent Deep Reinforcement Learning |
| title_sort | adaptive intelligent reflecting surfaces for enhanced wireless communication via multi agent deep reinforcement learning |
| topic | Multi-agent reinforcement learning channel state information Deep Q-Network hierarchical reinforcement learning multi-armed bandit random selection |
| url | https://ieeexplore.ieee.org/document/10947690/ |
| work_keys_str_mv | AT sakhshramonga adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning AT abhishakebansal adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning AT ibrahimaljubayri adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning AT nitinsaluja adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning AT chanderprabha adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning AT shivanimalhotra adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning AT prakashsrivastava adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning AT mohammadzubairkhan adaptiveintelligentreflectingsurfacesforenhancedwirelesscommunicationviamultiagentdeepreinforcementlearning |