Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning
Following the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio ch...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/22/7716 |
_version_ | 1797508422639288320 |
---|---|
author | Krzysztof K. Cwalina Piotr Rajchowski Alicja Olejniczak Olga Błaszkiewicz Robert Burczyk |
author_facet | Krzysztof K. Cwalina Piotr Rajchowski Alicja Olejniczak Olga Błaszkiewicz Robert Burczyk |
author_sort | Krzysztof K. Cwalina |
collection | DOAJ |
description | Following the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio channel parameters of the LTE (Long Term Evolution) radio interface is presented. It was proved that the deep learning approach provides a significant gain (almost 40%) with 10.7% compared to the linear model with the lowest RMSE (Root Mean Squared Error) 17.01%. The solution can be adopted as a part of the data allocation algorithm implemented in the telemetry devices equipped with the 4G radio interface, or, after the adjustment, the NB-IoT (Narrowband Internet of Things), to maximize the reliability of the services in harsh indoor or urban environments. Presented results also prove the existence of the inverse proportional dependence between the number of hidden layers and the number of historical samples in terms of the obtained RMSE. The increase of the historical data memory allows using models with fewer hidden layers while maintaining a comparable RMSE value for each scenario, which reduces the total computational cost. |
first_indexed | 2024-03-10T05:03:50Z |
format | Article |
id | doaj.art-217152518b9a45b3ae85889bdbeac016 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T05:03:50Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-217152518b9a45b3ae85889bdbeac0162023-11-23T01:28:31ZengMDPI AGSensors1424-82202021-11-012122771610.3390/s21227716Channel State Estimation in LTE-Based Heterogenous Networks Using Deep LearningKrzysztof K. Cwalina0Piotr Rajchowski1Alicja Olejniczak2Olga Błaszkiewicz3Robert Burczyk4Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233 Gdansk, PolandFaculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233 Gdansk, PolandFaculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233 Gdansk, PolandFaculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233 Gdansk, PolandFaculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233 Gdansk, PolandFollowing the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio channel parameters of the LTE (Long Term Evolution) radio interface is presented. It was proved that the deep learning approach provides a significant gain (almost 40%) with 10.7% compared to the linear model with the lowest RMSE (Root Mean Squared Error) 17.01%. The solution can be adopted as a part of the data allocation algorithm implemented in the telemetry devices equipped with the 4G radio interface, or, after the adjustment, the NB-IoT (Narrowband Internet of Things), to maximize the reliability of the services in harsh indoor or urban environments. Presented results also prove the existence of the inverse proportional dependence between the number of hidden layers and the number of historical samples in terms of the obtained RMSE. The increase of the historical data memory allows using models with fewer hidden layers while maintaining a comparable RMSE value for each scenario, which reduces the total computational cost.https://www.mdpi.com/1424-8220/21/22/7716deep learningheterogeneous networkchannel stateLTE |
spellingShingle | Krzysztof K. Cwalina Piotr Rajchowski Alicja Olejniczak Olga Błaszkiewicz Robert Burczyk Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning Sensors deep learning heterogeneous network channel state LTE |
title | Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning |
title_full | Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning |
title_fullStr | Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning |
title_full_unstemmed | Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning |
title_short | Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning |
title_sort | channel state estimation in lte based heterogenous networks using deep learning |
topic | deep learning heterogeneous network channel state LTE |
url | https://www.mdpi.com/1424-8220/21/22/7716 |
work_keys_str_mv | AT krzysztofkcwalina channelstateestimationinltebasedheterogenousnetworksusingdeeplearning AT piotrrajchowski channelstateestimationinltebasedheterogenousnetworksusingdeeplearning AT alicjaolejniczak channelstateestimationinltebasedheterogenousnetworksusingdeeplearning AT olgabłaszkiewicz channelstateestimationinltebasedheterogenousnetworksusingdeeplearning AT robertburczyk channelstateestimationinltebasedheterogenousnetworksusingdeeplearning |