A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks
In light of the high bit error rate in satellite network links, the traditional transmission control protocol (TCP) fails to distinguish between congestion and wireless losses, and existing loss differentiation methods lack heterogeneous ensemble learning models, especially feature selection for los...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/25/12/1642 |
| _version_ | 1797381100230672384 |
|---|---|
| author | Debin Wei Chuanqi Guo Li Yang Yongqiang Xu |
| author_facet | Debin Wei Chuanqi Guo Li Yang Yongqiang Xu |
| author_sort | Debin Wei |
| collection | DOAJ |
| description | In light of the high bit error rate in satellite network links, the traditional transmission control protocol (TCP) fails to distinguish between congestion and wireless losses, and existing loss differentiation methods lack heterogeneous ensemble learning models, especially feature selection for loss differentiation, individual classifier selection methods, effective ensemble strategies, etc. A loss differentiation method based on heterogeneous ensemble learning (LDM-HEL) for low-Earth-orbit (LEO) satellite networks is proposed. This method utilizes the Relief and mutual information algorithms for selecting loss differentiation features and employs the least-squares support vector machine, decision tree, logistic regression, and K-nearest neighbor as individual learners. An ensemble strategy is designed using the stochastic gradient descent method to optimize the weights of individual learners. Simulation results demonstrate that the proposed LDM-HEL achieves higher accuracy rate, recall rate, and F1-score in the simulation scenario, and significantly improves throughput performance when applied to TCP. Compared with the integrated model LDM-satellite, the above indexes can be improved by 4.37%, 4.55%, 4.87%, and 9.28%, respectively. |
| first_indexed | 2024-03-08T20:47:32Z |
| format | Article |
| id | doaj.art-296bd84973324a95bbf5cfd534dcc7bb |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-08T20:47:32Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-296bd84973324a95bbf5cfd534dcc7bb2023-12-22T14:07:28ZengMDPI AGEntropy1099-43002023-12-012512164210.3390/e25121642A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite NetworksDebin Wei0Chuanqi Guo1Li Yang2Yongqiang Xu3Communication and Network Laboratory, College of Information Engineering, Dalian University, Dalian 116622, ChinaCommunication and Network Laboratory, College of Information Engineering, Dalian University, Dalian 116622, ChinaSchool of Automation, Nanjing University of Science and Technology, Nanjing 210094, ChinaCommunication and Network Laboratory, College of Information Engineering, Dalian University, Dalian 116622, ChinaIn light of the high bit error rate in satellite network links, the traditional transmission control protocol (TCP) fails to distinguish between congestion and wireless losses, and existing loss differentiation methods lack heterogeneous ensemble learning models, especially feature selection for loss differentiation, individual classifier selection methods, effective ensemble strategies, etc. A loss differentiation method based on heterogeneous ensemble learning (LDM-HEL) for low-Earth-orbit (LEO) satellite networks is proposed. This method utilizes the Relief and mutual information algorithms for selecting loss differentiation features and employs the least-squares support vector machine, decision tree, logistic regression, and K-nearest neighbor as individual learners. An ensemble strategy is designed using the stochastic gradient descent method to optimize the weights of individual learners. Simulation results demonstrate that the proposed LDM-HEL achieves higher accuracy rate, recall rate, and F1-score in the simulation scenario, and significantly improves throughput performance when applied to TCP. Compared with the integrated model LDM-satellite, the above indexes can be improved by 4.37%, 4.55%, 4.87%, and 9.28%, respectively.https://www.mdpi.com/1099-4300/25/12/1642LEO satellite networksloss differentiationensemble strategyheterogeneous ensemble learning |
| spellingShingle | Debin Wei Chuanqi Guo Li Yang Yongqiang Xu A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks Entropy LEO satellite networks loss differentiation ensemble strategy heterogeneous ensemble learning |
| title | A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks |
| title_full | A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks |
| title_fullStr | A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks |
| title_full_unstemmed | A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks |
| title_short | A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks |
| title_sort | loss differentiation method based on heterogeneous ensemble learning model for low earth orbit satellite networks |
| topic | LEO satellite networks loss differentiation ensemble strategy heterogeneous ensemble learning |
| url | https://www.mdpi.com/1099-4300/25/12/1642 |
| work_keys_str_mv | AT debinwei alossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks AT chuanqiguo alossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks AT liyang alossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks AT yongqiangxu alossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks AT debinwei lossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks AT chuanqiguo lossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks AT liyang lossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks AT yongqiangxu lossdifferentiationmethodbasedonheterogeneousensemblelearningmodelforlowearthorbitsatellitenetworks |