Zero‑Shot Slice Policy Transfer for Cloud‑RAN Resource Allocation under Fronthaul and SLA Constraints.
DOI:
https://doi.org/10.37376/sjuob.v38i2.7469Keywords:
SLA., fronthaul,, proportional fair,, convex optimization,, zero shot learning,, Cloud RAN,, RAN slicing,Abstract
ABSTRACT Cloud RAN requires fast, SLA aware resource allocation across heterogeneous slices (eMBB, URLLC, mMTC). Training a dedicated controller for every slice is impractical; policies must generalize to unseen slice semantics spanning latency, reliability, rate, burstiness, and mobility. A coupled radio–compute–fronthaul allocation problem is formulated, and Zero Shot Slice Policy Transfer (ZSPT) is introduced as a semantics to policy mapping that operates without per slice training by distilling a high quality convex surrogate into a lightweight scheduler. In this paper zero shot performance was evaluated against Proportional Fair (PF) and the convex surrogate, reporting throughput, Jain’s fairness, UE rate percentiles, and SLA violation probability with bootstrap 95% confidence intervals. In a representative scenario, ZSPT matched PF on unseen slices, while the convex surrogate increased fairness and substantially raises 5th percentile UE rates.Downloads
References
Management and orchestration; Concepts, use cases and requirements for Network Slicing, 3GPP TS 28.530 V17.4.0, 3rd Generation Partnership Project (3GPP), Oct.. [Online]. Available: https://www.3gpp.org/ftp/Specs/archive/28_series/28.530/
Management and orchestration; Provisioning, 3GPP TS 28.531 V17.8.0, 3rd Generation Partnership Project (3GPP), Oct. 2023. [Online]. Available: https://www.3gpp.org/ftp/Specs/archive/28_series/28.531/
Policy and charging control framework for the 5G System (5GS); Stage 2, 3GPP TS 23.503 V18.7.0, 3rd Generation Partnership Project (3GPP), Oct. 2024. [Online]. Available: https://www.3gpp.org/ftp/Specs/archive/23_series/23.503/
L. Andersson and K. Homma, Eds., Framework for IETF Network Slices, RFC 9543, IETF, Apr. 2024. [Online]. Available: https://www.rfc-editor.org/rfc/rfc9543.html
End-to-End Network Slicing Requirements, GSMA PRD NG.135 V3.0, GSM Association, Jun. 2023. [Online]. Available: https://www.gsma.com/newsroom/resources/
O-RAN Fronthaul C/U/S-Plane Specification, ETSI TS 103 859 V12.0.1, European Telecommunications Standards Institute (ETSI), Apr. 2024. [Online]. Available: https://www.etsi.org/deliver/etsi_ts/103800_103899/103859/12.00.01_60/
Use Cases and Requirements for O-RAN Slicing, ETSI TS 104 041 V11.0.0, European Telecommunications Standards Institute (ETSI), Mar. 2025. [Online]. Available: https://www.etsi.org/standards
E2 Service Model (E2SM); General Aspects and Principles, ETSI TS 104 040 V4.0.0, European Telecommunications Standards Institute (ETSI), Oct. 2024. [Online]. Available: https://www.etsi.org/standards
Trends and Developments in Open RAN, White Paper, 5G Americas, Nov. 2024. [Online]. Available: https://www.5gamericas.org/trends-and-developments-in-open-ran/
R. Cannatà, H. Sun, D. M. Dumitriu, and H. Hassanieh, “Towards seamless 5G Open-RAN integration with Web Assembly,” in Proc. 23rd ACM Workshop Hot Topics Netw. (HotNets), Irvine, CA, USA, Nov. 2024, pp. 121–131, doi: 10.1145/3696348.3696864.
M. Karbalaee Motalleb, V. Shah-Mansouri, S. Parsaeefard, and O. L. Alcaraz López, “Resource allocation in an Open RAN system using network slicing,” IEEE Trans. Netw. Service Manag., vol. 20, no. 1, pp. 471–485, Mar. 2023, doi: 10.1109/TNSM.2022.3205415.
C. V. Nahum et al., “Intent-aware radio resource scheduling in a RAN slicing scenario using reinforcement learning,” IEEE Trans. Wireless Commun., vol. 23, no. 3, pp. 2253–2267, Mar. 2024, doi: 10.1109/TWC.2023.3297014.
Y. Chen, R. Yao, H. Hassanieh, and R. Mittal, “Channel-aware 5G RAN slicing with customizable scheduling,” in Proc. 20th USENIX Symp. Netw. Syst. Des. Implement. (NSDI), Boston, MA, USA, Apr. 2023, pp. 433–451.
J. A. Hurtado Sánchez, K. Casilimas, and O. M. Caicedo Rendon, “Deep reinforcement learning for resource management on network slicing: A survey,” Sensors, vol. 22, no. 8, p. 3031, Apr. 2022, doi: 10.3390/s22083031.
R. Raftopoulos, S. D’Oro, T. Melodia, and G. Schembra, “DRL-based latency-aware network slicing in O-RAN with time-varying SLAs,” in Proc. Int. Conf. Comput., Netw. Commun. (ICNC), Big Island, HI, USA, Feb. 2024, pp. 583–588, doi: 10.1109/ICNC59882.2024.10556357.
M. V. Ngo et al., “RAN Intelligent Controller (RIC): From open-source implementation to real-world validation,” ICT Express, vol. 10, no. 3, pp. 680–691, Jun. 2024, doi: 10.1016/j.icte.2024.02.001.
X. Sun et al., “Towards Efficient RAN Slicing: A Deep Hierarchical Reinforcement Learning Framework,” J. Parallel Distrib. Comput., 2024.
Y. L. Lee, T. C. Chuah, J. Loo, and F. Ke, “Proportional-fair uplink resource allocation with statistical QoS provisioning for RAN slicing,” Phys. Commun., vol. 65, Art. no. 102389, Aug. 2024, doi: 10.1016/j.phycom.2024.102389.
N. Moosavi, M. Sinaie, P. Azmi, and J. Huusko, “Delay aware resource allocation with radio remote head cooperation in user-centric C-RAN,” IEEE Commun. Lett., vol. 25, no. 7, pp. 2343–2347, Jul. 2021, doi: 10.1109/LCOMM.2021.3069324.
S. Lagén, X. Gelabert, L. Giupponi, and A. Hansson, “Fronthaul-aware scheduling strategies for dynamic modulation compression in next generation RANs,” IEEE Trans. Mob. Comput., vol. 22, no. 5, pp. 2725–2740, May 2023, doi: 10.1109/TMC.2021.3138439.
Z. Ji, Z. Qin, and X. Tao, “Meta federated reinforcement learning for distributed resource allocation,” IEEE Trans. Wireless Commun., vol. 23, no. 7, pp. 7865–7876, Jul. 2024, doi: 10.1109/TWC.2023.3345363.
A. M. Nagib, H. Abou-Zeid, and H. S. Hassanein, “Accelerating reinforcement learning via predictive policy transfer in 6G RAN slicing,” IEEE Trans. Netw. Service Manag., vol. 20, no. 2, pp. 1170–1183, Jun. 2023, doi: 10.1109/TNSM.2023.3259028.
J. Song, G. de Veciana, and S. Shakkottai, “Meta-scheduling for the wireless downlink through learning with bandit feedback,” IEEE/ACM Trans. Netw., vol. 30, no. 2, pp. 487–500, Apr. 2022, doi: 10.1109/TNET.2021.3117783.
R. Kirk, A. Zhang, E. Grefenstette, and T. Rocktäschel, “A survey of zero-shot generalisation in deep reinforcement learning,” J. Artif. Intell. Res., vol. 76, pp. 201–264, Jan. 2023, doi: 10.1613/jair.1.14174.
Z. Geng, C. She, R. Wang, and B. Vucetic, “Zero-shot learning for beam management in LEO satellite communications,” IEEE Trans. Wireless Commun., vol. 23, no. 10, pp. 14512–14526, Oct. 2024, doi: 10.1109/TWC.2024.3396860.
S. D’Oro, M. Polese, L. Bonati, H. Cheng, and T. Melodia, “dApps: Distributed applications for real-time inference and control in O-RAN,” IEEE Commun. Mag., vol. 60, no. 11, pp. 52–58, Nov. 2022, doi: 10.1109/MCOM.002.2200079.
A1 Interface: General Aspects and Principles, ETSI TS 103 983 V4.0.0, European Telecommunications Standards Institute (ETSI), May 2025. [Online]. Available: https://www.etsi.org/standards
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Scientific Journal of University of Benghazi
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
