Title
When Optimization Meets Machine Learning: The Case of IRS-Assisted Wireless Networks
Abstract
Performance optimization of wireless networks is typically complicated because of high computational complexity and dynamic channel conditions. Considering a specific case, the recent introduction of intelligent reflecting surface (IRS) can reshape the wireless channels by controlling the scattering elements' phase shifts, namely, passive beamforming. However, due to the large size of scattering elements, the IRS's beamforming optimization becomes intractable. In this article, we focus on machine learning (ML) approaches for complex optimization problems in wireless networks. ML approaches can provide flexibility and robustness against uncertain and dynamic systems. However, practical challenges still remain due to slow convergence in offline training or online learning. This motivated us to design a novel optimization-driven ML framework that exploits the efficiency of model-based optimization and the robustness of model-free ML approaches. Splitting the control variables into two parts allows one part to be updated by the outer loop ML approach while the other part is solved by the inner loop optimization. The case study in IRS-assisted wireless networks confirms that the optimization-driven ML framework can improve learning efficiency and the reward performance significantly compared to conventional model-free ML approaches.
Year
DOI
Venue
2022
10.1109/MNET.211.2100386
IEEE Network
Keywords
DocType
Volume
IRS-assisted wireless networks,performance optimization,high computational complexity,dynamic channel conditions,intelligent reflecting surface,wireless channels,scattering elements,passive beamforming,IRS's beamforming optimization,complex optimization problems,uncertain systems,dynamic systems,offline training,novel optimization-driven ML framework,model-based optimization,outer loop ML approach,inner loop optimization,conventional model-free ML approaches
Journal
36
Issue
ISSN
Citations 
2
0890-8044
0
PageRank 
References 
Authors
0.34
9
6
Name
Order
Citations
PageRank
Gong Shimin142434.89
Jiaye Lin200.34
Beichen Ding300.34
Niyato Dusit49486547.06
Dong In Kim53784220.90
Mohsen Guizani66456557.44