Deep Learning-based Power Allocation in Massive MIMO Systems with SLNR and SINR Criterions
- Authors
- Perdana, R.H.Y.; Nguyen, T.-V.; An, B.
- Issue Date
- 2021
- Publisher
- IEEE Computer Society
- Keywords
- Deep neural networks; massive MIMO; power allocation; signal-to-interference-plus-noise ratio (SINR); signal-to-leak-plus-noise ratio (SLNR)
- Citation
- International Conference on Ubiquitous and Future Networks, ICUFN, v.2021-August, pp.87 - 92
- Journal Title
- International Conference on Ubiquitous and Future Networks, ICUFN
- Volume
- 2021-August
- Start Page
- 87
- End Page
- 92
- URI
- https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/17708
- DOI
- 10.1109/ICUFN49451.2021.9528565
- ISSN
- 2165-8528
- Abstract
- In this paper, we design a deep learning framework for the power allocation problems in massive MIMO networks. In particular, we formulate the max-min and max-product power allocation problems by using signal-to-interference-plus-noise ratio (SINR) and signal-to-leak-plus-noise ratio (SLNR) criteria for linear precoder design. Multiple base stations are deployed to serve multiple user equipments, the power allocation process to each user equipment takes long processing time to converge, which is inefficient approach. We tackle this problem by designing a framework based on deep neural network, where the user equipment position is used to train the deep model, and then it is used to predict the optimal power allocation according to the user's locations. The resulting deep learning helps to reduce the processing time of the system in determining the optimal power allocation for the user equipment. Compared to the standard optimization approach, the deep learning design helps to obtain the optimal solution of the power allocation problem within a short time via a quick-inference process. Simulation results show that the SINR criterion outperforms the SLNR one. Meanwhile, deep learning performance in predicting power allocation gets excellent results with an accuracy of 85% for the max-min strategy and 99% for the max-product strategy. © 2021 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > Software and Communications Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/17708)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.