COMPARATIVE PERFORMANCE OF DEEP LEARNING ARCHITECTURES FOR 5G NETWORK TRAFFIC CLASSIFICATION
DOI:
https://doi.org/10.21831/jited.v4i2.4048Keywords:
deep learning, klasifikasi trafik, 5G, performa komparatif, efisiensi komputasiAbstract
Studi ini melakukan evaluasi komparatif terhadap arsitektur deep learning (LSTM, BiLSTM, GRU, dan Transformer) untuk klasifikasi trafik jaringan 5G dengan fokus pada performa klasifikasi, efisiensi komputasi, dan ketahanan terhadap variasi trafik. Metode yang digunakan melibatkan pelatihan dan pengujian model pada dataset Key Performance Indicator (KPI) jaringan dengan analisis terhadap skor F1, waktu inferensi, dan jumlah parameter. Hasil menunjukkan bahwa model Transformer mencapai performa klasifikasi tertinggi (unggul secara statistik), tetapi membutuhkan waktu inferensi terpanjang (78,56 ms) meskipun memiliki jumlah parameter paling sedikit (4.696). Sebaliknya, model GRU menawarkan keseimbangan optimal antara performa (F1: 0,8822) dan efisiensi (waktu inferensi 31,44 ms; 27.609 parameter) sehingga cocok untuk skenario dengan keterbatasan sumber daya. Ukuran jendela optimal adalah 100 sampel KPI berturut-turut (25 detik), dan indikator skema modulasi dan pengodean merupakan fitur paling berpengaruh. Model LSTM menunjukkan ketahanan yang sangat baik (F1: 0,8780) di seluruh skenario variasi trafik. Simpulannya, pemilihan arsitektur melibatkan kompromi antara akurasi, efisiensi, dan ketahanan sesuai kebutuhan penerapan. Implikasi studi ini mencakup panduan pemilihan arsitektur berbasis bukti, konfirmasi keunggulan pemrosesan temporal Transformer, serta wawasan terkait alokasi sumber daya komputasi.
Downloads
References
3GPP. (2020). Management and orchestration: Architecture framework [Technical report]. 3GPP.
Andrews, J. G., Buzzi, S., Choi, W., Hanly, S. V., Lozano, A., Soong, A. C., & Zhang, J. C. (2014). What will 5G be? IEEE Journal on Selected Areas in Communications, 32, 1065–1082.
Bergstra, J., Bardenet, R., Bengio, Y., & Kégl, B. (2011). Algorithms for hyper-parameter optimization. In Advances in Neural Information Processing Systems (Vol. 24). Curran Associates.
Chatras, B., Kwong, U. S. T., & Bihannic, N. (2017). NFV enabling network slicing for 5G. In Proceedings of the 20th Conference on Innovations in Clouds, Internet and Networks (ICIN) (pp. 219–225).
Chen, W.-E., Fan, X.-Y., & Chen, L.-X. (2019). A CNN-based packet classification of eMBB, mMTC and URLLC applications for 5G. In Proceedings of the International Conference on Intelligent Computing and its Emerging Applications (ICEA) (pp. 140–145).
Chevalier, G. (2018). LSTM cell [Image]. Wikimedia Commons. Licensed under CC BY-SA 4.0.
Cornegruta, S., Bakewell, R., Withey, S., & Montana, G. (2016). Modeling radiological language with bidirectional long short-term memory networks. In Proceedings of the 7th International Workshop on Health Text Mining and Information Analysis (pp. 17–27).
Cyril, E. G., & Gaussier, G. (2005). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In J. M. L. Fernández-Luna (Ed.), Advances in information retrieval (pp. 345–359). Springer Berlin Heidelberg.
Dietterich, T. G. (1998). Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation, 10(7), 1895–1923.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
ITU. (2015). IMT Vision – Framework and overall objectives of the future development of IMT for 2020 and beyond (Recommendation ITU-R M.2083-0).
Jeblad. (2018). [Untitled] [Image]. Wikimedia Commons. Licensed under CC BY-SA 4.0 International.
Jia, Y. (2019). The transformer model architecture [Image]. Wikimedia Commons. https://commons.wikimedia.org/wiki/File:The-Transformer-model-architecture.png
Kaloxylos, A. (2018). A survey and an analysis of network slicing in 5G networks. IEEE Communications Standards Magazine, 2, 60–65.
Khodapanah, B., Awada, A., Viering, I., Barreto, A. N., Simsek, M., & Fettweis, G. (2020). Framework for slice-aware radio resource management utilizing artificial neural networks. IEEE Access, 8, 174972–174987.
LeCun, Y., Bottou, E., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition [Technical report].
Ma, X., Dai, Z., He, Z., Ma, J., Wang, Y., & Wang, Y. (2017). Learning traffic as images: A deep convolutional neural network for large-scale transportation network speed prediction. Sensors (Switzerland), 17.
Mareri, B., Boateng, G. O., Ou, R., Sun, G., Pang, Y., & Liu, G. (2022). MANTA: Multi-lane capsule network assisted traffic classification for 5G network slicing. IEEE Wireless Communications Letters, 11, 1905–1909.
Maxwell, A. E., Warner, T. A., & Guillén, L. A. (2021). Accuracy assessment in convolutional neural network-based deep learning remote sensing studies—Part 1: Literature review.
Menghani, G. (2023). Efficient deep learning: A survey on making deep learning models smaller, faster, and better.
NGMN Alliance. (2016). Description of network slicing concept. NGMN 5G P, 1, 1–11.
Nguyen, T. T., & Armitage, G. (2008). A survey of techniques for internet traffic classification using machine learning.
Nissar, I., Alam, S., & Masood, S. (2024). Computationally efficient LC-SCS deep learning model for breast cancer classification using thermal imaging. Neural Computing and Applications, 36, 16233–16250.
Ordonez-Lucena, J., Ameigeiras, P., Lopez, D., Ramos-Munoz, J. J., Lorca, J., & Folgueira, J. (2017). Network slicing for 5G with SDN/NFV: Concepts, architectures, and challenges. IEEE Communications Magazine, 55, 80–87.
Polese, M., Bonati, L., D'Oro, S., Basagni, S., & Melodia, T. (2023). Understanding O-RAN: Architecture, interfaces, algorithms, security, and research challenges. IEEE Communications Surveys and Tutorials, 25, 1376–1411.
Powers, D. M. W. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation.
Qiang, C. Q., Ping, L. J., Haq, A. U., He, L., & Haq, A. (2021). Net traffic classification based on GRU network using sequential features. In Proceedings of the 18th International Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) (pp. 460–465).
Raschka, S. (2018). Model evaluation, model selection, and algorithm selection in machine learning (arXiv:1811.12808). arXiv.
Rezaei, S., & Liu, X. (2019). Deep learning for encrypted traffic classification: An overview.
Sharma, S., Deivakani, M., Reddy, K. S., Gnanasekar, A. K., & Aparna, G. (2021). Key enabling technologies of 5G wireless mobile communication. Journal of Physics: Conference Series, 1817, 012003.
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427–437.
Thantharate, A., Paropkari, R. A., Walunj, V., & Beard, C. C. (2019). DeepSlice: A deep learning approach towards an efficient and reliable network slicing in 5G networks. In Proceedings of the 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) (pp. 762–767).
TSGS. (2021). TS 128 533 - V16.7.0 - 5G; Management and orchestration; Architecture framework (3GPP TS 28.533 version 16.7.0 Release 16) [Technical report]. ETSI 3rd Generation Partnership Project (3GPP).
Yang, H., So, T., & Xu, Y. (2022). 5G network slicing. In J. Shen, Z. Du, Z. Zhang, N. Yang, & H. Tang (Eds.), 5G NR and enhancements (pp. 621–639). Elsevier.
Zhang, H., Liu, N., Chu, X., Long, K., Aghvami, A. H., & Leung, V. C. (2017). Network slicing based 5G and future mobile networks: Mobility, resource management, and challenges. IEEE Communications Magazine, 55, 138–145.
Zhang, W., Wang, J., Chen, S., Qi, H., & Li, K. (2019). A framework for resource-aware online traffic classification using CNN. In ACM International Conference Proceeding Series.
Zhao, R., Zhan, M., Deng, X., Wang, Y., Wang, Y., Gui, G., & Xue, Z. (2023). Yet another traffic classifier: A masked autoencoder based traffic transformer with multi-level flow representation. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023) (Vol. 37, pp. 5420–5427). AAAI Press.
Zheng, W., Zhong, J., Zhang, Q., & Zhao, G. (2022). MTT: An efficient model for encrypted network traffic classification using multi-task transformer. Applied Intelligence, 52, 10741–10756.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Information Technology and Education (JITED)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
