1.
Li, Haiyuan; Madhukumar, Hari; Li, Peizheng; Liu, Yuelin; Teng, Yiran; Wu, Yulei; Wang, Ning; Yan, Shuangyi; Simeonidou, Dimitra
Toward Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges Journal Article
In: IEEE Communications Magazine, 2025, ISSN: 0163-6804.
Abstract | Links | BibTeX | Tags: DRL, MEC, Network management and orchestration, O-RAN, Practical deployment
@article{li_toward_2025,
title = {Toward Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges},
author = {Haiyuan Li and Hari Madhukumar and Peizheng Li and Yuelin Liu and Yiran Teng and Yulei Wu and Ning Wang and Shuangyi Yan and Dimitra Simeonidou},
doi = {10.1109/MCOM.001.2500207},
issn = {0163-6804},
year = {2025},
date = {2025-07-01},
journal = {IEEE Communications Magazine},
abstract = {Deep Reinforcement Learning (DRL) has emerged as a powerful solution for meeting the growing demands for connectivity, reliability, low latency and operational efficiency in advanced networks. However, most research has focused on theoretical analysis and simulations, with limited investigation into real-world deployment. To bridge the gap and support practical DRL deployment for network management, we first present an orchestration framework that integrates ETSI Multi-access Edge Computing (MEC) with Open RAN, enabling seamless adoption of DRL-based strategies across different time scales while enhancing agent lifecycle management. We then identify three critical challenges hindering DRL's real-world deployment, including asynchronous requests from unpredictable or bursty traffic, adaptability and generalization across heterogeneous topologies and evolving service demands, and prolonged convergence and service interruptions due to exploration in live operational environments. To address these challenges, we propose a three-fold solution strategy: advanced time-series integration for handling asynchronized traffic, flexible architecture design such as multi-agent DRL and incremental learning to support heterogeneous scenarios, and simulation-driven deployment with transfer learning to reduce convergence time and service disruptions. Lastly, the feasibility of the MEC-O-RAN architecture is validated on an urban-wide testing infrastructure, and two real-world use cases are presented, showcasing the three identified challenges and demonstrating the effectiveness of the proposed solutions.},
keywords = {DRL, MEC, Network management and orchestration, O-RAN, Practical deployment},
pubstate = {published},
tppubtype = {article}
}
Deep Reinforcement Learning (DRL) has emerged as a powerful solution for meeting the growing demands for connectivity, reliability, low latency and operational efficiency in advanced networks. However, most research has focused on theoretical analysis and simulations, with limited investigation into real-world deployment. To bridge the gap and support practical DRL deployment for network management, we first present an orchestration framework that integrates ETSI Multi-access Edge Computing (MEC) with Open RAN, enabling seamless adoption of DRL-based strategies across different time scales while enhancing agent lifecycle management. We then identify three critical challenges hindering DRL's real-world deployment, including asynchronous requests from unpredictable or bursty traffic, adaptability and generalization across heterogeneous topologies and evolving service demands, and prolonged convergence and service interruptions due to exploration in live operational environments. To address these challenges, we propose a three-fold solution strategy: advanced time-series integration for handling asynchronized traffic, flexible architecture design such as multi-agent DRL and incremental learning to support heterogeneous scenarios, and simulation-driven deployment with transfer learning to reduce convergence time and service disruptions. Lastly, the feasibility of the MEC-O-RAN architecture is validated on an urban-wide testing infrastructure, and two real-world use cases are presented, showcasing the three identified challenges and demonstrating the effectiveness of the proposed solutions.