IJSDIP | International Journal of System Design & Info Processing

Edge-Enabled 6G Core: A Federated Intelligence Approach for Distributed Computing and Control

Paper ID:

IJSDIP_2024_VOLUME 12_ISSUE 4_121-126

Author's Name:

Senthil Kumar M, Sapthagiri Vienala

Volume:

Issue:

Issue 4

Year:

2024

Pages:

121-126

Abstract

The rapid evolution of wireless communication towards the sixth-generation (6G) paradigm demands an architectural shift from centralized cloud computing to decentralized edge intelligence. Traditional 5G networks, though capable of delivering enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (URLLC), remain limited by core network centralization and data privacy challenges. This paper proposes an Edge-Enabled 6G Core (E6C) framework that integrates Federated Intelligence (FI) for distributed computing, learning, and control. In the proposed model, the edge nodes collaboratively train machine learning models using local datasets without sharing raw data, thus preserving privacy and reducing backhaul congestion. The federated orchestration layer ensures synchronization between multiple edge nodes and the core control unit, enabling real-time adaptation to dynamic network states and heterogeneous traffic demands. Experimental evaluation through simulation and prototype deployment reveals that the E6C framework improves latency performance by up to 42%, reduces control signaling overhead by 31%, and achieves a 25% increase in overall throughput compared to conventional centralized architectures. The paper further discusses implementation challenges, including model convergence at the edge, privacy leakage mitigation, and energy efficiency, providing future insights into how federated learning and edge computing will redefine the 6G core network landscape.

Keywords

6G Communication, Edge Computing, Federated Intelligence, Distributed Learning, Network Orchestration, Ultra-Low Latency, Privacy Preservation, Intelligent Core Network, Network Slicing, AI-Driven Optimization

References

[1] K. B. Letaief, W. Chen, Y. Shi, J. Zhang, and Y.-J. A. Zhang, “The Roadmap to 6G: AI Empowered Wireless Networks,” IEEE Communications Magazine, vol. 57, no. 8, pp. 84–90, Aug. 2019. [2] M. Giordani, M. Polese, A. Roy, D. Castor, and M. Zorzi, “A Tutorial on 6G Networks: Vision, Enabling Technologies, and New Paradigms,” IEEE Communications Surveys & Tutorials, vol. 23, no. 3, pp. 1972–2008, 2021. [3] H. Huang, C. Xu, and D. Li, “Federated Learning for 6G: Applications, Challenges, and Opportunities,” IEEE Internet of Things Journal, vol. 9, no. 12, pp. 8880–8892, 2022. [4] N. Rajatheva et al., “White Paper on Broadband Connectivity in 6G,” 6G Flagship, University of Oulu, Finland, 2021. [5] L. Liu, J. Zhang, and S. Song, “Federated Learning in Mobile Edge Networks: A Comprehensive Survey,” IEEE Access, vol. 10, pp. 101338–101359, 2022. [6] X. You, C.-X. Wang, J. Huang, and X. Gao, “Towards 6G Wireless Communication Networks: Vision, Enabling Technologies, and New Paradigms,” Science China Information Sciences, vol. 64, no. 1, pp. 1–74, 2021. [7] Y. Mao, S. Leng, and S. Maharjan, “Joint Resource Allocation and Model Aggregation for Federated Learning over 6G Networks,” IEEE Transactions on Vehicular Technology, vol. 71, no. 8, pp. 8929–8942, 2022. [8] Z. Ning, P. Dong, J. Rodrigues, and F. Xia, “Deep Reinforcement Learning for Intelligent Edge Computing in 6G Networks,” IEEE Network, vol. 35, no. 1, pp. 204–211, 2021. [9] S. Samarakoon, M. Bennis, and W. Saad, “Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications,” IEEE Transactions on Communications, vol. 68, no. 2, pp. 1146–1159, 2020. [10] Y. Xu, H. Wang, and J. Chen, “Edge Intelligence in 6G: Vision, Enabling Technologies, and Applications,” IEEE Wireless Communications, vol. 29, no. 2, pp. 106–113, 2022. [11] F. Restuccia, N. Mohammadi, and T. Melodia, “Federated Learning in 6G Edge Networks: Fundamentals, Security, and Challenges,” IEEE Network, vol. 37, no. 1, pp. 54–61, 2023. [12] T. Mahmood, K. M. Alam, and M. S. Hossain, “AI-Driven Network Slicing for 6G: Design and Challenges,” IEEE Communications Standards Magazine, vol. 5, no. 2, pp. 30–37, 2021. [13] C. Sun, X. Li, and L. Chen, “Resource Optimization in Edge-Assisted Federated Learning for 6G Networks,” IEEE Transactions on Mobile Computing, vol. 23, no. 4, pp. 2002–2016, 2024. [14] S. Han, S. Choi, and M. Bennis, “Federated Edge Intelligence for 6G Networks,” IEEE Wireless Communications, vol. 29, no. 4, pp. 24–31, 2022. [15] L. U. Khan, S. R. Pandey, and M. Alsenwi, “Reinforcement Learning for Resource Optimization in 6G Networks,” IEEE Internet of Things Magazine, vol. 5, no. 3, pp. 14–21, 2022. [16] R. Ahmad, M. A. Javed, and D. Kim, “Energy-Aware Federated Learning Framework for Edge-Enabled 6G Networks,” IEEE Access, vol. 10, pp. 115567–115580, 2022. [17] H. Zhang, N. Liu, and X. Tao, “Blockchain-Assisted Secure Federated Learning for 6G-Edge Intelligence,” IEEE Transactions on Industrial Informatics, vol. 19, no. 3, pp. 1845–1855, 2023. [18] A. Diro and N. Chilamkurti, “Collaborative Learning for Distributed AI in 6G-Enabled IoT Systems,” IEEE Systems Journal, vol. 17, no. 1, pp. 734–744, 2023. [19] C. Pan, Y. Xu, and Z. Yang, “Dynamic Edge Resource Allocation for Latency-Sensitive Federated Learning,” IEEE Transactions on Wireless Communications, vol. 22, no. 6, pp. 3894–3907, 2023. [20] M. R. Khosravirad et al., “6G Network Architecture: A View on Enabling Technologies and Research Challenges,” IEEE Access, vol. 9, pp. 55408–55429, 2021. [21] Y. Dai, D. Xu, and K. Yang, “Learning-Based Orchestration for Distributed 6G Edge Intelligence,” IEEE Communications Letters, vol. 26, no. 5, pp. 1050–1054, 2022. [22] J. Kim, M. Jo, and Y. Park, “AI-Native Core Networks for 6G Systems,” IEEE Transactions on Network and Service Management, vol. 20, no. 1, pp. 201–214, 2023. [23] A. Saeed, N. Saeed, and T. Devassy, “Federated Deep Reinforcement Learning for Edge-Enabled 6G Communications,” IEEE Transactions on Cognitive Communications and Networking, vol. 9, no. 1, pp. 80–91, 2023.

DOI: https://doi.org/10.64971/j.cph.ijsdip.v12.i4.1.2024