BROWSE
Detail
Journal Article
Deep Learning Methods for Joint Optimization of Beamforming and Fronthaul Quantization in Cloud Radio Access Networks
Cited 13 time in 
Share 
Share
- Authors
- Daesung Yu, Hoon Lee, Seok-Hwan Park, Seung-Eun Hong
- Issue Date
- 2021-10
- Citation
- IEEE Wireless Communications Letters, v.10, no.10, pp.2180-2184
- ISSN
- 2162-2337
- Publisher
- IEEE
- Language
- English
- Type
- Journal Article
- Abstract
- Cooperative beamforming across access points (APs) and fronthaul quantization strategies are essential for cloud radio access network (C-RAN) systems. The nonconvexity of the C-RAN optimization problems, which is stemmed from per-AP power and fronthaul capacity constraints, requires high computational complexity for executing iterative algorithms. To resolve this issue, we investigate a deep learning approach where the optimization module is replaced with a well-trained deep neural network (DNN). An efficient learning solution is proposed which constructs a DNN to produce a low-dimensional representation of optimal beamforming and quantization strategies. Numerical results validate the advantages of the proposed learning solution.
- KSP Keywords
- Access point, Cloud radio, Cloud-RAN(C-RAN), Computational complexity, Cooperative Beamforming, Deep neural network(DNN), Efficient learning, Joint optimization, Learning approach, Learning methods, Low-dimensional representation