Semantic-Aware Network Slicing Orchestration with DeepSeek-Enhanced Traffic Forecasting in 6G Ecosystems
Keywords:
6G, network slicing, semantic-aware, DeepSeek, traffic forecasting, orchestration, intent-based networking, AI-native architecture, resource managementAbstract
The sixth generation of mobile networks envisions a radical shift from mere connectivity to a fully intelligent, semantic-aware fabric capable of supporting immersive holographic communications, autonomous systems, and large-scale digital twins. Central to this transformation is network slicing, which enables the partitioning of a single physical infrastructure into multiple logical networks with tailored performance guarantees. Traditional slicing orchestration relies on coarse-grained traffic descriptors and static resource allocation policies, falling short of the dynamic and context-rich demands of future applications. This paper presents a novel system architecture for semantic-aware network slicing orchestration that integrates advanced traffic forecasting powered by DeepSeek models. By embedding semantic intelligence directly into the orchestration loop, our framework deciphers application intent, predicts multidimensional traffic patterns with high spatial and temporal resolution, and adaptively reconfigures slice resources across edge, fog, and cloud domains. We extensively discuss architectural design choices, cross-layer governance mechanisms, and the translational mapping from high-level intent to low-level resource policies. DeepSeek-enhanced forecasting is examined through its multi-modal fusion, self-attention capabilities, and continuous learning paradigms, demonstrating how it surpasses conventional time-series models in capturing complex semantic correlations. The paper further probes into system-level trade-offs involving robustness, fairness, energy sustainability, and regulatory compliance within a federated multi-operator environment. Through a thorough conceptual analysis and forward-looking perspectives, we argue that semantic-driven slicing orchestration represents a foundational capability for 6G ecosystems, ensuring that networks become not only faster but also profoundly understanding and proactive. The study contributes a comprehensive discussion on infrastructure deployment imperatives, policy frameworks, and the delicate balance between autonomous decision-making and human oversight, thereby providing a holistic reference for designing resilient, efficient, and socially attuned next-generation networks.
References
1. Foukas, X., Patounas, G., Elmokashfi, A., & Marina, M. K. (2017). Network slicing in 5G: Survey and challenges. IEEE Communications Magazine, 55(5), 94–100.
2. Bonati, L., D’Oro, S., Polese, M., Pecorella, T., Meneghello, F., & Melodia, T. (2023). Open, programmable, and virtualized 5G networks: State-of-the-art and the road ahead. Computer Networks, 182, 107516.
3. Kountouris, M., & Pappas, N. (2021). Semantics-empowered communication for networked intelligent systems. IEEE Communications Magazine, 59(6), 96–102.
4. Hua, Y., Zhao, Z., Li, R., Chen, X., Liu, Z., & Zhang, H. (2020). Traffic prediction based on random connectivity in deep learning with long short-term memory for communication networks. IEEE Transactions on Network and Service Management, 17(2), 942–955.
5. Jiang, W., & Zhang, L. (2021). Graph neural network based traffic prediction for network slicing. IEEE Transactions on Vehicular Technology, 70(10), 10826–10837.
6. Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., & Sun, L. (2023). Transformers in time series: A survey. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 6778–6786.
7. Li, Y., Yu, R., Shahabi, C., & Liu, Y. (2018). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. International Conference on Learning Representations.
8. DeepSeek-AI. (2024). DeepSeek-V2: A strong, economical, and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434.
9. Bega, D., Gramaglia, M., Fiore, M., Banchs, A., & Costa-Pérez, X. (2019). DeepCog: Cognitive network management in sliced 5G networks with deep learning. IEEE INFOCOM, 280–288.
10. Sciancalepore, V., Samdanis, K., Costa-Perez, X., Bega, D., Gramaglia, M., & Banchs, A. (2019). Mobile traffic forecasting for maximizing 5G network sharing profits. IEEE Transactions on Mobile Computing, 18(11), 2565–2580.
11. Samdanis, K., & Taleb, T. (2020). The road beyond 5G: A vision and insight of the key technologies. IEEE Network, 34(2), 135–141.
12. Letaiief, K. B., Chen, W., Shi, Y., Zhang, J., & Zhang, Y. J. A. (2023). The roadmap to 6G: AI as a key enabler. Proceedings of the IEEE, 111(5), 635–671.
13. Tomforde, S., & Müller-Schloer, C. (2023). Organic computing: A grand challenge for mastering complex systems. ACM Transactions on Autonomous and Adaptive Systems, 18(1), 1–32.
14. He, Y., Zhao, N., & Yin, H. (2021). Integrated networking, caching, and computing for connected vehicles: A deep reinforcement learning approach. IEEE Transactions on Vehicular Technology, 70(4), 3912–3924.
15. Zhang, C., Zhang, H., Qiao, J., Li, Z., & Alouini, M. S. (2025). TIDES: Traffic Intelligence with DeepSeek Enhanced Spatial Temporal Prediction. IEEE Journal on Selected Areas in Communications.
16. Boutaba, R., Shahriar, N., & Salahuddin, M. A. (2023). Managing the network slicing lifecycle in 5G and beyond: A comprehensive survey. IEEE Communications Surveys & Tutorials, 25(2), 1343–1379.
17. Corneo, L., & Mohapatra, P. (2024). Carbon-aware computing for sustainable networking: A research agenda. ACM SIGCOMM Computer Communication Review, 54(1), 12–20.
18. Liyanage, M., Ahmad, I., Abro, A. B., Gurtov, A., & Ylianttila, M. (2018). A comprehensive guide to 5G security. Wiley.
19. Barakabitze, A. A., Ahmad, A., Mijumbi, R., & Hines, A. (2020). 5G network slicing using SDN and NFV: A survey of taxonomy, architectures and future challenges. Computer Networks, 167, 106984.
20. Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020). Convergence of edge computing and deep learning: A comprehensive survey. IEEE Communications Surveys & Tutorials, 22(2), 869–904.
21. Dogra, A., Jha, R. K., & Jain, S. (2022). A survey on beyond 5G network with the advent of 6G: Architecture and emerging technologies. IEEE Access, 10, 36152–36188.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Data Intelligence and AI Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
