 |
Conference papers
ONLINE ENERGY-EFFICIENT POWER CONTROL IN WIRELESS NETWORKS BY DEEP NEURAL NETWORKS
Abstract : The work describes how deep learning by artificial neural networks (ANNs) enables online power allocation for energy efficiency maximization in wireless interference networks. A deep ANN architecture is proposed and trained to take as input the network communication channels and to output suitable power allocations. It is shown that this approach requires a much lower computational complexity compared to traditional optimization-oriented approaches, dispensing with the need of solving the optimization problem anew in each channel coherence time. Despite the lower complexity, numerical results show that a properly trained ANN achieves similar performance as more traditional optimization-oriented methods.
Cited literature [22 references]
https://hal-centralesupelec.archives-ouvertes.fr/hal-01962086
Contributor : Delphine Le Piolet <>
Submitted on : Thursday, December 20, 2018 - 1:33:18 PM
Last modification on : Wednesday, April 8, 2020 - 3:17:50 PM
Document(s) archivé(s) le : Friday, March 22, 2019 - 10:42:34 AM
Contributor : Delphine Le Piolet <>
Submitted on : Thursday, December 20, 2018 - 1:33:18 PM
Last modification on : Wednesday, April 8, 2020 - 3:17:50 PM
Document(s) archivé(s) le : Friday, March 22, 2019 - 10:42:34 AM
File
PID5385981.pdf
Files produced by the author(s)
