Intelligent Resource Allocation for IRS-Enhanced OFDM Communication Systems: A Hybrid Deep Reinforcement Learning Approach

Wu, Wei; Yang, Fengchun; Zhou, Fuhui; Wu, Qihui; Hu, Rose Qingyang

doi:10.1109/twc.2022.3222864

Cited by 23 publications

(12 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of RIS in a multi-user OFDM system has been studied in [41]- [49]. In [43], [45], it was shown that RIS can increase the sum-rate of multi-user multiple-input single-output (MISO) RIS-aided OFDM systems. In [44], the authors studied a multi-user SISO RIS-aided OFDM BC and optimized the RIS elements to maximize the total power received by users for a given transmit power.…”

Section: Star-ris √mentioning

confidence: 99%

Rate Splitting in MIMO RIS-Assisted Systems With Hardware Impairments and Improper Signaling

Soleymani

Santamarı́a

Jorswieck

2023

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

This paper proposes schemes to improve the spectral efficiency of a multiple-input multiple-output (MIMO) broadcast channel (BC) with I/Q imbalance (IQI) at transceivers by employing a combination of improper Gaussian signaling (IGS), non-orthogonal multiple access (NOMA) and simultaneously transmit and reflect (STAR) reconfigurable intelligent surface (RIS). When there exists IQI, the output RF signal is a widely linear transformation of the input signal, which may make the output signal improper. To compensate for IQI, we employ IGS, thus generating a transmit improper signal. We show that IGS alongside with NOMA can highly increase the minimum rate of the users. Moreover, we propose schemes for different operational modes of STAR-RIS and show that STAR-RIS can significantly improve the system performance. Additionally, we show that IQI can highly degrade the performance especially if it is overlooked in the design.

show abstract

Section: Star-ris √mentioning

confidence: 99%

Rate Splitting in MIMO RIS-Assisted Systems With Hardware Impairments and Improper Signaling

Soleymani

Santamarı́a

Jorswieck

2023

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…Ensuring the adaptability of ML models to rapidly changing wireless environments is an ongoing concern. Techniques like meta-learning, continuous learning, and Reinforcement Learning (RL) are under exploration to make ML models more agile and responsive to dynamic network conditions [ 175 , 176 ].…”

Section: Future Directionsmentioning

confidence: 99%

A Survey of PAPR Techniques Based on Machine Learning

da Silva,

Souto,

Souza

et al. 2024

Sensors

View full text Add to dashboard Cite

Orthogonal Frequency Division Multiplexing (OFDM) is the modulation technology used in Fourth Generation (4G) and Fifth Generation (5G) wireless communication systems, and it will likely be essential to Sixth Generation (6G) wireless communication systems. However, OFDM introduces a high Peak to Average Power Ratio (PAPR) in the time domain due to constructive interference among multiple subcarriers, increasing the complexity and cost of the amplifiers and, consequently, the cost and complexity of 6G networks. Therefore, the development of new solutions to reduce the PAPR in OFDM systems is crucial to 6G networks. The application of Machine Learning (ML) has emerged as a promising avenue for tackling PAPR issues. Along this line, this paper presents a comprehensive review of PAPR optimization techniques with a focus on ML approaches. From this survey, it becomes clear that ML solutions offer customized optimization, effective search space navigation, and real-time adaptability. In light of the demands of evolving 6G networks, integration of ML is a necessity to propel advancements and meet increasing prerequisites. This integration not only presents possibilities for PAPR reduction but also calls for continued exploration to harness its potential and ensure efficient and reliable communication within 6G networks.

show abstract

“…The selection of the neural network structure relies on the characteristics of the environment and the specific task being performed 41–43 . The network typically consists of multiple layers, with each layer performing a different type of computation 44,45 . The hidden layers are designed to extract features from the observations that are relevant to the task 46 .…”

Section: Literature Reviewmentioning

confidence: 99%

“…The scientists have developed a systematic approach to enable autonomous activation of cellular functions and customized resource allocation techniques for achieving a harmonious balance between energy consumption, environmental preservation, and ensuring the satisfactory quality of service. In Reference [44], the authors discuss the utilization of the DQN and deep deterministic policy‐gradient (DDPG) algorithms proposed to optimize the allocation of resources within intelligent reflecting surface (IRS) enhanced orthogonal frequency division multiplexing (OFDM) systems. The proposed approach involves the simultaneous optimization of subcarrier allocation, base station transmit beamforming, and phase shift adjustments of the IRS to maximize the overall system sum rate.…”

Section: Literature Reviewmentioning

confidence: 99%

“…[41][42][43] The network typically consists of multiple layers, with each layer performing a different type of computation. 44,45 The hidden layers are designed to extract features from the observations that are relevant to the task. 46 The choice of loss function also depends on the task at hand.…”

Section: Introduction To Drl Algorithms and Their Potential For Solvi...mentioning

confidence: 99%

See 1 more Smart Citation

Resource allocation in 5G cloud‐RAN using deep reinforcement learning algorithms: A review

Khani,

Jamali,

Sohrabi

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

This paper reviews recent research on resource allocation in 5G cloud‐based radio access networks (C‐RAN) using deep reinforcement learning (DRL) algorithms. It explores the potential of DRL for learning complex decision‐making policies without human intervention. The paper first introduces the C‐RAN architecture and resource allocation concepts, followed by an overview of DRL algorithms applied to C‐RAN. It discusses the challenges and potential solutions in applying DRL to C‐RAN resource allocation, including scalability, convergence, and fairness. The review concludes by highlighting open research directions for future investigation. By providing insights into the state‐of‐the‐art techniques for resource allocation in 5G C‐RAN using DRL, this paper emphasizes their potential impact on advancing 5G network technology.

show abstract

Intelligent Resource Allocation for IRS-Enhanced OFDM Communication Systems: A Hybrid Deep Reinforcement Learning Approach

Cited by 23 publications

References 38 publications

Rate Splitting in MIMO RIS-Assisted Systems With Hardware Impairments and Improper Signaling

Rate Splitting in MIMO RIS-Assisted Systems With Hardware Impairments and Improper Signaling

A Survey of PAPR Techniques Based on Machine Learning

Resource allocation in 5G cloud‐RAN using deep reinforcement learning algorithms: A review

Contact Info

Product

Resources

About