Abstract
The addition of a large number of antennas to a conventional MIMO system results in significant improvement in the performance of multicellular communication systems. The performance of this so-called massive MIMO system however suffers from pilot contamination. This interference to a user communication by a nearby cell base station causes significant limitation in the performance of the system. In this work, we propose a pilot allocation scheme as a careful allocation of pilots sequences can mitigate the diverse effect of pilot contamination. We train convolutional neural networks to discover the best set of users that can share the same pilot sequences such that contamination does not occur. The simulation results show that our proposed solution is capable of pilot assignment to avoid pilot contamination.
Original language | English |
---|---|
Pages (from-to) | 613-621 |
Number of pages | 9 |
Journal | Wireless Personal Communications |
Volume | 129 |
Issue number | 1 |
DOIs | |
State | Published - Mar 2023 |
Bibliographical note
Publisher Copyright:© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Keywords
- Convolutional neural network
- Deep learning
- Massive MIMO
- Pilot contamination
ASJC Scopus subject areas
- Computer Science Applications
- Electrical and Electronic Engineering