Graduate School and Research Center in Digital Sciences

Predicting device-to-device channels from cellular channel measurements: A learning approach

Najla, Mehyar; Becvar, Zdenek; Mach, Pavel; Gesbert, David

Submitted to ArXiV, 17 November 2019

Device-to-device (D2D) communication, which enables a direct connection between users while bypassing the cellular channels to base stations (BSs), is a promising way to offload the traffic from conventional cellular networks. In D2D communication, one recurring problem is that, in order to optimally allocate resources across D2D and cellular users, the knowledge of D2D channel gains is needed. However, such knowledge is hard to obtain at reasonable signaling costs. In this paper, we show this problem can be circumvented by tapping into the information provided by the estimation of the cellular channels between the users and surrounding BSs as this estimation is done anyway for a normal operation of the network. While the cellular and D2D channel gains exhibit independent fast fading behavior, we show that average gains of the cellular and D2D channels share a non-explicit correlation structure, which is rooted into the network topology, terrain, and buildings setup. We propose a machine (deep) learning approach capable of predicting the D2D channel gains from seemingly independent cellular channels. Our results show a high degree of convergence between true and predicted D2D channel gains. The predicted gains allow to reach a near-optimal communication capacity in many radio resource management algorithms.

Arxiv Bibtex

Title:Predicting device-to-device channels from cellular channel measurements: A learning approach
Keywords:Device-to-device; Channel prediction; Deep neural networks; Supervised machine learning
Department:Communication systems
Eurecom ref:6127
Copyright: © EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Submitted to ArXiV, 17 November 2019 and is available at :
Bibtex: @inproceedings{EURECOM+6127, year = {2019}, title = {{P}redicting device-to-device channels from cellular channel measurements: {A} learning approach}, author = {{N}ajla, {M}ehyar and {B}ecvar, {Z}denek and {M}ach, {P}avel and {G}esbert, {D}avid}, booktitle = {{S}ubmitted to {A}r{X}i{V}, 17 {N}ovember 2019}, address = {}, month = {11}, url = {} }
See also: