Abstract:
|
RAN virtualization will become a key technology for the last mileof next-generation mobile networks driven by initiatives such asthe O-RAN alliance. However, due to the computing fluctuationsinherent to wireless dynamics and resource contention in sharedcomputing infrastructure, the price to migrate fromdedicatedtosharedplatforms may be too high. Indeed, we show in this paperthat the baseline architecture of a base station’s distributed unit(DU) collapses upon moments of deficit in computing capacity.Recent solutions to accelerate some signal processing tasks certainlyhelp but do not tackle the core problem: a DU pipeline that requirespredictable computing to provide carrier-grade reliability.We present Nuberu, a novel pipeline architecture for 4G/5G DUsspecifically engineered for non-deterministic computing platforms.Our design has one key objective to attain reliability: to guaranteea minimum set of signals that preserve synchronization betweenthe DU and its users during computing capacity shortages and,provided this, maximize network throughput. To this end, we usetechniques such as tight deadline control, jitter-absorbing buffers,predictive HARQ, and congestion control. Using an experimentalprototype, we show that Nuberu attains>95%of the theoreticalspectrum efficiency in hostile environments, where state-of-artapproaches lose connectivity, and at least 80% resource savings. |
Rights:
|
Permission to make digital or hard copies of all or part of this work for personal or
classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from ermissions@acm.org.
ACM MobiCom ’21, October 25–29, 2021, New Orleans, LA, USA
© 2021 Association for Computing Machinery.
ACM ISBN 978-1-4503-8342-4/21/10. . . $15.00
https://doi.org/10.1145/3447993.3483266 |