DRL-based Energy Efficient Resource Allocation for STAR-RIS Assisted Coordinated Multi-cell Networks

Chen, Jian; Ma, Ziye; Zou, Yixuan; Jia, Jie; Wang, Xingwei

doi:10.1109/globecom48099.2022.10001595

Cited by 4 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[20], [21], and (ii) the recent learning-driven ones, e.g. [18], [19]. The former category applies mathematical transformations to reformulate the non-convex resource management optimisation problems in convex form and address them via existing off-theshelf solvers, e.g., CVX.…”

Section: B Research Challenges and Contributionsmentioning

confidence: 99%

“…Our work differs from [23] by adopting active beamforming at the STAR-RIS and also differs from [15] by employing SWIPT technology. In addition, an energy-efficient element selection mechanism is designed in this paper to mitigate the significant energy consumption of the active STAR-RIS system, in contrast to [13], [14] and [16], [17], [18], [19], [20], [21]. Under the assumption of weak LoS links between the BS and the users, an active STAR-RIS is deployed, which uses active beamforming to redirect (transmit or reflect) incident signals and simultaneously serves the users with energy and information.…”

Section: B Research Challenges and Contributionsmentioning

confidence: 99%

“…Compared to [18], [19], our enhanced meta-MDS (MMDS) algorithm performs well in highly dynamic scenarios with user mobility by enhancing the generalisation ability of the MDS algorithm and showing fast adaptability to the upcoming network dynamics. • Simulation results show that our proposed active STAR-RIS-based SWIPT scheme achieves a significant system EE gain of around 57%, compared to its passive counterpart.…”

Section: B Research Challenges and Contributionsmentioning

confidence: 99%

“…Numerical results demonstrated a significant improvement for the proposed system over the conventional active RIS-aided cell-free massive MIMO system. The authors of [18] and [19] investigated the potential of deep reinforcement learning (DRL) for optimising the performance of STAR-RIS-aided systems. Specifically, in [18], an online joint active and passive beamforming framework was proposed to maximise the long-term EE of a multi-cell STAR-RIS-enabled system using a parallel DRL technique.…”

Section: Introduction a Background And Motivationmentioning

confidence: 99%

“…The authors of [18] and [19] investigated the potential of deep reinforcement learning (DRL) for optimising the performance of STAR-RIS-aided systems. Specifically, in [18], an online joint active and passive beamforming framework was proposed to maximise the long-term EE of a multi-cell STAR-RIS-enabled system using a parallel DRL technique. In [19], the maximisation of the overall EE of a NOMAenabled STAR-RIS-based network was investigated using a deep deterministic policy gradient (DDPG)-based DRL algorithm.…”

Section: Introduction a Background And Motivationmentioning

confidence: 99%

See 4 more Smart Citations

Max-Min Fair Energy-Efficient Beamforming Design for Intelligent Reflecting Surface-Aided SWIPT Systems With Non-Linear Energy Harvesting Model

Zargari

Khalili

et al. 2021

IEEE Trans. Veh. Technol.

105

View full text Add to dashboard Cite

In this paper, we consider the downlink transmission of a multi-antenna base station (BS) supported by an active simultaneously transmitting and reconfigurable intelligent surface (STAR-RIS) to serve single-antenna users via simultaneous wireless information and power transfer (SWIPT). In this context, we formulate an energy efficiency maximisation problem that jointly optimises the gain, element selection and phase shift matrices of the active STAR-RIS, the transmit beamforming of the BS and the power splitting ratio of the users. With respect to the highly coupled and non-convex form of this problem, an alternating optimisation solution approach is proposed, using tools from convex optimisation and reinforcement learning. Specifically, semi-definite relaxation (SDR), difference of concave functions (DC), and fractional programming techniques are employed to transform the non-convex optimisation problem into a convex form for optimising the BS beamforming vector and the power splitting ratio of the SWIPT. Then, by integrating meta-learning with the modified deep deterministic policy gradient (DDPG) and soft actor-critical (SAC) methods, a combinatorial reinforcement learning network is developed to optimise the element selection, gain and phase shift matrices of the active STAR-RIS. Our simulations show the effectiveness of the proposed resource allocation scheme. Furthermore, our proposed active STAR-RISbased SWIPT system outperforms its passive counterpart by 57% on average. Index Terms-Active simultaneously transmitting and reflecting intelligent surface (STAR-RIS), simultaneously wireless information and power transfer (SWIPT), energy efficiency (EE), convex optimisation, meta-learning, deep deterministic policy gradient (DDPG), soft actor-critic (SAC).

show abstract

Section: B Research Challenges and Contributionsmentioning

confidence: 99%

Section: B Research Challenges and Contributionsmentioning

confidence: 99%

Section: B Research Challenges and Contributionsmentioning

confidence: 99%

Section: Introduction a Background And Motivationmentioning

confidence: 99%

Section: Introduction a Background And Motivationmentioning

confidence: 99%

See 3 more Smart Citations

Max-Min Fair Energy-Efficient Beamforming Design for Intelligent Reflecting Surface-Aided SWIPT Systems With Non-Linear Energy Harvesting Model

Zargari

Khalili

et al. 2021

IEEE Trans. Veh. Technol.

105

View full text Add to dashboard Cite

show abstract

Deep Reinforcement Learning Based Energy-Efficient Design for STAR-IRS Assisted V2V Users

Yadav,

Rishi

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

A Survey on Federated Learning for Reconfigurable Intelligent Metasurfaces-Aided Wireless Networks

Das,

Champagne,

Psaromiligkos

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Wireless networks are increasingly relying on machine learning (ML) paradigms to provide various services at the user level. Yet, it remains impractical for users to offload their collected data set to a cloud server for centrally training their local ML model. Federated learning (FL), which aims to collaboratively train a global ML model by leveraging the distributed wireless computation resources across users without exchanging their local information, is therefore deemed as a promising solution for enabling intelligent wireless networks in the data-driven society of the future. Recently, reconfigurable intelligent metasurfaces (RIMs) have emerged as a revolutionary technology, offering a controllable means for increasing signal diversity and reshaping transmission channels, without implementation constraints traditionally associated with multiantenna systems. In this paper, we present a comprehensive survey of recent works on the applications of FL to RIM-aided communications. We first review the fundamental basis of FL with an emphasis on distributed learning mechanisms, as well as the operating principles of RIMs, including tuning mechanisms, operation modes, and deployment options. We then proceed with an in-depth survey of literature on FL-based approaches recently proposed for the solution of three key interrelated problems in RIM-aided wireless networks, namely: channel estimation (CE), passive beamforming (PBF) and resource allocation (RA). In each case, we illustrate the discussion by introducing an expanded FL (EFL) framework in which only a subset of active users partake in the distributed training process, thereby allowing to reduce transmission overhead. Lastly, we discuss some current challenges and promising research avenues for leveraging the full potential of FL in future RIM-aided extremely large-scale multiple-input-multiple-output (XL-MIMO) networks.

show abstract

DRL-based Energy Efficient Resource Allocation for STAR-RIS Assisted Coordinated Multi-cell Networks

Cited by 4 publications

References 10 publications

Max-Min Fair Energy-Efficient Beamforming Design for Intelligent Reflecting Surface-Aided SWIPT Systems With Non-Linear Energy Harvesting Model

Max-Min Fair Energy-Efficient Beamforming Design for Intelligent Reflecting Surface-Aided SWIPT Systems With Non-Linear Energy Harvesting Model

Deep Reinforcement Learning Based Energy-Efficient Design for STAR-IRS Assisted V2V Users

A Survey on Federated Learning for Reconfigurable Intelligent Metasurfaces-Aided Wireless Networks

Contact Info

Product

Resources

About