MOBICOM 2023, 29th Annual International Conference On Mobile Computing And Networking, 2-6 October 2023, Madrid, Spain
As modern manufacturing lines embrace greater modularity and flexibility, the need to transition factory networks from wired to wireless grows. Yet the mission-critical nature of factory networks poses a key challenge - connecting numerous diverse machines with high QoS predictability. After formulating this challenge as predictable RAN optimization
via Reinforcement Learning (RL), we highlight a major-yetoverlooked modeling issue: matching the packet handling mechanics of a production/real RAN software. In this paper,
we show that these mismatches inside RAN simulators can cause non-trivial QoS gaps in production. Then, we present Twin5G, a novel training solution that brings scalable and
near-discrete-time emulations to real RAN software, removing the need for RAN simulators. In a RAN Slicing example, Twin5G-trained policy outperforms simulator-trained and standard RL-trained policies in both QoS achieved (+16%) and predictability (+19%) during tests.
Type:
Poster / Demo
City:
Madrid
Date:
2023-10-02
Department:
Communication systems
Eurecom Ref:
7461
Copyright:
© ACM, 2023. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in MOBICOM 2023, 29th Annual International Conference On Mobile Computing And Networking, 2-6 October 2023, Madrid, Spain https://doi.org/10.1145/3570361.3615758
See also: