Deep Reinforcement Learning Based Intelligent Reflecting Surface for Secure Wireless Communications

Yang, Helin; Xiong, Zehui; Zhao, Jun; Niyato, Dusit; Xiao, Liang; Wu, Qingqing

doi:10.48550/arxiv.2002.12271

Cited by 9 publications

(14 citation statements)

References 34 publications

(86 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show how increasing the number of RISs elements can increase the secrecy rate at the expense of burdening the optimization algorithm with a larger phase shift matrix to optimize. Similarly, the authors in [26] considered a LoS channel as in [25] where they provide a machine learning (ML) approach to tackle the problem. They utilized deep post-decision-state and prioritized-experience-replay schemes to enhance the learning performance and the secrecy rate in a dynamic RIS-aided communication system.…”

Section: B Mimo System Modelmentioning

confidence: 99%

“…Simulation results showed that the ML approach can achieve comparable results to conventional optimization methods with simpler and faster implementation. To the best of the authors' knowledge, [40] and [26] are the only studies that use an ML approach to tackle the PLS problem in RIS-aided communication systems, which opens the door for a new area to exploit.…”

Section: Miso System Modelmentioning

confidence: 99%

“…The use of data-driven tools such as ML, deep learning, and reinforcement learning, is a promising solution to support the flexibility and the selfoptimizability of such networks. Only a few works, [26], [40], have been reported employing ML-based approaches to solve the PLS problem in RIS-assisted networks.…”

Section: G Optimization Problems To Enhance Plsmentioning

confidence: 99%

See 2 more Smart Citations

Smart and Secure Wireless Communications via Reflecting Intelligent Surfaces: A Short Survey

Almohamad¹,

Tahir²,

Al‐Kababji³

et al. 2020

Preprint

View full text Add to dashboard Cite

I. INTRODUCTIOND UE to the considerable increase in the number of wirelessly communicating devices, different innovative technologies have been proposed in the literature to enhance the energy and spectrum efficiency along with the reliability and security of wireless communication systems. The future applications from the perspective of 5G (fifth generation) wireless communication include three use cases with diverse requirements such as ultra-reliable low latency communication (URLLC), enhanced mobile broadband (eMBB), and massive machine-type communication (mMTC). The promising physical layer technologies to fulfill the requirements of the above-mentioned applications include cognitive radio, cooperative communication, massive multiple-input multiple-output, millimeter-wave, orthogonal frequency division multiplexing (OFDM) numerologies, and so on [1].Although, rigorous efforts have been done in research and development of wireless communications to fulfill the requirements of diverse users and applications of future wireless communication generations, where we require extremely high energy and spectral efficiencies, ultra-security, ultra-reliability, and highly flexible design [2], overall progress has been relatively slow. This is due to the fact that the conventional wireless communication designers have been focusing only on transmitter and receiver ends while considering the wireless communication environment an uncontrollable factor that has usually a negative effect on communication efficiency and reliability, and needs to be compensated for.Recently, reconfigurable intelligent surfaces (RIS) got much attention due to their capability to enable a smart and controllable wireless propagation environments [3]. Specifically, an RIS is a uniform planar array that consists of low-cost passive reflecting elements. Each element in an RIS can be controlled to smartly adjust the amplitude and/or phase of the incoming This publication was made possible by the grants NPRP12S-0225-190152 and GSRA6-2-0521-19034 from the Qatar National Research Fund (a member of The Qatar Foundation). The statements made herein are solely the responsibility of the author[s].

show abstract

Section: B Mimo System Modelmentioning

confidence: 99%

Section: Miso System Modelmentioning

confidence: 99%

See 1 more Smart Citation

Smart and Secure Wireless Communications via Reflecting Intelligent Surfaces: A Short Survey

Almohamad¹,

Tahir²,

Al‐Kababji³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast to the traditional model driven approaches, data driven deep learning (DL) techniques [22]- [24] have proved their effectiveness in IRS-assisted communication systems, such as the DL-based passive beamforming design [25], [26], the deep reinforcement learning (DRL)based phase shift optimization [27], and the DRL-based secure wireless communications for IRS-MC systems [28]. Although these DL-based methods are promising, they still require the availability of perfect CSI for implementation and the DL techniques have not been exploited for channel estimation in IRS-assisted systems, yet.…”

Section: Introductionmentioning

confidence: 99%

Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications

Liu,

et al. 2020

Preprint

View full text Add to dashboard Cite

Channel estimation is one of the main tasks in realizing practical intelligent reflecting surfaceassisted multi-user communication (IRS-MC) systems. However, different from traditional communication systems, an IRS-MC system generally involves a cascaded channel with a sophisticated statistical distribution. In this case, the optimal minimum mean square error (MMSE) estimator requires the calculation of a multidimensional integration which is intractable to be implemented in practice. To further improve the channel estimation performance, in this paper, we model the channel estimation as a denoising problem and adopt a deep residual learning (DReL) approach to implicitly learn the residual noise for recovering the channel coefficients from the noisy pilot-based observations. To this end, we first develop a versatile DReL-based channel estimation framework where a deep residual network (DRN)-based MMSE estimator is derived in terms of Bayesian philosophy. As a realization of the developed DReL framework, a convolutional neural network (CNN)-based DRN (CDRN) is then proposed for channel estimation in IRS-MC systems, in which a CNN denoising block equipped with an element-wise subtraction structure is specifically designed to exploit both the spatial features of the noisy channel matrices and the additive nature of the noise simultaneously. In particular, an explicit expression of the proposed CDRN is derived and analyzed in terms of Bayesian estimation to characterize its properties theoretically. Finally, simulation results demonstrate that the performance of the proposed method approaches that of the optimal MMSE estimator requiring the availability of the prior probability density function of channel.

show abstract

“…The authors in [14] apply the deep deterministic policy gradient (DDPG) algorithm to maximize the received SNR of an IRS-assisted system by continuously interacting with the environment. The DRL approach is used in [15] to enhance secrecy rate against multiple eavesdroppers. The authors in [16] implement the DRL agent at the IRS, which can observe the channel conditions and take actions based on the receiver's feedback.…”

Section: Introductionmentioning

confidence: 99%

Optimization-driven Deep Reinforcement Learning for Robust Beamforming in IRS-assisted Wireless Communications

Lin¹,

Zou²,

Dong³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Intelligent reflecting surface (IRS) is a promising technology to assist downlink information transmissions from a multi-antenna access point (AP) to a receiver. In this paper, we minimize the AP's transmit power by a joint optimization of the AP's active beamforming and the IRS's passive beamforming. Due to uncertain channel conditions, we formulate a robust power minimization problem subject to the receiver's signalto-noise ratio (SNR) requirement and the IRS's power budget constraint. We propose a deep reinforcement learning (DRL) approach that can adapt the beamforming strategies from past experiences. To improve the learning performance, we derive a convex approximation as a lower bound on the robust problem, which is integrated into the DRL framework and thus promoting a novel optimization-driven deep deterministic policy gradient (DDPG) approach. In particular, when the DDPG algorithm generates a part of the action (e.g., passive beamforming), we can use the model-based convex approximation to optimize the other part (e.g., active beamforming) of the action more efficiently. Our simulation results demonstrate that the optimization-driven DDPG algorithm can improve both the learning rate and reward performance significantly compared to the conventional modelfree DDPG algorithm.

show abstract

Deep Reinforcement Learning Based Intelligent Reflecting Surface for Secure Wireless Communications

Cited by 9 publications

References 34 publications

Smart and Secure Wireless Communications via Reflecting Intelligent Surfaces: A Short Survey

Smart and Secure Wireless Communications via Reflecting Intelligent Surfaces: A Short Survey

Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications

Optimization-driven Deep Reinforcement Learning for Robust Beamforming in IRS-assisted Wireless Communications

Contact Info

Product

Resources

About