Machine Learning for QoS-Aware Fairness of a D2D Network

In the quickly changing environment such as IoT, it is highly desirable to design a QoS-aware strategy to allocate the transmission power. In this paper, we apply the machine learning (ML) methodology to solve such a problem for a D2D network where the nodes are distributed following the conditional Poisson point process (PPP). The training is conducted in the feed-forward neural network (FNN).

[1]  Jeffrey G. Andrews,et al.  Power Control for D2D Underlaid Cellular Networks: Modeling, Algorithms, and Analysis , 2013, IEEE Journal on Selected Areas in Communications.

[2]  Martin Haenggi,et al.  Stochastic Geometry for Wireless Networks , 2012 .

[3]  Zhi-Quan Luo,et al.  Dynamic Spectrum Management: Complexity and Duality , 2008, IEEE Journal of Selected Topics in Signal Processing.

[4]  Bernard Fino,et al.  Multiuser detection: , 1999, Ann. des Télécommunications.

[5]  A. Leon-Garcia Probability, statistics, and random processes for electrical engineering , 2008 .