MultiNet: deep unsupervised power control for industrial MU-MIMO networks

This paper presents Multinet, an unsupervised deep learning (DL) approach for power allocation in industrial environments and IIoT applications. Multinet extends the previously proposed singular value decomposition network (SVDNet), which utilizes supervised DL to approximate the performance of the...

Full description

Saved in:
Bibliographic Details
Main Authors: Maiti, Ritabrata, Madhukumar, A. S., Tan, Ernest Zheng Hui
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175403
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-175403
record_format dspace
spelling sg-ntu-dr.10356-1754032024-04-23T02:47:51Z MultiNet: deep unsupervised power control for industrial MU-MIMO networks Maiti, Ritabrata Madhukumar, A. S. Tan, Ernest Zheng Hui School of Computer Science and Engineering Engineering Resource allocation Deep learning Unsupervised learning Power control This paper presents Multinet, an unsupervised deep learning (DL) approach for power allocation in industrial environments and IIoT applications. Multinet extends the previously proposed singular value decomposition network (SVDNet), which utilizes supervised DL to approximate the performance of the WMMSE algorithm. While SVDNet requires labeled data for training, limiting its scalability and generalization performance, in contrast, Multinet employs unsupervised DL to directly optimize the sum rate maximization objective function, eliminating the need for labeled datasets and improving training efficiency. Simulation studies are conducted to evaluate Multinet's performance in an industrial environment, utilizing parameters derived from measured large-scale fading characteristics of the industrial radio channel at 5200 MHz. The suitability of Multinet for industrial applications is thus assessed and numerical evaluations demonstrate that Multinet outperforms benchmark supervised and unsupervised DL-based power control schemes in terms of sum rate and energy efficiency. 2024-04-23T02:47:50Z 2024-04-23T02:47:50Z 2023 Journal Article Maiti, R., Madhukumar, A. S. & Tan, E. Z. H. (2023). MultiNet: deep unsupervised power control for industrial MU-MIMO networks. Physical Communication, 60, 102158-. https://dx.doi.org/10.1016/j.phycom.2023.102158 1874-4907 https://hdl.handle.net/10356/175403 10.1016/j.phycom.2023.102158 2-s2.0-85172420615 60 102158 en Physical Communication © 2023 Elsevier B.V. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Resource allocation
Deep learning
Unsupervised learning
Power control
spellingShingle Engineering
Resource allocation
Deep learning
Unsupervised learning
Power control
Maiti, Ritabrata
Madhukumar, A. S.
Tan, Ernest Zheng Hui
MultiNet: deep unsupervised power control for industrial MU-MIMO networks
description This paper presents Multinet, an unsupervised deep learning (DL) approach for power allocation in industrial environments and IIoT applications. Multinet extends the previously proposed singular value decomposition network (SVDNet), which utilizes supervised DL to approximate the performance of the WMMSE algorithm. While SVDNet requires labeled data for training, limiting its scalability and generalization performance, in contrast, Multinet employs unsupervised DL to directly optimize the sum rate maximization objective function, eliminating the need for labeled datasets and improving training efficiency. Simulation studies are conducted to evaluate Multinet's performance in an industrial environment, utilizing parameters derived from measured large-scale fading characteristics of the industrial radio channel at 5200 MHz. The suitability of Multinet for industrial applications is thus assessed and numerical evaluations demonstrate that Multinet outperforms benchmark supervised and unsupervised DL-based power control schemes in terms of sum rate and energy efficiency.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Maiti, Ritabrata
Madhukumar, A. S.
Tan, Ernest Zheng Hui
format Article
author Maiti, Ritabrata
Madhukumar, A. S.
Tan, Ernest Zheng Hui
author_sort Maiti, Ritabrata
title MultiNet: deep unsupervised power control for industrial MU-MIMO networks
title_short MultiNet: deep unsupervised power control for industrial MU-MIMO networks
title_full MultiNet: deep unsupervised power control for industrial MU-MIMO networks
title_fullStr MultiNet: deep unsupervised power control for industrial MU-MIMO networks
title_full_unstemmed MultiNet: deep unsupervised power control for industrial MU-MIMO networks
title_sort multinet: deep unsupervised power control for industrial mu-mimo networks
publishDate 2024
url https://hdl.handle.net/10356/175403
_version_ 1800916319851249664