Applying AI-Based Performance Modelling to Improve QoS in Maritime Communication Infrastructures

Koki Panneerselvam; C Rajendran

doi:10.31838/NJAP/08.01.09

Authors

Koki Panneerselvam Department of Marine Engineering, AMET University, Kanathur, Tamilnadu -603112 https://orcid.org/0009-0004-2543-9738
C Rajendran Department of Nautical Science, AMET University, Kanathur, Tamilnadu -603112 https://orcid.org/0009-0007-0137-5700

DOI:

https://doi.org/10.31838/NJAP/08.01.09

Keywords:

AI-Based, Performance Modelling, Quality of Service (QoS), Maritime, Communication, Infrastructure, Optimization

Abstract

High seas present unparalleled challenges for maritime communication infrastructures which are further exacerbated by the aggressive environment, scant bandwidth, and continuous topology alterations. Such factors deeply affect the quality of service (QoS) vital in navigation, security, and logistics which need to be carefully managed regionally and globally. This paper aims at enhancing QoS in maritime networks through the AI-based performance modelling approach by anticipating and preventing risks that can lead to disruptions. The model autonomously adapts to optimize ship and network configurations through real-time measurements and historic data inputs, such as signal strength, weather conditions, and vessel movement patterns. Through the proposed framework, control over optimal resource allocation as well as smart routing to enhance network communication subsystem resilience and effectiveness is accomplished within software-defined networking (SDN) architectures. SDN is widely integrated due to its ability to deliver superior control over maritime communications networks that utilize multiple constrained devices. Extensive simulations conducted demonstrate superior outcomes on throughput, latency, and network availability cross compared to existing approaches. A new paradigm of transforming maritime communication with AI-driven models providing insight and automated control has been established for safer and reliable operations while at sea. The next steps of this study are the realistic implementation in maritime scenarios and standard framework optimization supporting various maritime systems interoperability.

References

1. Hussain, S., Alam, T., & Ahmed, M. (2021). Review of maritime communication technologies. Marine Technology

Society Journal, 55(4), 33–45. https://doi.org/10.4031/MTSJ.55.4.4

2. Chen, L., Zhang, R., Wang, X., & Huang, Y. (2022). Adaptive routing in maritime mesh networks: challenges and solutions. IEEE Communications Surveys & Tutorials, 24(1), 117–138. https://doi.org/10.1109/COMST.2021.3112538

3. Ahmed, K., Zhou, J., & Lin, C. (2020). Adaptive QoS provisioning in maritime wireless networks. IEEE Transactions

on Network and Service Management, 17(4), 2340–2352. https://doi.org/10.1109/TNSM.2020.3032239

4. International Telecommunication Union (ITU). (2021). Maritime Communications and Radiocommunications Handbook. Geneva: ITU Publications.

5. Chowdhury, U., & Chakma, S. (2022). Millimeter-wave technology based applications across industries. National Journal of Antennas and Propagation, 4(1), 33–40.

6. Wang, H., Song, Y., & Liu, J. (2020). IoT-based maritime communication for smart ports. Ocean Engineering, 209, 107456. https://doi.org/10.1016/j.oceaneng.2020.107456

7. Asadov, B. (2018). The current state of artificial intelligence (AI) and implications for computer technologies. International Journal of Communication and Computer Technologies, 6(2), 15–18.

8. Feifei, W. (2024). Optimization algorithm of public service facilities layout in earthquake-stricken areas based on SA algorithm. Archives for Technical Sciences, 2(31), 70–85. https://doi.org/10.70102/afts.2024.1631.070

9. Zhang, K., Fan, P., & Zhang, X. (2021). Deep learning-based channel prediction for maritime networks. IEEE Transactions on Vehicular Technology, 70(3), 2638–2649. https://doi.org/10.1109/TVT.2021.3056742

10. Pan, B., Liu, Q., & Gao, Y. (2021). SDN-based QoS aware routing for maritime mesh networks. Computer Networks, 198, 108372. https://doi.org/10.1016/j.comnet.2021.108372

11. Zhang, J., & Song, X. (2024). The AI-assisted traditional design methods for the construction sustainability: a case study of the Lisu Ethnic Minority Village. Natural and Engineering Sciences, 9(2), 213–233. https://doi.org/10.28978/nesciences.1569562

12. Khan, M., & Taha, A. (2023). Simulating complex structures with structural engineering software. Association Journal of Interdisciplinary Technics in Engineering Mechanics, 1(1), 26–37.

13. Gao, Q., Tang, L., Liu, Y., & Wu, J. (2023). AI-enabled software-defined networking for maritime communication. IEEE Access, 11, 34677–34689. https://doi.org/10.1109/ACCESS.2023.3258946

14. Liu, F., Zhao, T., & Yan, G. (2023). Improving maritime network performance using deep learning. Journal of Ocean Engineering and Science, 8(1), 100–109. https://doi.org/10.1016/j.joes.2022.05.004

15. Kumar, R., Li, M., & Chen, Z. (2023). Machine learning applications in maritime wireless networks. Sensors, 23(8), 3641. https://doi.org/10.3390/s23083641

16. Yang, J., He, Y., & Zhou, L. (2022). AI-driven QoS optimization in dynamic maritime environments. IEEE Internet of Things Journal, 9(10), 7385–7396. https://doi.org/10.1109/JIOT.2022.3145287

17. Dinesh, R., Myilraj, R., Ragul, G., Ranjith Kumar, T., & Singaravel, G. (2023). Energy efficient task allocation algorithm for fog computing networks. International Journal of Advances in Engineering and Emerging Technology, 14(1), 46–51.

18. Kim, S., Park, Y., & Jang, H. (2023). Challenges of maritime AI: dataset scarcity and deployment risks. Ocean Engineering, 267, 113318. https://doi.org/10.1016/j.oceaneng.2023.113318

19. Chen, Y., & Li, M. (2021). Temporal deep learning for QoS forecasting in maritime communication. Sensors, 21(12), 4002. https://doi.org/10.3390/s21124002

20. Zhao, Y., Chen, D., & Lin, X. (2020). A hybrid maritime communication model integrating satellite and VHF. IEEE Transactions on Wireless Communications, 19(12), 8162-8174. https://doi.org/10.1109/TWC.2020.3021110

21. Shabbooie, A., & Iranban, S.J. (2014). Prioritizing effective indicators in the process of strategic management of universities (Case study: Shiraz University). International Academic Journal of Organizational Behavior and Human Resource Management, 1(2), 47–64.

22. Rahman, M., Ismail, M., & Latif, M. (2022). Toward a unified AI architecture for maritime network optimization. IEEE Communications Magazine, 60(12), 78–84. https://doi.org/10.1109/MCOM.001.2200209

23. Rahman, F. (2025). Artificial intelligence-driven cybersecurity framework for industrial control networks. Transactions on Secure Communication Networks and Protocol Engineering, 2(1), 1–8.

24. Rahim, R. (2024). Spectrum-adaptive neuromorphic learning for wireless wind turbine condition monitoring. Journal of Wireless Intelligence and Spectrum Engineering, vol. 1, no. 1, pp. 10–18.

25. Huang, R., & Wang, T. (2023). Edge AI for autonomous maritime communication systems. IEEE Internet of Things Journal, 10(5), 3764–3775. https://doi.org/10.1109/JIOT.2023.3241910

26. Xu, D., Li, T., & Ren, J. (2021). Security-aware AI modeling for maritime IoT networks. IEEE Transactions on Industrial Informatics, 17(10), 6990–7000. https://doi.org/10.1109/TII.2021.3064933

27. Chakma, K.S. (2025). Flexible and wearable electronics: innovations, challenges, and future prospects. Progress in Electronics and Communication Engineering, 2(2), 41–46. https://doi.org/10.31838/PECE/02.02.05

28. Li, J., Tan, W., & Chen, L. (2019). A survey on AI-based QoS modeling in wireless networks. IEEE Access, 7, 124721-124740. https://doi.org/10.1109/ACCESS.2019.2937948

29. Jouya, M., & Khayati, S. (2017). Review local search algorithms in artificial intelligence. International Academic Journal of Science and Engineering, 4(1), 190–195.

30. Muralidharan, J., & Abdullah, D. (2023). AI-driven acoustic metamaterial optimization for broadband noise control. Advanced Computational Acoustics Engineering, 1(1), 25–32.

31. Aguila, C.I.G., Arellano, M.D.P.C., Castro, M.D.P.Q., Mondragón, E.M.B., & Castro, G.A.Q. (2024). Examining artificial intelligence and law as a tool for legal service, decision-making, job transformation, and ethical performance. Journal of Internet Services and Information Security, 14(3), 99–115. https://doi.org/10.58346/JISIS.2024.I3.006

32. Jiang, X., Sun, H., & Wu, F. (2018). Hybrid satellite-terrestrial communication for maritime QoS improvement. Marine Technology Journal, 52(2), 44–53. https://doi.org/10.1109/MTJ.2018.2821011

33. Wang, P., & Zhao, N. (2022). Machine learning for real time maritime network performance prediction. IEEE Access,

10, 99822–99834. https://doi.org/10.1109/ACCESS.2022.3205521