The efficient allocation of radio resources is an essential trait of 5G/6G radio access networks (RANs), as they are called to meet diverse QoS requirements of highly demanding applications. To equip RANs with such an ability and, at the same time, meet their function split constraints, we envision a distributed learning approach for radio resource allocation that makes the most out of the Central Unit (CU) and Distributed Unit (DU) components by effectively exploiting their synergy. On the one hand, our solution, named MERGE, leverages the knowledge of the radio connectivity dynamics that each DU can acquire through the local use of a deep reinforcement learning radio agent. On the other hand, it lets the CU collect such agents in a crowdsourcing fashion, and, then, thanks to a meta-learning policy, properly select and aggregate them to create up-to-date radio agents of the right size (hence, complexity level) to fit the computing constraints of the individual DUs. Our results show that MERGE can match the performance of the highest- complexity radio model with 25% less computational require- ments, and, for a given computational resource, it outperforms a single pruned model with a 19% increase in QoS.

MERGE: Meta Reinforcement Learning for Tunable RL Agents at the Edge / Tripathi, Sharda; Chiasserini, Carla Fabiana. - ELETTRONICO. - (2023), pp. 3506-3511. (Intervento presentato al convegno IEEE GLOBECOM 2023 tenutosi a Kuala Lumpur (Malaysia) nel 04-08 December 2023) [10.1109/GLOBECOM54140.2023.10437278].

MERGE: Meta Reinforcement Learning for Tunable RL Agents at the Edge

Carla Fabiana Chiasserini
2023

Abstract

The efficient allocation of radio resources is an essential trait of 5G/6G radio access networks (RANs), as they are called to meet diverse QoS requirements of highly demanding applications. To equip RANs with such an ability and, at the same time, meet their function split constraints, we envision a distributed learning approach for radio resource allocation that makes the most out of the Central Unit (CU) and Distributed Unit (DU) components by effectively exploiting their synergy. On the one hand, our solution, named MERGE, leverages the knowledge of the radio connectivity dynamics that each DU can acquire through the local use of a deep reinforcement learning radio agent. On the other hand, it lets the CU collect such agents in a crowdsourcing fashion, and, then, thanks to a meta-learning policy, properly select and aggregate them to create up-to-date radio agents of the right size (hence, complexity level) to fit the computing constraints of the individual DUs. Our results show that MERGE can match the performance of the highest- complexity radio model with 25% less computational require- ments, and, for a given computational resource, it outperforms a single pruned model with a 19% increase in QoS.
2023
979-8-3503-1090-0
File in questo prodotto:
File Dimensione Formato  
Meta_Learning-5.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 386.57 kB
Formato Adobe PDF
386.57 kB Adobe PDF Visualizza/Apri
Chiasserini-MERGE.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 473.66 kB
Formato Adobe PDF
473.66 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2980931