Machine-Learning-Empowered Passive Beamforming and Routing Design for Multi-RIS-Assisted Multihop Networks

Huang, Chong; Chen, Gaojie; Tang, Jinchuan; Xiao, Pei; Han, Zhu

doi:10.1109/jiot.2022.3195543

Cited by 9 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [107], authors have used PPO algorithm that optimizes route node and power allocation for multi-RIS-assisted multihop networks, aiming to maximize end-to-end data rate. Simulation findings show that the PPO algorithm increases RIS-assisted system performance by 33.7% compared to random RIS coefficient systems.…”

Section: B Reinforcement Learningmentioning

confidence: 99%

Going Beyond a Simple RIS: Trends and Techniques Paving the Path of Future RIS

Shafique,

Alhassoun

2024

IEEE Open J. Antennas Propag.

View full text Add to dashboard Cite

To have uninterrupted wireless connectivity, higher throughput, and latency rate down to nanoseconds; future networks will rely heavily on higher frequency bands, yet these signals suffer from attenuation and can be easily blocked by objects. Hence, those signals lose strength over longer distances significantly compared to their low-frequency counterparts. To overcome these constraints, reconfigurable intelligent surfaces (RIS) can increase the wireless network capacity and coverage by consciously altering the wireless propagation environment, which makes them one of the key enablers of the 6G communication networks. The potential benefits of RIS-assisted communication systems can be effectively increased using machine learning (ML) to pave the path towards Wireless 2.0, having a vision of digitization, programmability, and intelligence. This paper reviews recent developments in RIS technology with a special emphasis on tuning techniques, hardware concepts, RIS empowered by artificial intelligence techniques, and applications for next generation of networks. Finally, a viewpoint on the difficulties and potential directions of intelligent metasurfaces are also presented.

show abstract

Section: B Reinforcement Learningmentioning

confidence: 99%

Going Beyond a Simple RIS: Trends and Techniques Paving the Path of Future RIS

Shafique,

Alhassoun

2024

IEEE Open J. Antennas Propag.

View full text Add to dashboard Cite

show abstract

“…DNN model is then used in the SDN controller to perform dynamic QoS classification for each request that enters the network [35]. In [36], the author proposed a routing protocol for D2D communication to reduce routing overhead and energy consumption resulting from delivering various parameters separately. The model was trained using four supervised ML techniques to find the best technique for the proposed protocol.…”

Section: Supervised Learning Based Routing Algorithmmentioning

confidence: 99%

Review on Machine Learning for Intelligent Routing, Key Requirement and Challenges Towards 6G

Langpoklakpam,

Murry

2023

Comput. Networks Commun.

View full text Add to dashboard Cite

The constant desire for faster data rates, lower latency, improved reliability, global device integration, and pervasiveness are some of the factors driving the development of next-generation communication systems. Sixth-generation (6G) networks have received a lot of attention from the industry and academics as fifth-generation (5G) communications are being rolled out globally. With the proliferation of smart devices and the Internet of Things (IoT), 6G networks will require ultra-reliable and low-latency communication. Routing protocols have a significant role in improving the performance of a network. Traditional routing techniques will have difficulty coping with the highly complex and dynamic 6G environments. Recently, machine learning (ML), a key component of artificial intelligence, is emerging as the key to managing complex and dynamic networks efficiently. However, there are still several significant challenges that need to be addressed. In this paper, we provide an overview of current machine-learning techniques used in network routing. Lastly, we highlight open research problems that need to be addressed and prospects for future research.

show abstract

“…However, sample efficiency is still an important challenge in DRL which leads to an expensive training process. Moreover, DRL is ineffective for problems in wireless networks with independent fading channel since it is designed for sequential decision-making tasks [18], [19]. To address the above issues, in this paper we propose a double cascade correlation network (DCCN) to improve the optimization of RIS reflection coefficients efficiently and introduce an inverse-variance deep reinforcement learning (IV-DRL) algorithm to improve sample efficiency in UAV trajectory optimization.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Resource Allocation in UAV-RIS-Aided Cell-Free Hybrid NOMA/OMA Networks

Huang,

Chen,

Wen

et al. 2023

GLOBECOM 2023 - 2023 IEEE Global Communications Conference

Self Cite

View full text Add to dashboard Cite

This paper investigates a deep learning-based algorithm to optimize the unmanned aerial vehicle (UAV) trajectory and reconfigurable intelligent surface (RIS) reflection coefficients in UAV-RIS-aided cell-free (CF) hybrid non-orthogonal multipleaccess (NOMA)/orthogonal multiple-access (OMA) networks. The practical RIS reflection model and user grouping optimization are considered in the proposed network. A double cascade correlation network (DCCN) is proposed to optimize the RIS reflection coefficients, and based on the results from DCCN, an inverse-variance deep reinforcement learning (IV-DRL) algorithm is introduced to address the UAV trajectory optimization problem. Simulation results show that the proposed algorithms significantly improve the performance in UAV-RIS-assisted CF networks.

show abstract

Machine-Learning-Empowered Passive Beamforming and Routing Design for Multi-RIS-Assisted Multihop Networks

Cited by 9 publications

References 40 publications

Going Beyond a Simple RIS: Trends and Techniques Paving the Path of Future RIS

Going Beyond a Simple RIS: Trends and Techniques Paving the Path of Future RIS

Review on Machine Learning for Intelligent Routing, Key Requirement and Challenges Towards 6G

Deep Learning-Based Resource Allocation in UAV-RIS-Aided Cell-Free Hybrid NOMA/OMA Networks

Contact Info

Product

Resources

About