隨著5G通訊與多媒體串流應用的普及，提升網路傳輸效率與可靠性成為研究重點；然而，雖然TCP協定已經被調校至最符合現代網路傳輸的需求了，還是有需多不夠完整的部分，比如對於傳輸過程的加密需要額外的應用程式、經常遇到Head-of-Line（HoL）阻塞等問題。因此，如何在不修改原有架構的前提上，又保留TCP/UDP的優點，並且額外添加一些有利於傳輸的功能，成為了近年來對於傳輸的主要研究方向。
本研究以QUIC為出發點，並且採用多路徑傳輸協議--MPQUIC為傳輸方式，來模擬網路實體層為LTE、5G網路時的傳送，並且採用了D-OLIA混合式壅塞控制演算法進行實作，於ns-3網路模擬平台進行效能分析。從研究結果顯示，透過在MPQUIC中實作D-OLIA演算法，能有效提升多路徑傳輸的效能，特別是在異質網路環境（如LTE與5G的混合網路）中，能更迅速地適應網路變化，減少延遲與提高頻寬利用率。

With the widespread adoption of 5G communications and multimedia streaming applications, improving network transmission efficiency and reliability has become a key research focus. Although the TCP protocol has been optimized to meet modern networking demands, several limitations remain, such as the need for additional applications to enable encryption during transmission and frequent occurrences of Head-of-Line (HoL) blocking. Therefore, recent research has focused on enhancing transmission performance by introducing new functionalities while retaining the advantages of TCP/UDP and without modifying the existing network architecture.

This study is based on QUIC and employs MPQUIC, a multipath transmission protocol, to simulate data transmission over LTE and 5G networks. A hybrid congestion control algorithm, D-OLIA, was implemented on the ns-3 network simulation platform to evaluate its performance. The results demonstrate that integrating D-OLIA into MPQUIC significantly improves multipath transmission performance, particularly in heterogeneous network environments (such as mixed LTE and 5G networks), by enabling faster adaptation to network variations, reducing latency, and improving bandwidth utilization.

[1] Alvise De Biasio, Federico Chiariotti, Michele Polese, Andrea Zanella, and Michele Zorzi. 2019. A QUIC Implementation for ns-3. In Proceedings of the 2019 Workshop on ns-3 (WNS3 '19). Association for Computing Machinery, New York, NY, USA, 1–8.
[2] Shan Chen, Samuel Jero, Matthew Jagielski, Alexandra Boldyreva, and Cristina Nita-Rotaru. 2021. Secure Communication Channel Establishment: TLS 1.3 (over TCP Fast Open) versus QUIC. J. Cryptol. 34, 3 (Jul 2021).
[3] DebugBear, "HTTP/3 and QUIC: The complete guide," DebugBear. [Online]. Available: https://www.debugbear.com/blog/http3-quic-protocol-guide.
[4] Shengjie Shu, Wenjun Yang, Jianping Pan, and Lin Cai. 2023. A Multipath Extension to the QUIC Module for ns-3. In Proceedings of the 2023 Workshop on ns-3 (WNS3 '23). Association for Computing Machinery, New York, NY, USA, 86–93.
[5] H. Wu, Ö. Alay, A. Brunstrom, S. Ferlin and G. Caso, "Peekaboo: Learning-Based Multipath Scheduling for Dynamic Heterogeneous Environments," in IEEE Journal on Selected Areas in Communications, vol. 38, no. 10, pp. 2295-2310, Oct. 2020, doi: 10.1109/JSAC.2020.3000365.
[6] Lubna, T.; Mahmud, I.; Kim, G.-H.; Cho, Y.-Z. D-OLIA: A Hybrid MPTCP Congestion Control Algorithm with Network Delay Estimation. Sensors 2021, 21, 5764
[7] Kheirkhah, M., Wakeman, I., & Parisis, G. (2014). Multipath-TCP in ns-3. In The Workshop on ns-3 (WNS3 2014)
[8] S L. Zhang et al., "DeepPath: Multi-path Traffic Scheduling Algorithm for 5G High Dynamic Network," 2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys), Hainan, China, 2022, pp. 490-498
[9] D. Scharnitzky, Z. Krämer, S. Molnár, and A. Mihály, “Real-time Emulation of MASQUE-based QUIC Proxying in LTE Networks using ns-3,” Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning (CACML 2023), Shanghai, China, Mar. 2023, pp. 581–586.
[10] M. Mezzavilla, M. Zhang, M. Polese, R. Ford, S. Dutta, S. Rangan, and M. Zorzi, “End-to-End Simulation of 5G mmWave Networks,” IEEE Communications Surveys & Tutorials, vol. 20, no. 3, pp. 2237–2263, Third Quarter 2018
[11] A. Sharma and A. Banerjee, “Formal Analysis of QUIC Handshake Protocol Using Symbolic Model Verification,” Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning (CACML 2023), Shanghai, China, Mar. 2023, pp. 531–539.
[12] T. L. Habibi and R. F. Sari, “Performance Evaluation of QUIC Protocol in Message Replication Overhead in PBFT Consensus using NS-3,” International Journal of Electrical, Computer and Biomedical Engineering (IJECBE), vol. 1, no. 1, pp. 44–56, Sep. 2023
[13] Y. He, C. Liu, C. Lin, J. Ren and Y. Xu, “Fairness Analysis of Deep Reinforcement Learning based Multi-path QUIC Scheduling,” in Proceedings of the 2023 IEEE 48th Conference on Local Computer Networks (LCN), Daytona Beach, FL, USA, 2023, pp. 362–365
[14] R. Khalili, N. Gast, M. Popovic and J.-Y. Le Boudec, “MPTCP is not Pareto-Optimal: Performance Issues and a Possible Solution,” in IEEE/ACM Transactions on Networking, vol. 21, no. 5, pp. 1651–1665, Oct. 2013
[15] D. Scharnitzky, Z. Krämer, S. Molnár and A. Mihály, “Real-time Emulation of MASQUE-based QUIC Proxying in LTE Networks using ns-3,” in Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning (CACML 2023), Shanghai, China, Mar. 2023, pp. 581–586.
[16] G. Meng and K. B. Letaief, “Quick Multimedia Data Transfer with QUIC,” in IEEE Wireless Communications, vol. 28, no. 3, pp. 57–63, Jun. 2021
[17] K. D. Nguyen, A. Virdis, G. Stea and F. Barcella, “FTM-ns3: WiFi Fine Time Measurements for ns-3,” in Proceedings of the 2022 Workshop on ns-3 (WNS3), Rome, Italy, Jun. 2022, pp. 1–8