Constrained Deep Learning for Wireless Resource Management

Hoon Lee, Sang Hyun Lee, Tony Q.S. Quek

研究成果: Conference contribution

3 引文 斯高帕斯(Scopus)

摘要

In this paper, we investigate a deep learning (DL) approach to solve a generic constrained optimization problem in wireless networks, where the objective and constraint functions can be nonconvex. To this target, the computation process of the solution is replaced by deep neural networks (DNNs). The original problem is transformed to a training task of the DNNs subject to nonconvex constraints. Since existing DL libraries are originally intended for unconstrained training, they cannot be directly applied to our constrained training problem. We propose a constrained training strategy based on the primal-dual method from optimization techniques. The proposed DL approach is deployed to solve transmit power allocation problems in various network configurations. The simulation results shed light on the feasibility of the DL method as an alternative to existing optimization algorithms.

原文English
主出版物標題2019 IEEE International Conference on Communications, ICC 2019 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781538680889
DOIs
出版狀態Published - 2019 五月
事件2019 IEEE International Conference on Communications, ICC 2019 - Shanghai, China
持續時間: 2019 五月 202019 五月 24

出版系列

名字IEEE International Conference on Communications
2019-May
ISSN(列印)1550-3607

Conference

Conference2019 IEEE International Conference on Communications, ICC 2019
國家/地區China
城市Shanghai
期間19-05-2019-05-24

All Science Journal Classification (ASJC) codes

  • 電腦網路與通信
  • 電氣與電子工程

指紋

深入研究「Constrained Deep Learning for Wireless Resource Management」主題。共同形成了獨特的指紋。

引用此