A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios
This paper presents TCReC, an innovative model designed for reconstructing network traffic characteristics in the presence of packet loss. With the rapid expansion of wireless networks driven by edge computing, IoT, and 5G technologies, challenges such as transmission instability, channel competitio...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/17/5/208 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850126881327677440 |
|---|---|
| author | Jiawei Ye Yanting Chen Aierpanjiang Simayi Yu Liu Zhihui Lu Jie Wu |
| author_facet | Jiawei Ye Yanting Chen Aierpanjiang Simayi Yu Liu Zhihui Lu Jie Wu |
| author_sort | Jiawei Ye |
| collection | DOAJ |
| description | This paper presents TCReC, an innovative model designed for reconstructing network traffic characteristics in the presence of packet loss. With the rapid expansion of wireless networks driven by edge computing, IoT, and 5G technologies, challenges such as transmission instability, channel competition, and environmental interference have led to significant packet loss rates, adversely impacting deep learning-based network traffic analysis tasks. To address this issue, TCReC leverages masked autoencoder techniques to reconstruct missing traffic features, ensuring reliable input for downstream tasks in edge computing scenarios. Experimental results demonstrate that TCReC maintains detection model accuracy within 10% of the original data, even under packet loss rates as high as 70%. For instance, on the ISCX-VPN-2016 dataset, TCReC achieves a Reconstruction Ability Index (RAI) of 94.02%, while on the CIC-IDS-2017 dataset, it achieves an RAI of 94.99% when combined with LSTM, significantly outperforming other methods such as Transformer, KNN, and RNN. Additionally, TCReC exhibits robustness across various packet loss scenarios, consistently delivering high-quality feature reconstruction for both attack traffic and common Internet application data. TCReC provides a robust solution for network traffic analysis in high-loss edge computing scenarios, offering practical value for real-world deployment. |
| format | Article |
| id | doaj-art-bd6e4f256b1541d09d1a612a1e2c8d49 |
| institution | OA Journals |
| issn | 1999-5903 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj-art-bd6e4f256b1541d09d1a612a1e2c8d492025-08-20T02:33:50ZengMDPI AGFuture Internet1999-59032025-05-0117520810.3390/fi17050208A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing ScenariosJiawei Ye0Yanting Chen1Aierpanjiang Simayi2Yu Liu3Zhihui Lu4Jie Wu5School of Computer Science, Fudan University, Shanghai 200433, ChinaSchool of Computer Science, Fudan University, Shanghai 200433, ChinaSchool of Computer Science, Fudan University, Shanghai 200433, ChinaSchool of Computer Science, Fudan University, Shanghai 200433, ChinaSchool of Computer Science, Fudan University, Shanghai 200433, ChinaSchool of Computer Science, Fudan University, Shanghai 200433, ChinaThis paper presents TCReC, an innovative model designed for reconstructing network traffic characteristics in the presence of packet loss. With the rapid expansion of wireless networks driven by edge computing, IoT, and 5G technologies, challenges such as transmission instability, channel competition, and environmental interference have led to significant packet loss rates, adversely impacting deep learning-based network traffic analysis tasks. To address this issue, TCReC leverages masked autoencoder techniques to reconstruct missing traffic features, ensuring reliable input for downstream tasks in edge computing scenarios. Experimental results demonstrate that TCReC maintains detection model accuracy within 10% of the original data, even under packet loss rates as high as 70%. For instance, on the ISCX-VPN-2016 dataset, TCReC achieves a Reconstruction Ability Index (RAI) of 94.02%, while on the CIC-IDS-2017 dataset, it achieves an RAI of 94.99% when combined with LSTM, significantly outperforming other methods such as Transformer, KNN, and RNN. Additionally, TCReC exhibits robustness across various packet loss scenarios, consistently delivering high-quality feature reconstruction for both attack traffic and common Internet application data. TCReC provides a robust solution for network traffic analysis in high-loss edge computing scenarios, offering practical value for real-world deployment.https://www.mdpi.com/1999-5903/17/5/208edge computingnetwork traffic analysispacket lossnetwork traffic characteristic reconstruction |
| spellingShingle | Jiawei Ye Yanting Chen Aierpanjiang Simayi Yu Liu Zhihui Lu Jie Wu A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios Future Internet edge computing network traffic analysis packet loss network traffic characteristic reconstruction |
| title | A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios |
| title_full | A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios |
| title_fullStr | A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios |
| title_full_unstemmed | A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios |
| title_short | A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios |
| title_sort | network traffic characteristics reconstruction method for mitigating the impact of packet loss in edge computing scenarios |
| topic | edge computing network traffic analysis packet loss network traffic characteristic reconstruction |
| url | https://www.mdpi.com/1999-5903/17/5/208 |
| work_keys_str_mv | AT jiaweiye anetworktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT yantingchen anetworktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT aierpanjiangsimayi anetworktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT yuliu anetworktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT zhihuilu anetworktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT jiewu anetworktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT jiaweiye networktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT yantingchen networktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT aierpanjiangsimayi networktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT yuliu networktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT zhihuilu networktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios AT jiewu networktrafficcharacteristicsreconstructionmethodformitigatingtheimpactofpacketlossinedgecomputingscenarios |