Markov Modelling and Cluster-Based Analysis of Transport Layer Traffic Using Quick User Datagram Protocol Internet Connections †
Abstract
1. Introduction
- Connection establishment and zero-round-trip time (RTT) handshake: QUIC reduces the connection setup time by integrating the handshake with transport layer security (TLS) 1.3, enabling encrypted connections in a single round trip. For repeat connections, QUIC supports 0-RTT resumption, minimizing latency for recurrent communication sessions.
- Multiplexed streams without head-of-line (HoL) blocking: unlike TCP, which enforces strict in-order delivery, QUIC supports multiple independent streams within a single connection. This prevents HoL blocking, where packet loss in one stream delays the delivery of other data, leading to smoother web browsing and real-time communication.
- Connection migration and stateless reset: QUIC connections are identified by connection identification (IDs) instead of internet protocol (IP) addresses, allowing seamless migration between networks (e.g., switching from Wi-Fi to mobile data) without requiring a new handshake. Additionally, QUIC enables stateless resets, allowing servers to discard inactive connections efficiently.
- Congestion and flow control: QUIC implements sophisticated congestion control algorithms, such as cubic congestion control (CUBIC) and bottleneck bandwidth and round-trip (BBR) propagation time, to optimize throughput and minimize packet loss. Flow control mechanisms prevent buffer overflow by dynamically adjusting window sizes based on network conditions.
- Encryption and security: all QUIC packets, except initial handshake messages, are encrypted using Transport Layer Security (TLS) 1.3. This enhances privacy, prevents traffic tampering, and protects against attacks like injection and spoofing. QUIC also obfuscates transport headers, making it more resilient against passive traffic analysis.
- Error correction and reliability: while QUIC operates over UDP, it includes features traditionally associated with TCP, such as automatic retransmissions and acknowledgment mechanisms. Forward error correction (FEC) is used to further enhance reliability in lossy networks.
- Improved Web performance: QUIC’s low-latency design significantly enhances page load times and video streaming experiences. By minimizing handshake delays and avoiding HoL blocking, QUIC reduces buffering and ensures smoother media delivery.
- Enhanced mobile connectivity: With support for connection migration, QUIC ensures uninterrupted communication when switching between network interfaces, making it ideal for mobile applications and IoT deployments.
- Optimized cloud and CDN services: content delivery networks (CDNs) benefit from QUIC’s efficient transport mechanisms, leading to a reduced server load, improved cache efficiency, and better scalability.
- Better performance in high-loss networks: QUIC’s adaptive retransmission strategies and advanced congestion control make it well-suited for high-latency and lossy environments, such as satellite networks and wireless communication.
2. Related Works
2.1. Performance Analysis of QUIC Service
2.2. Markov-Based Modeling of Network Traffic
3. Methodology
3.1. Adaptive Clustering: OPTICS
- Neighborhood identification: each data point is evaluated to determine whether it is a core point based on MinPts and its ε-neighborhood.
- Priority queue processing: the algorithm processes points in increasing order of their RD, maintaining a queue that dynamically expands clusters as new core points are discovered.
- Reachability plot construction: instead of assigning direct clusters, OPTICS constructs a reachability plot, which is a 1D visualization where clusters appear as valleys (Figure 1).
3.2. Markov Chain Modelling
4. Results and Discussion
4.1. Measurement of QUIC Traffic
- (1)
- MAX_DATA: increases the connection-level data limit;
- (2)
- MAX_STREAM_DATA: increases the data limit for a particular stream;
- (3)
- DATA_BLOCKED: sent by the sender if it wants to send but is blocked by connection-level limits;
- (4)
- STREAM_DATA_BLOCKED: sent if blocked by stream-level limit.
4.2. Markov Chain and Steady State of Transition Matrix
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
Abbreviations
QUIC | Quick UDP Internet Connections |
RTT | Round-Trip Time |
HoL | Head-of-Line |
IAT | Interarrival Time |
OPTICS | Ordering Points To Identify the Clustering Structure |
MTU | Maximum Transfer Unit |
Bw | Bandwidth |
SSize | Segment Size |
CLI Tx | Client Transmit Ethernet frames |
SER Rx | Server Receive Ethernet frames |
References
- Kakhki, A.M.; Jero, S.; Choffnes, D.; Nita-Rotaru, C.; Mislove, A. Taking a long look at QUIC: An approach for rigorous evaluation of rapidly evolving transport protocols. In Proceedings of the 2017 Internet Measurement Conference, London, UK, 1–3 November 2017; pp. 290–303. [Google Scholar]
- Rüth, J.; Poese, I.; Dietzel, C.; Hohlfeld, O. A First Look at QUIC in the Wild. In Passive and Active Measurement, PAM 2018; Beverly, R., Smaragdakis, G., Feldmann, A., Eds.; Lecture Notes in Computer Science; Springer: Cham, Switzerland, 2018; Volume 10771. [Google Scholar]
- Polese, M.; Chiariotti, F.; Bonetto, E.; Rigotto, F.; Zanella, A.; Zorzi, M. A Survey on Recent Advances in Transport Layer Protocols. IEEE Commun. Surv. Tutor. 2019, 21, 3584–3608. [Google Scholar] [CrossRef]
- Zheng, Z.; Ma, Y.; Liu, Y.; Yang, F.; Li, Z.; Zhang, Y.; Zhang, J.; Shi, W.; Chen, W.; Li, D.; et al. XLINK: QoE-driven multi-path QUIC transport in large-scale video services. In Proceedings of the 2021 ACM SIGCOMM 2021 Conference, Virtual, 23–27 August 2021; pp. 418–432. [Google Scholar]
- Gál, Z.; Terdik, G. On the patterns of the nonstationary datagram based fast communication processes. Ann. Math. Inform. 2023, 58, 41–55. [Google Scholar] [CrossRef]
- Ye, N. A Markov chain model of temporal behavior for anomaly detection. In Proceedings of the 2000 IEEE Systems, Man, and Cybernetics Information Assurance and Security Workshop, West Point, NY, USA, 6–7 June 2000; p. 169. [Google Scholar]
- Muscariello, L.; Mellia, M.; Meo, M.; Marsan, M.A.; Cigno, R.L. Markov models of internet traffic and a new hierarchical MMPP model. Comput. Commun. 2005, 28, 1835–1851. [Google Scholar] [CrossRef]
- Dainotti, A.; Pescapé, A.; Rossi, P.S.; Palmieri, F.; Ventre, G. Internet traffic modeling by means of Hidden Markov Models. Comput. Netw. 2008, 52, 2645–2662. [Google Scholar] [CrossRef]
- More, S.; Shukla, D. Review on Internet Traffic Sharing Using Markov Chain Model in Computer Network. 2018. Available online: https://link.springer.com/chapter/10.1007/978-981-10-7641-1_7 (accessed on 13 May 2025).
- Aceto, G.; Bovenzi, G.; Ciuonzo, D.; Montieri, A.; Persico, V.; Pescapé, A. Characterization and Prediction of Mobile-App Traffic Using Markov Modeling. IEEE Trans. Netw. Serv. Manag. 2021, 18, 907–925. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Gal, Z.; Gal, M.B.; Terdik, G. Markov Modelling and Cluster-Based Analysis of Transport Layer Traffic Using Quick User Datagram Protocol Internet Connections. Eng. Proc. 2025, 108, 31. https://doi.org/10.3390/engproc2025108031
Gal Z, Gal MB, Terdik G. Markov Modelling and Cluster-Based Analysis of Transport Layer Traffic Using Quick User Datagram Protocol Internet Connections. Engineering Proceedings. 2025; 108(1):31. https://doi.org/10.3390/engproc2025108031
Chicago/Turabian StyleGal, Zoltan, Marcell B. Gal, and Gyorgy Terdik. 2025. "Markov Modelling and Cluster-Based Analysis of Transport Layer Traffic Using Quick User Datagram Protocol Internet Connections" Engineering Proceedings 108, no. 1: 31. https://doi.org/10.3390/engproc2025108031
APA StyleGal, Z., Gal, M. B., & Terdik, G. (2025). Markov Modelling and Cluster-Based Analysis of Transport Layer Traffic Using Quick User Datagram Protocol Internet Connections. Engineering Proceedings, 108(1), 31. https://doi.org/10.3390/engproc2025108031