FPGA-Based Network Traffic Classification Using Machine Learning
Real-time classification of internet traffic is critical for the efficient management of networks. Classification approaches based on machine learning techniques have shown promising results with high levels of accuracy. In this paper, the suitability of packet-level and flow-level features is valid...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , |
| التنسيق: | article |
| منشور في: |
2020
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | http://hdl.handle.net/11073/19796 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513433365381120 |
|---|---|
| author | Elnawawy, Mohammed |
| author2 | Sagahyroon, Assim Shanableh, Tamer |
| author2_role | author author |
| author_facet | Elnawawy, Mohammed Sagahyroon, Assim Shanableh, Tamer |
| author_role | author |
| dc.creator.none.fl_str_mv | Elnawawy, Mohammed Sagahyroon, Assim Shanableh, Tamer |
| dc.date.none.fl_str_mv | 2020-09-27T09:14:20Z 2020-09-27T09:14:20Z 2020 |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | M. Elnawawy, A. Sagahyroon and T. Shanableh, "FPGA-Based Network Traffic Classification Using Machine Learning," in IEEE Access, doi: 10.1109/ACCESS.2020.3026831. 2169-3536 http://hdl.handle.net/11073/19796 10.1109/ACCESS.2020.3026831 |
| dc.language.none.fl_str_mv | en_US |
| dc.publisher.none.fl_str_mv | IEEE Xplore |
| dc.relation.none.fl_str_mv | https://ieeexplore.ieee.org/document/9205799 |
| dc.subject.none.fl_str_mv | Feature extraction FPGA Machine learning Random forest Traffic classification |
| dc.title.none.fl_str_mv | FPGA-Based Network Traffic Classification Using Machine Learning |
| dc.type.none.fl_str_mv | Peer-Reviewed Published version info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
| description | Real-time classification of internet traffic is critical for the efficient management of networks. Classification approaches based on machine learning techniques have shown promising results with high levels of accuracy. In this paper, the suitability of packet-level and flow-level features is validated using stepwise regression and random forest feature selection. Moreover, the optimal percentage of packets considered within a flow while extracting flow-level features is determined. Several experiments are conducted using naïve Bayes, support vector machine, k-nearest neighbor, random forest, and artificial neural networks on the University of Brescia (UNIBS) and the University of New Brunswick (UNB) datasets, which are both publicly available. The performed experiments show that 60% of flow packets are a good compromise that ensures high performance in the least processing time. The results of the conducted experiments indicate that random forest outperforms other algorithms achieving a maximum accuracy of 98.5% and an F-score of 0.932. Further, and since software-based classifiers cannot meet the anticipated real-time requirements, we propose a Field-Programmable Gate Array (FPGA) based random forest implementation that utilizes a highly pipelined architecture to accelerate such a time-consuming task. The proposed design achieves an average throughput of 163.24 Gbps, exceeding throughputs of reported hardware-based classifiers that use comparable approaches, which in turn ensures the continuity of realtime traffic classification at congested data centers. |
| format | article |
| id | aus_3424642754bc116c52c3db73fa897f16 |
| identifier_str_mv | M. Elnawawy, A. Sagahyroon and T. Shanableh, "FPGA-Based Network Traffic Classification Using Machine Learning," in IEEE Access, doi: 10.1109/ACCESS.2020.3026831. 2169-3536 10.1109/ACCESS.2020.3026831 |
| language_invalid_str_mv | en_US |
| network_acronym_str | aus |
| network_name_str | aus |
| oai_identifier_str | oai:repository.aus.edu:11073/19796 |
| publishDate | 2020 |
| publisher.none.fl_str_mv | IEEE Xplore |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | FPGA-Based Network Traffic Classification Using Machine LearningElnawawy, MohammedSagahyroon, AssimShanableh, TamerFeature extractionFPGAMachine learningRandom forestTraffic classificationReal-time classification of internet traffic is critical for the efficient management of networks. Classification approaches based on machine learning techniques have shown promising results with high levels of accuracy. In this paper, the suitability of packet-level and flow-level features is validated using stepwise regression and random forest feature selection. Moreover, the optimal percentage of packets considered within a flow while extracting flow-level features is determined. Several experiments are conducted using naïve Bayes, support vector machine, k-nearest neighbor, random forest, and artificial neural networks on the University of Brescia (UNIBS) and the University of New Brunswick (UNB) datasets, which are both publicly available. The performed experiments show that 60% of flow packets are a good compromise that ensures high performance in the least processing time. The results of the conducted experiments indicate that random forest outperforms other algorithms achieving a maximum accuracy of 98.5% and an F-score of 0.932. Further, and since software-based classifiers cannot meet the anticipated real-time requirements, we propose a Field-Programmable Gate Array (FPGA) based random forest implementation that utilizes a highly pipelined architecture to accelerate such a time-consuming task. The proposed design achieves an average throughput of 163.24 Gbps, exceeding throughputs of reported hardware-based classifiers that use comparable approaches, which in turn ensures the continuity of realtime traffic classification at congested data centers.IEEE Xplore2020-09-27T09:14:20Z2020-09-27T09:14:20Z2020Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfM. Elnawawy, A. Sagahyroon and T. Shanableh, "FPGA-Based Network Traffic Classification Using Machine Learning," in IEEE Access, doi: 10.1109/ACCESS.2020.3026831.2169-3536http://hdl.handle.net/11073/1979610.1109/ACCESS.2020.3026831en_UShttps://ieeexplore.ieee.org/document/9205799oai:repository.aus.edu:11073/197962024-08-22T12:07:24Z |
| spellingShingle | FPGA-Based Network Traffic Classification Using Machine Learning Elnawawy, Mohammed Feature extraction FPGA Machine learning Random forest Traffic classification |
| status_str | publishedVersion |
| title | FPGA-Based Network Traffic Classification Using Machine Learning |
| title_full | FPGA-Based Network Traffic Classification Using Machine Learning |
| title_fullStr | FPGA-Based Network Traffic Classification Using Machine Learning |
| title_full_unstemmed | FPGA-Based Network Traffic Classification Using Machine Learning |
| title_short | FPGA-Based Network Traffic Classification Using Machine Learning |
| title_sort | FPGA-Based Network Traffic Classification Using Machine Learning |
| topic | Feature extraction FPGA Machine learning Random forest Traffic classification |
| url | http://hdl.handle.net/11073/19796 |