Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Intelligent Hybrid Resource Allocation in MEC-assisted RAN Slicing Network (2405.17436v1)

Published 2 May 2024 in cs.NI, cs.AI, and cs.LG

Abstract: In this paper, we aim to maximize the SSR for heterogeneous service demands in the cooperative MEC-assisted RAN slicing system by jointly considering the multi-node computing resources cooperation and allocation, the transmission resource blocks (RBs) allocation, and the time-varying dynamicity of the system. To this end, we abstract the system into a weighted undirected topology graph and, then propose a recurrent graph reinforcement learning (RGRL) algorithm to intelligently learn the optimal hybrid RA policy. Therein, the graph neural network (GCN) and the deep deterministic policy gradient (DDPG) is combined to effectively extract spatial features from the equivalent topology graph. Furthermore, a novel time recurrent reinforcement learning framework is designed in the proposed RGRL algorithm by incorporating the action output of the policy network at the previous moment into the state input of the policy network at the subsequent moment, so as to cope with the time-varying and contextual network environment. In addition, we explore two use case scenarios to discuss the universal superiority of the proposed RGRL algorithm. Simulation results demonstrate the superiority of the proposed algorithm in terms of the average SSR, the performance stability, and the network complexity.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. Z. Wang, Y. Wei, F. R. Yu, and Z. Han, “Utility optimization for resource allocation in multi-access edge network slicing: A twin-actor deep deterministic policy gradient approach,” IEEE Trans. Wireless Commun., vol. 21, no. 8, pp. 5842–5856, Aug. 2022.
  2. X. Foukas, G. Patounas, A. Elmokashfi, and M. K. Marina, “Network slicing in 5G: Survey and challenges,” IEEE Commun. Mag., vol. 55, no. 5, pp. 94–100, May 2017.
  3. X. Zhou, R. Li, T. Chen, and H. Zhang, “Network slicing as a service: Enabling enterprisesówn software-defined cellular networks,” IEEE Commun. Mag., vol. 54, no. 7, pp. 146–153, Jul. 2016.
  4. A. Azari, M. Ozger, and C. Cavdar, “Risk-aware resource allocation for uRLLC: Challenges and strategies with machine learning,” IEEE Commun. Mag., vol. 57, no. 3, pp. 42–48, Mar. 2019.
  5. H.-T. Chien, Y.-D. Lin, C.-L. Lai, and C.-T. Wang, “End-to-end slicing as a service with computing and communication resource allocation for multi-tenant 5G systems,” IEEE Wireless Commun. , vol. 26, no. 5, pp. 104–112, Oct. 2019.
  6. W. K. G. Seah, C.-H. Lee, Y.-D. Lin, and Y.-C. Lai, “Combined communication and computing resource scheduling in sliced 5G multi-access edge computing systems,” IEEE Trans. Veh. Technol., vol. 71, no. 3, pp. 3144–3154, Mar. 2022.
  7. S. Zarandi, and H. Tabassum, “Delay minimization in sliced multi-cell mobile edge computing (MEC) systems,” IEEE Commun. Lett., vol. 25, no. 6, pp. 1964–1968, Jun. 2021.
  8. Z. Wang, M. Eisen, and A. Ribeiro, “Learning decentralized wireless resource allocations with graph neural networks,” IEEE Trans. Signal Process., vol. 70, pp. 1850–1863, Mar. 2022.
  9. M. Eisen, and A. Ribeiro, “Optimal wireless resource allocation with random edge graph neural networks,” IEEE Trans. Signal Process., vol. 68, pp. 2977–2991, Apr. 2020.
  10. G. Faraci, C. Grasso, and G. Schembra, “Design of a 5G network slice extension with MEC UAVs managed with reinforcement learning,” IEEE J. Sel. Areas Commun., vol. 38, no. 10, pp. 2356–2371, Oct. 2020.
  11. Y. Gong, Y. Wei, F. R. Yu, and Z. Han, “Slicing-based resource optimization in multi-access edge network using ensemble learning aided DDPG algorithm,” J. Commun. Networks, vol. 25, no. 1, pp. 1–14, Feb. 2023.
  12. S. Liu, C. Zheng, Y. Huang, and T. Q. S. Quek,“Distributed reinforcement learning for privacy-preserving dynamic edge caching,” IEEE J. Sel. Areas Commun., vol. 40, no. 3, pp. 749–760, Mar. 2022.
  13. C. Zheng, S. Liu, Y. Huang, and L. Yang, “Hybrid policy learning for energy-latency tradeoff in MEC-assisted VR video service,” IEEE Trans. Veh. Technol., vol. 70, no. 9, pp. 9006–9021, Sept. 2021.
  14. J. Jiang, C. Dun, T. Huang, and Z. Lu, “Graph convolutional reinforcement learning,” Proc. 8th Int. Conf. Learn. Represent. (ICLR’20), Addis Ababa, Ethiopia, 2020, pp. 1665-1673.
  15. Y. You, T. Chen, Z. Wang, and Y. Shen, “L2-GCN: Layer-wise and learned efficient training of graph convolutional networks,” Proc. IEEE/CVF Conf. Comput. Vision and Pattern Recognit. (CVPR’20), Seattle, WA, USA, 2020, pp. 2124–2132.
  16. D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, and M. Riedmiller, “Deterministic policy gradient algorithms,” in Proc. 31st Int. Conf. Mach. Learn. (ICML’14), Beijing, China, June 2014, pp. 387–395.
  17. GSA, “5G network slicing for vertical industries,” 2017.
  18. S. Sinha, H. Bharadhwaj, A. Srinivas, and A, Garg, “D2RL: Deep dense architectures in reinforcement learning,” 2020, arXiv:2010.09163.
  19. D. Kingma and J. Ba, “Adam: A method for stochastic optimization,” Proc. 3rd Int. Conf. Learn. Represent. (ICLR’15), San Diego, CA, USA, May 2015.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now