Athena: An intelligent multi-x cloud native network operator

Mohammadi, Alireza; Nikaein, Navid
IEEE Journal on Selected Areas in Communications, JSAC Special Issue on Open RAN: a New Paradigm for Open, Virtualized, Programmable, and Intelligent Cellular Networks, 28 November 2023

This paper presents ATHENA, a novel design and a new generation of MANO/OAM that fully adheres to the cloud native principles, while fostering innovation and sustainable deployment for 4G, 5G, and beyond. It elicits an agile and intelligent, dynamic control over a variety of vendors and radio stacks (multi-x) coexisting on the same network with built-in observability and at the scale. With an intent-based,
declarative, and distributed constitution, authentic to the cloud native pillars of isolation, scalability, and observability, we have established a scalable and efficient design and implemented its concrete proof-of-concept platform that is able to simplify
the adaptation of cloud native for telecommunication. ATHENA automates both the semantics and synthetics of the lifecycle of telco workloads while attending to the performance and sustainability requirements. Accompanied by intensive evaluation
on a concrete implementation, we show how several uses cases including private networking, Open RAN, and green computing would be facilitated and sustained with a low footprint and green management and operation. In particular, we improve the agility by 75% on Day-1 and 60% on Day-2 in comparison to OSM, while reducing over 93% overhead in Operation, 70% in Management, and 90% in Orchestration. ATHENA shows less than 2% performance loss for high throughput, with less than 50`s jitter. It demonstrates 99.9995% availability for immutable Day-2 upgrades and zero down-time for mutable reconfigurations. And for energy efficiency, we show improvements of maximum 17.4% per UE and 78.3% per gNB using the proposed decision-making framework.

Communication systems
Eurecom Ref:
© 2023 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.