Process-Informed Multi-Agent Reinforcement Learning for Joint Radio-Compute Orchestration in Industrial O-RAN
IEEE Networking Letters · 2026 · 8 · 199-203
DOI: 10.1109/lnet.2026.3687238 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Networking Letters, 2026. Verfasst von Xingqi Wu und 5 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben.
Abstract (Originalsprache)
Industrial open radio access network (O-RAN) systems must support manufacturing workloads with dynamically varying communication and computation demands driven by production processes. Existing O-RAN orchestration mechanisms remain largely network-centric and fail to capture such process-induced variability. This letter proposes a decentralized process-informed reinforcement learning (RL) framework for joint radio and compute orchestration in industrial O-RAN. Distributed agents at radio units (RUs) adapt physical resource block (PRB) and compute allocations based on workload and latency requirements. Using a multi-agent dueling deep Q-network architecture, the approach improves latency fulfillment and reliability under nonstationary industrial traffic. Simulation results demonstrate consistent gains over network-centric multi-agent baselines.
Zitieren
APA
Wu, X., Wang, Y., Farooq, J., Ghazzai, H., Butt, M. M., & Setti, G. (2026). Process-Informed Multi-Agent Reinforcement Learning for Joint Radio-Compute Orchestration in Industrial O-RAN. IEEE Networking Letters, 8, 199-203. https://doi.org/10.1109/lnet.2026.3687238
Vancouver
Wu X, Wang Y, Farooq J, Ghazzai H, Butt MM, Setti G. Process-Informed Multi-Agent Reinforcement Learning for Joint Radio-Compute Orchestration in Industrial O-RAN. IEEE Networking Letters. 2026;8:199-203. doi:10.1109/lnet.2026.3687238
BibTeX
@article{Wu2026,
author = {Wu, Xingqi and Wang, Yuhui and Farooq, Junaid and Ghazzai, Hakim and Butt, M. Majid and Setti, Gianluca},
title = {Process-Informed Multi-Agent Reinforcement Learning for Joint Radio-Compute Orchestration in Industrial O-RAN},
journal = {IEEE Networking Letters},
year = {2026},
volume = {8},
pages = {199--203},
doi = {10.1109/lnet.2026.3687238}
}
EUVIMED