When Optimization Meets Machine Learning: The Case of IRS-Assisted Wireless Networks

Gong, Shimin; Lin, Jiaye; Ding, Beichen; Niyato, Dusit; Kim, Dong In; Guizani, Mohsen

doi:10.1109/mnet.211.2100386

Cited by 8 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the success of the IRS-aided BackCom system, the joint design of the beamforming at the reader and the IRS reflection coefficients is crucial, which is a difficult problem due to the multi-reflection nature of the system and the large number of parameters to be learned. Thus, DL based approaches have huge potential for realizing IRSaided systems, in particular, the design of IRS phase shifts for different system applications, as evidenced by [33]- [39].…”

Section: Monostatic Backscatter Joint Optimization Of Irs and Snr Workmentioning

confidence: 99%

Joint Active and Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems: An Unsupervised Learning Approach

Idrees,

Durrani,

et al. 2024

Trans. Mach. Learn. Comm. Netw.

View full text Add to dashboard Cite

Backscatter Communication (BackCom) has been envisioned as a key enabler for ubiquitous connectivity in the Internet of Things (IoT). However, the inherent issues of limited range and low achievable bit rate are prominent barriers to the widespread deployment of BackCom. In this work, we address these challenges by considering a monostatic BackCom system assisted by an intelligent reflecting surface (IRS) and controlled seamlessly by data driven deep learning (DL) based approach. We propose a deep residual neural network (DRCNN) BackIRS-Net that exploits the unique coupling between the IRS phase shifts and the beamforming at the reader, to jointly optimize these quantities in order to maximize the effective signal to noise ratio (SNR) of the backscatter signal received at the reader. We show that the performance of a trained BackIRS-Net is close to the conventional optimization based approach while requiring much less computational complexity and time, which indicates the utility of this scheme for real-time deployment. Our results show that an IRS of moderate size can significantly improve backscatter SNR, resulting in range extension by a factor of 4 for monostatic BackCom, which is an important improvement in the context of BackCom based IoT systems.

show abstract

Section: Monostatic Backscatter Joint Optimization Of Irs and Snr Workmentioning

confidence: 99%

Joint Active and Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems: An Unsupervised Learning Approach

Idrees,

Durrani,

et al. 2024

Trans. Mach. Learn. Comm. Netw.

View full text Add to dashboard Cite

show abstract

“…Similarly, the authors of [20] and [21] only considered the application of IRS in WPT systems. In our previous works [23]- [24], we considered the performance optimization of wireless-powered IRS-assisted single-user systems based on PS and TS protocols. Numerical results showed that PS outperforms TS when the IRS is closer to the AP, while TS outperforms PS when the IRS is closer to the users.…”

Section: Introductionmentioning

confidence: 99%