No Free Lunch: Balancing Learning and Exploitation at the Network Edge

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mason, Federico, Chiariotti, Federico, Zanella, Andrea
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916363527782400
author Mason, Federico
Chiariotti, Federico
Zanella, Andrea
author_facet Mason, Federico
Chiariotti, Federico
Zanella, Andrea
contents Over the last few years, the DRL paradigm has been widely adopted for 5G and beyond network optimization because of its extreme adaptability to many different scenarios. However, collecting and processing learning data entail a significant cost in terms of communication and computational resources, which is often disregarded in the networking literature. In this work, we analyze the cost of learning in a resource-constrained system, defining an optimization problem in which training a DRL agent makes it possible to improve the resource allocation strategy but also reduces the number of available resources. Our simulation results show that the cost of learning can be critical when evaluating DRL schemes on the network edge and that assuming a cost-free learning model can lead to significantly overestimating performance.
format Preprint
id arxiv_https___arxiv_org_abs_2111_11912
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle No Free Lunch: Balancing Learning and Exploitation at the Network Edge
Mason, Federico
Chiariotti, Federico
Zanella, Andrea
Networking and Internet Architecture
Over the last few years, the DRL paradigm has been widely adopted for 5G and beyond network optimization because of its extreme adaptability to many different scenarios. However, collecting and processing learning data entail a significant cost in terms of communication and computational resources, which is often disregarded in the networking literature. In this work, we analyze the cost of learning in a resource-constrained system, defining an optimization problem in which training a DRL agent makes it possible to improve the resource allocation strategy but also reduces the number of available resources. Our simulation results show that the cost of learning can be critical when evaluating DRL schemes on the network edge and that assuming a cost-free learning model can lead to significantly overestimating performance.
title No Free Lunch: Balancing Learning and Exploitation at the Network Edge
topic Networking and Internet Architecture
url https://arxiv.org/abs/2111.11912