Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE Networks

The variations in the atmospheric refractivity in the lower atmosphere create a natural phenomenon known as atmospheric ducts. The atmospheric ducts allow radio signals to travel long distances. This can adversely affect telecommunication systems, as cells with similar frequencies can interfere with...

Full description

Saved in:
Bibliographic Details
Main Authors: Rasendram Muralitharan, Upul Jayasinghe, Roshan G. Ragel, Gyu Myoung Lee
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/6/237
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432667404107776
author Rasendram Muralitharan
Upul Jayasinghe
Roshan G. Ragel
Gyu Myoung Lee
author_facet Rasendram Muralitharan
Upul Jayasinghe
Roshan G. Ragel
Gyu Myoung Lee
author_sort Rasendram Muralitharan
collection DOAJ
description The variations in the atmospheric refractivity in the lower atmosphere create a natural phenomenon known as atmospheric ducts. The atmospheric ducts allow radio signals to travel long distances. This can adversely affect telecommunication systems, as cells with similar frequencies can interfere with each other due to frequency reuse, which is intended to optimize resource allocation. Thus, the downlink signals of one base station will travel a long distance via the atmospheric duct and interfere with the uplink signals of another base station. This scenario is known as atmospheric duct interference (ADI). ADI could be mitigated using digital signal processing, machine learning, and hybrid approaches. To address this challenge, we explore machine learning and deep learning techniques for ADI prediction and mitigation in Time-Division Long-Term Evolution (TD-LTE) networks. Our results show that the Random Forest algorithm achieves the highest prediction accuracy, while a convolutional neural network demonstrates the best mitigation performance with accuracy. Additionally, we propose optimizing special subframe configurations in TD-LTE networks using machine learning-based methods to effectively reduce ADI.
format Article
id doaj-art-915c2ec120af4f6e8ad22245f53dd31f
institution Kabale University
issn 1999-5903
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-915c2ec120af4f6e8ad22245f53dd31f2025-08-20T03:27:18ZengMDPI AGFuture Internet1999-59032025-05-0117623710.3390/fi17060237Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE NetworksRasendram Muralitharan0Upul Jayasinghe1Roshan G. Ragel2Gyu Myoung Lee3Department of Computer Engineering, Faculty of Engineering, University of Peradeniya, Peradeniya 20400, Sri LankaDepartment of Computer Engineering, Faculty of Engineering, University of Peradeniya, Peradeniya 20400, Sri LankaDepartment of Computer Engineering, Faculty of Engineering, University of Peradeniya, Peradeniya 20400, Sri LankaFaculty of Engineering and Technology, Liverpool John Moores University, Liverpool L3 3AF, UKThe variations in the atmospheric refractivity in the lower atmosphere create a natural phenomenon known as atmospheric ducts. The atmospheric ducts allow radio signals to travel long distances. This can adversely affect telecommunication systems, as cells with similar frequencies can interfere with each other due to frequency reuse, which is intended to optimize resource allocation. Thus, the downlink signals of one base station will travel a long distance via the atmospheric duct and interfere with the uplink signals of another base station. This scenario is known as atmospheric duct interference (ADI). ADI could be mitigated using digital signal processing, machine learning, and hybrid approaches. To address this challenge, we explore machine learning and deep learning techniques for ADI prediction and mitigation in Time-Division Long-Term Evolution (TD-LTE) networks. Our results show that the Random Forest algorithm achieves the highest prediction accuracy, while a convolutional neural network demonstrates the best mitigation performance with accuracy. Additionally, we propose optimizing special subframe configurations in TD-LTE networks using machine learning-based methods to effectively reduce ADI.https://www.mdpi.com/1999-5903/17/6/237TD-LTEADImachine learningSVMrandom forestLSTM
spellingShingle Rasendram Muralitharan
Upul Jayasinghe
Roshan G. Ragel
Gyu Myoung Lee
Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE Networks
Future Internet
TD-LTE
ADI
machine learning
SVM
random forest
LSTM
title Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE Networks
title_full Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE Networks
title_fullStr Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE Networks
title_full_unstemmed Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE Networks
title_short Machine Learning and Deep Learning-Based Atmospheric Duct Interference Detection and Mitigation in TD-LTE Networks
title_sort machine learning and deep learning based atmospheric duct interference detection and mitigation in td lte networks
topic TD-LTE
ADI
machine learning
SVM
random forest
LSTM
url https://www.mdpi.com/1999-5903/17/6/237
work_keys_str_mv AT rasendrammuralitharan machinelearninganddeeplearningbasedatmosphericductinterferencedetectionandmitigationintdltenetworks
AT upuljayasinghe machinelearninganddeeplearningbasedatmosphericductinterferencedetectionandmitigationintdltenetworks
AT roshangragel machinelearninganddeeplearningbasedatmosphericductinterferencedetectionandmitigationintdltenetworks
AT gyumyounglee machinelearninganddeeplearningbasedatmosphericductinterferencedetectionandmitigationintdltenetworks