Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNN
Data traffic in cellular networks has surged due to the growing number of users and high-bandwidth applications. The quality of service (QoS) for users will degrade if the network resources cannot handle the increasing traffic volume. A user’s application requires a minimum throughput to...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838521/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207036281880576 |
|---|---|
| author | Kukuh Nugroho Hendrawan Iskandar |
| author_facet | Kukuh Nugroho Hendrawan Iskandar |
| author_sort | Kukuh Nugroho |
| collection | DOAJ |
| description | Data traffic in cellular networks has surged due to the growing number of users and high-bandwidth applications. The quality of service (QoS) for users will degrade if the network resources cannot handle the increasing traffic volume. A user’s application requires a minimum throughput to maintain QoS levels above the Service Level Agreement (SLA) promised by the operator. The network’s ability to handle traffic growth will depend on well-prepared network resource management. KPI traffic prediction is one solution to anticipate traffic surges. This study utilized Federated Learning (FL) as a machine learning paradigm and employed CNN as a model to predict throughput in the cellular network. The efficacy of the model is compared with Centralized Learning (CL) and other deep learning models, including MLP, RNN, LSTM, and GRU. The experimental results indicate that the CNN model implemented in FL outperforms both CL and the other models. The number of rounds used in the FL system is held in two rounds, and the model’s performance remains steady with an increasing number of clients, showing superior performance compared to CL. |
| format | Article |
| id | doaj-art-9c034c24d6cd4021ac26c854c4a83668 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-9c034c24d6cd4021ac26c854c4a836682025-02-07T00:01:14ZengIEEEIEEE Access2169-35362025-01-0113227452276310.1109/ACCESS.2025.352852710838521Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNNKukuh Nugroho0https://orcid.org/0009-0002-3010-1155 Hendrawan1 Iskandar2School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, IndonesiaSchool of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, IndonesiaSchool of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, IndonesiaData traffic in cellular networks has surged due to the growing number of users and high-bandwidth applications. The quality of service (QoS) for users will degrade if the network resources cannot handle the increasing traffic volume. A user’s application requires a minimum throughput to maintain QoS levels above the Service Level Agreement (SLA) promised by the operator. The network’s ability to handle traffic growth will depend on well-prepared network resource management. KPI traffic prediction is one solution to anticipate traffic surges. This study utilized Federated Learning (FL) as a machine learning paradigm and employed CNN as a model to predict throughput in the cellular network. The efficacy of the model is compared with Centralized Learning (CL) and other deep learning models, including MLP, RNN, LSTM, and GRU. The experimental results indicate that the CNN model implemented in FL outperforms both CL and the other models. The number of rounds used in the FL system is held in two rounds, and the model’s performance remains steady with an increasing number of clients, showing superior performance compared to CL.https://ieeexplore.ieee.org/document/10838521/Federated learningthroughput predictioncellular networkdistributed learningconvolutional neural networkdropout |
| spellingShingle | Kukuh Nugroho Hendrawan Iskandar Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNN IEEE Access Federated learning throughput prediction cellular network distributed learning convolutional neural network dropout |
| title | Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNN |
| title_full | Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNN |
| title_fullStr | Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNN |
| title_full_unstemmed | Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNN |
| title_short | Comparative Analysis of Federated and Centralized Learning Systems in Predicting Cellular Downlink Throughput Using CNN |
| title_sort | comparative analysis of federated and centralized learning systems in predicting cellular downlink throughput using cnn |
| topic | Federated learning throughput prediction cellular network distributed learning convolutional neural network dropout |
| url | https://ieeexplore.ieee.org/document/10838521/ |
| work_keys_str_mv | AT kukuhnugroho comparativeanalysisoffederatedandcentralizedlearningsystemsinpredictingcellulardownlinkthroughputusingcnn AT hendrawan comparativeanalysisoffederatedandcentralizedlearningsystemsinpredictingcellulardownlinkthroughputusingcnn AT iskandar comparativeanalysisoffederatedandcentralizedlearningsystemsinpredictingcellulardownlinkthroughputusingcnn |