RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN
release_g4tj7q7pevde5funhd2u3nqhoi
by
Peizheng Li, Jonathan Thomas, Xiaoyang Wang, Ahmed Khalil, Abdelrahim Ahmad, Rui Inacio, Shipra Kapoor, Arjun Parekh, Angela Doufexi, Arman Shojaeifard, Robert Piechocki
2021
Abstract
Radio access network (RAN) technologies continue to witness massive growth,
with Open RAN gaining the most recent momentum. In the O-RAN specifications,
the RAN intelligent controller (RIC) serves as an automation host. This article
introduces principles for machine learning (ML), in particular, reinforcement
learning (RL) relevant for the O-RAN stack. Furthermore, we review
state-of-the-art research in wireless networks and cast it onto the RAN
framework and the hierarchy of the O-RAN architecture. We provide a taxonomy of
the challenges faced by ML/RL models throughout the development life-cycle:
from the system specification to production deployment (data acquisition, model
design, testing and management, etc.). To address the challenges, we integrate
a set of existing MLOps principles with unique characteristics when RL agents
are considered. This paper discusses a systematic life-cycle model development,
testing and validation pipeline, termed: RLOps. We discuss all fundamental
parts of RLOps, which include: model specification, development and
distillation, production environment serving, operations monitoring,
safety/security and data engineering platform. Based on these principles, we
propose the best practices for RLOps to achieve an automated and reproducible
model development process.
In text/plain
format
Archived Files and Locations
application/pdf 10.6 MB
file_nkqglqa6wzd55gdx44ao2hlxse
|
arxiv.org (repository) web.archive.org (webarchive) |
2111.06978v1
access all versions, variants, and formats of this works (eg, pre-prints)