A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMO
The emergence of 6G wireless networks presents new challenges, for which cell-free massive MIMO combined with machine learning (ML) offers a promising solution. A key requirement for practical deployment is the generalizability of ML models—their ability to maintain robust performance across varying...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/13/3845 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839631588579606528 |
|---|---|
| author | Guillermo García-Barrios Manuel Fuentes David Martín-Sacristán |
| author_facet | Guillermo García-Barrios Manuel Fuentes David Martín-Sacristán |
| author_sort | Guillermo García-Barrios |
| collection | DOAJ |
| description | The emergence of 6G wireless networks presents new challenges, for which cell-free massive MIMO combined with machine learning (ML) offers a promising solution. A key requirement for practical deployment is the generalizability of ML models—their ability to maintain robust performance across varying propagation conditions, user distributions, and network topologies. However, achieving generalizability typically demands large, diverse training datasets and high model complexity, which can hinder practical feasibility. This study analyzes the robustness of a low-complexity deep neural network (DNN) trained for power control under a single network configuration. The model’s robustness is assessed by testing it across a wide range of unseen scenarios, including changes in the number of access points, user equipment, and propagation environments. The DNN is trained to emulate three power control schemes: max-min spectral efficiency (SE) fairness, sum SE maximization, and fractional power control. To rigorously evaluate robustness, we compare the cumulative distribution functions of performance metrics quantitatively using the Kolmogorov–Smirnov test. Results show strong robustness, particularly for the sum SE scheme, with D statistics below 0.05 and <i>p</i>-values above 0.001. This work provides a reproducible framework and dataset to support further research into practical ML-based power control in cell-free massive MIMO systems. |
| format | Article |
| id | doaj-art-f77d1a29febf4d06b859b8da1d315eb4 |
| institution | Matheson Library |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-f77d1a29febf4d06b859b8da1d315eb42025-07-11T14:42:44ZengMDPI AGSensors1424-82202025-06-012513384510.3390/s25133845A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMOGuillermo García-Barrios0Manuel Fuentes1David Martín-Sacristán25G Communications for Future Industry Verticals S.L. (Fivecomm), Camí de Vera s/n (6D Building), 46022 Valencia, Spain5G Communications for Future Industry Verticals S.L. (Fivecomm), Camí de Vera s/n (6D Building), 46022 Valencia, SpainiTEAM Research Institute, Universitat Politècnica de València, 46022 Valencia, SpainThe emergence of 6G wireless networks presents new challenges, for which cell-free massive MIMO combined with machine learning (ML) offers a promising solution. A key requirement for practical deployment is the generalizability of ML models—their ability to maintain robust performance across varying propagation conditions, user distributions, and network topologies. However, achieving generalizability typically demands large, diverse training datasets and high model complexity, which can hinder practical feasibility. This study analyzes the robustness of a low-complexity deep neural network (DNN) trained for power control under a single network configuration. The model’s robustness is assessed by testing it across a wide range of unseen scenarios, including changes in the number of access points, user equipment, and propagation environments. The DNN is trained to emulate three power control schemes: max-min spectral efficiency (SE) fairness, sum SE maximization, and fractional power control. To rigorously evaluate robustness, we compare the cumulative distribution functions of performance metrics quantitatively using the Kolmogorov–Smirnov test. Results show strong robustness, particularly for the sum SE scheme, with D statistics below 0.05 and <i>p</i>-values above 0.001. This work provides a reproducible framework and dataset to support further research into practical ML-based power control in cell-free massive MIMO systems.https://www.mdpi.com/1424-8220/25/13/3845cell-free massive MIMOpower controldeep neural networksrobustnessspectral efficiency6G wireless |
| spellingShingle | Guillermo García-Barrios Manuel Fuentes David Martín-Sacristán A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMO Sensors cell-free massive MIMO power control deep neural networks robustness spectral efficiency 6G wireless |
| title | A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMO |
| title_full | A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMO |
| title_fullStr | A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMO |
| title_full_unstemmed | A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMO |
| title_short | A Study on the Robustness of a DNN Under Scenario Shifts for Power Control in Cell-Free Massive MIMO |
| title_sort | study on the robustness of a dnn under scenario shifts for power control in cell free massive mimo |
| topic | cell-free massive MIMO power control deep neural networks robustness spectral efficiency 6G wireless |
| url | https://www.mdpi.com/1424-8220/25/13/3845 |
| work_keys_str_mv | AT guillermogarciabarrios astudyontherobustnessofadnnunderscenarioshiftsforpowercontrolincellfreemassivemimo AT manuelfuentes astudyontherobustnessofadnnunderscenarioshiftsforpowercontrolincellfreemassivemimo AT davidmartinsacristan astudyontherobustnessofadnnunderscenarioshiftsforpowercontrolincellfreemassivemimo AT guillermogarciabarrios studyontherobustnessofadnnunderscenarioshiftsforpowercontrolincellfreemassivemimo AT manuelfuentes studyontherobustnessofadnnunderscenarioshiftsforpowercontrolincellfreemassivemimo AT davidmartinsacristan studyontherobustnessofadnnunderscenarioshiftsforpowercontrolincellfreemassivemimo |