Beamforming Optimization for Intelligent Reflecting Surface Assisted MISO: A Deep Transfer Learning Approach

Ge, Yimeng; Fan, Jiancun

doi:10.1109/tvt.2021.3062870

Cited by 33 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fortunately, artificial intelligence (AI) technology provides simple approaches to address such complex problems [21][22][23][24]. Yang et al [22] investigated secure physical communication based on IRS under the condition of time-varying channel coefficients and proposed a deep reinforcement learning approach to jointly optimize both BS and IRS beamforming.…”

Section: Introductionmentioning

confidence: 99%

“…Yang et al [22] investigated secure physical communication based on IRS under the condition of time-varying channel coefficients and proposed a deep reinforcement learning approach to jointly optimize both BS and IRS beamforming. Ge et al [23] established a deep transfer learning framework to solve the beamforming optimization problem for the IRS-assisted MISO system. Jiang et al [24] trained a graph neural network (GNN) architecture to directly map the received pilots to the IRS's phase shifts and BS beamforming matrix.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Beamforming Based On Graph Attention Networks For IRS-assisted Satellite IoT Communications

Cao¹,

Zhu²,

Feng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Satellite communication is expected to play a vital role in realizing Internet of Remote Things (IoRT) applications. This article considers an intelligent reflecting surface (IRS)-assisted downlink low Earth orbit (LEO) satellite communication network, where IRS provides additional reflective links to enhance the intended signal power. We aim to maximize the sum-rate of all the terrestrial users by jointly optimizing the satellite’s precoding matrix and IRS’s phase shifts. However, it is difficult to directly acquire the instantaneous channel state information (CSI) and optimal phase shifts of IRS due to the high mobility of LEO and the passive nature of reflective elements. Moreover, most conventional solution algorithms suffer from high computational complexity and are not applicable to these dynamic scenarios. A robust beamforming design based on graph attention networks (RBF-GAT) is proposed to establish a direct mapping from the received pilots and dynamic network topology to the satellite and IRS’s beamforming, which is trained offline using the unsupervised learning approach. The simulation results corroborate that the proposed RBF-GAT can achieve approximate performance compared to the upper bound with low complexity.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robust Beamforming Based On Graph Attention Networks For IRS-assisted Satellite IoT Communications

Cao¹,

Zhu²,

Feng³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robust Beamforming Based on Graph Attention Networks for IRS-Assisted Satellite IoT Communications

Cao

Zhu

Feng

et al. 2022

Entropy

View full text Add to dashboard Cite

Satellite communication is expected to play a vital role in realizing Internet of Remote Things (IoRT) applications. This article considers an intelligent reflecting surface (IRS)-assisted downlink low Earth orbit (LEO) satellite communication network, where IRS provides additional reflective links to enhance the intended signal power. We aim to maximize the sum-rate of all the terrestrial users by jointly optimizing the satellite’s precoding matrix and IRS’s phase shifts. However, it is difficult to directly acquire the instantaneous channel state information (CSI) and optimal phase shifts of IRS due to the high mobility of LEO and the passive nature of reflective elements. Moreover, most conventional solution algorithms suffer from high computational complexity and are not applicable to these dynamic scenarios. A robust beamforming design based on graph attention networks (RBF-GAT) is proposed to establish a direct mapping from the received pilots and dynamic network topology to the satellite and IRS’s beamforming, which is trained offline using the unsupervised learning approach. The simulation results corroborate that the proposed RBF-GAT approach can achieve more than 95% of the performance provided by the upper bound with low complexity.

show abstract

“…The weights of the ANNs are trained, mainly by means of gradient descent-based algorithms, to learn and later generalize the actual correspondence between the input and output sets. Several works have proposed the use of supervised DL approaches to solve different challenging problems in IRS-assisted MIMO communications like channel estimation [27]- [33], beamforming [34], [35] and IRS phase-shift matrix optimization [36]. However, the performance of supervised DL approaches is highly dependent on the data sets available for the training process.…”

Section: Introductionmentioning

confidence: 99%

A Deep Reinforcement Learning Approach to IRS-assisted MU-MIMO Communication Systems

Pereira-Ruisánchez¹,

Fresnedo²,

Pérez-Adán³

et al. 2022

Preprint

View full text Add to dashboard Cite

<div>The deep reinforcement learning (DRL)-based deep deterministic policy gradient (DDPG) framework is proposed to solve the joint optimization of the IRS phase-shift matrix and the precoding matrix in an IRS-assisted multi-stream multi-user MIMO communication.<br></div><div><br></div><div>The combination of multiple-input multiple-output(MIMO) communications and intelligent reflecting surfaces(IRSs) is foreseen as a key enabler of beyond 5G (B5G) and 6Gsystems. In this work, we develop an innovative deep reinforcement learning (DRL)-based approach to the joint optimization of the MIMO precoders and the IRS phase-shift matrices that is proved to be efficient in high dimensional systems. The proposed approach is termed deep deterministic policy gradient (DDPG)and maximizes the sum rate of an IRS-assisted multi-stream(MS) multi-user MIMO (MU-MIMO) system by learning the best matrix configuration through online trial-and-error interactions. The proposed approach is formulated in terms of continuous state and action spaces, and a sum-rate-based reward function. The computational complexity is reduced by using artificial neural networks (ANNs) for function approximations and it is shown that the proposed solution scales better than other state-of-the-art methods, while reaching a competitive performance.<br></div>

show abstract

Beamforming Optimization for Intelligent Reflecting Surface Assisted MISO: A Deep Transfer Learning Approach

Cited by 33 publications

References 20 publications

Robust Beamforming Based On Graph Attention Networks For IRS-assisted Satellite IoT Communications

Robust Beamforming Based On Graph Attention Networks For IRS-assisted Satellite IoT Communications

Robust Beamforming Based on Graph Attention Networks for IRS-Assisted Satellite IoT Communications

A Deep Reinforcement Learning Approach to IRS-assisted MU-MIMO Communication Systems

Contact Info

Product

Resources

About