From Hype to Reality: The Road Ahead of Deploying DRL in 6G Networks
Abstract: The industrial landscape is rapidly evolving with the advent of 6G applications, which demand massive connectivity, high computational capacity, and ultra-low latency. These requirements present new challenges, which can no longer be efficiently addressed by conventional strategies. In response, this article underscores the transformative potential of Deep Reinforcement Learning (DRL) for 6G, highlighting its advantages over classic machine learning solutions in meeting the demands of 6G. The necessity of DRL is further validated through three DRL applications in an end-to-end communication procedure, including wireless access control, baseband function placement, and network slicing coordination. However, DRL-based network management initiatives are far from mature. We extend the discussion to identify the challenges of applying DRL in practical networks and explore potential solutions along with their respective limitations. In the end, these insights are validated through a practical DRL deployment in managing network slices on the testbed.
- M. Series, “Framework and Overall Objectives of the Future Development of IMT for 2030 and Beyond,” Recommendation ITU, vol. 2083, no. 0, 2023.
- X. Lin, “Artificial Intelligence in 3GPP 5G-Advanced: A Survey,” arXiv preprint arXiv:2305.05092, 2023.
- M. C. Gamito, “The Role of ETSI in the EU’s Regulation and Governance of Artificial Intelligence,” Innovation: The European Journal of Social Science Research, pp. 1–16, 2024.
- M. W. Berry, A. Mohamed, and B. W. Yap, “Supervised and Unsupervised Learning for Data Science,” in Springer, 2019.
- P. Ladosz et al., “Exploration in Deep Reinforcement Learning: A Survey,” Information Fusion, vol. 85, pp. 1–22, 2022.
- X. Zhou et al., “DRL-Driven Intelligent Access Traffic Management for Hybrid 5G-WiFi Multi-RAT Networks,” in Proc. of IEEE PIMRC, 2023.
- H. Li et al., “DRL-Based Energy-Efficient Baseband Function Deployments for Service-Oriented Open RAN,” IEEE Trans. Green Commun. Netw., vol. 8, no. 1, pp. 224–237, 2024.
- ——, “NetMind: Adaptive RAN Baseband Function Placement by GCN Encoding and Maze-solving DRL,” in Proc. of IEEE WCNC, 2024.
- ETSI GS MEC 003, “Multi-access Edge Computing (MEC); Framework and Reference Architecture,” V3.1.1, Mar. 2022.
- O-RAN.WG1.OAD-R003-v10.00, “O-RAN Work Group 1 (Use Cases and Overall Architecture) O-RAN Architecture Description,” Oct. 2023.
- Y. Kim and H. Lim, “Multi-Agent Reinforcement Learning-based Resource Management for End-to-End Network Slicing,” IEEE Access, vol. 9, pp. 56 178–56 190, 2021.
- M. Tsampazi et al., “A Comparative Analysis of Deep Reinforcement Learning-based xApps in O-RAN,” in Proc. of IEEE GLOBECOM, 2023, pp. 1638–1643.
- M. Polese et al., “ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-Loop Control on Programmable Experimental Platforms,” IEEE TMC, vol. 22, no. 10, pp. 5787–5800, 2022.
- P. Caballero et al., “Network Slicing Games: Enabling Customization in Multi-Tenant Mobile Networks,” IEEE/ACM Trans. Netw., vol. 27, no. 2, pp. 662–675, 2019.
- W. Wang et al., “From Few to More: Large-Scale Dynamic Multiagent Curriculum Learning,” in Proc. AAAI Conf. Artif. Intell., vol. 34, no. 05, 2020, pp. 7293–7300.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.