Projects per year
Abstract
This paper investigates efficient deep learning based methods for interference mitigation in independent wireless subnetworks via dynamic allocation of radio resources. Resource allocation is cast as a mapping from interference power measurements at each subnetwork to a class of shared frequency channels. A deep neural network (DNN) is then trained to approximate this mapping using data obtained via application of centralized graph coloring (CGC). The trained network is then deployed at each subnetwork for distributed channel selection. Simulation results in an environment with mobile subnetworks have shown that relatively small-sized DNNs can be trained offline to perform distributed channel allocation. The results also show that regardless of the choice of initialization, a DNN for distributed channel selection can achieve similar performance as CGC up to a probability of loop failure (PLF) of 6 × 10-5 in diverse environments with only aggregate interference power measurements as input.
Original language | English |
---|---|
Title of host publication | 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) |
Number of pages | 7 |
Publisher | IEEE |
Publication date | 16 Sept 2021 |
Pages | 959-965 |
Article number | 9569345 |
ISBN (Print) | 978-1-7281-7587-4 |
ISBN (Electronic) | 978-1-7281-7586-7 |
DOIs | |
Publication status | Published - 16 Sept 2021 |
Event | 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) - Helsinki, Finland Duration: 13 Sept 2021 → 16 Sept 2021 |
Conference
Conference | 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) |
---|---|
Country/Territory | Finland |
City | Helsinki |
Period | 13/09/2021 → 16/09/2021 |
Series | I E E E International Symposium Personal, Indoor and Mobile Radio Communications |
---|---|
ISSN | 2166-9570 |
Keywords
- 6G
- Subnetworks
- Resource allocation
- interference management
- Machine Learning
- Graph coloring
- 5G
- Wireless communication
Fingerprint
Dive into the research topics of 'Learning to Dynamically Allocate Radio Resources in Mobile 6G in-X Subnetworks'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Enabling ultra-reliable low-latency communication in wireless networks via interference prediction
Berardinelli, G. & Adeogun, R. O.
01/10/2019 → 30/04/2022
Project: Research