Learning-based joint optimization of mode selection and transmit power control for D2D communication underlaid cellular networks
作者：
Highlights：
• In D2D, each user can choose to direct D2D or DID mode, called as mode selection.
• A joint optimization of mode selection and transmit power control is studied.
• A DNN algorithm is proposed to solve the joint optimization problem.
• The DNN is trained by minimizing the loss function from Lagrange duality function.
• Results show DNN achieves a near-global optimal solution with lower time complexity.
摘要
•In D2D, each user can choose to direct D2D or DID mode, called as mode selection.•A joint optimization of mode selection and transmit power control is studied.•A DNN algorithm is proposed to solve the joint optimization problem.•The DNN is trained by minimizing the loss function from Lagrange duality function.•Results show DNN achieves a near-global optimal solution with lower time complexity.
论文关键词：Deep neural network,D2D communication,Sum-rate maximization,Mode selection,Transmit power control
论文评审过程：Received 10 May 2021, Revised 14 January 2022, Accepted 21 February 2022, Available online 12 March 2022, Version of Record 22 March 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116725
