An Intelligent User Plane to Support In-Network Computing in 6G Networks

Schwarzmann, Susanna; Trivisonno, Riccardo; Lange, Stanislav; Civelek, Tugce Erkilic; Corujo, Daniel; Guerzoni, Riccardo; Zinner, Thomas; Mahmoodi, Toktam

doi:10.1109/icc45041.2023.10279652

Cited by 6 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The UP path involves one or more UPEs and the radio access network. A compute task is carried out at one of the involved UPEs along the UP path [6]. An example of a compute task is in-network video quality adaptation implemented in [22].…”

Section: A the Automated System For Dynamic Task Migrationmentioning

confidence: 99%

See 1 more Smart Citation

Distributed Intelligence for Dynamic Task Migration in the 6G User Plane using Deep Reinforcement Learning

Majumdar,

Schwarzmann,

Trivisonno

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>In-Network Computing (INC) is a currently emerging paradigm. Realizing INC in 6G networks could mean that user plane entities (UPEs) carry out computations on packets while transmitting them. These computations may have specific requirements in terms of their completion time. In case of high compute pressure at one UPE, migrating computations to another UPE may be beneficial, in order to avoid exceeding the completion time requirement. Centralized migration approaches suffer from increased signaling and are prone to react too slow. Therefore, this paper investigates the applicability of distributed intelligence to tackle the problem of compute task migration in the 6G user plane. Each UPE is equipped with an intelligent agent, enabling autonomous decisions on whether computations should be migrated to another UPE. To enable the intelligent agents to learn and apply an optimal task migration policy, we investigate and compare of two state-of-the-art Deep Reinforcement Learning (DRL) approaches: Advantage Actor-Critic (A2C) and Double Deep Q-Network (DDQN). We show, via simulations, that the performance of both solutions, in terms of the percentage of tasks exceeding their completion time requirement, is near-optimal and training A2C is at least 60% faster. </p>

show abstract

Section: A the Automated System For Dynamic Task Migrationmentioning

confidence: 99%

“…INC may become a potential key enabler for 6G, among others, because it is capable of significantly reducing the applicationlevel delay [4] and the traffic volume [5]. It can further support the design of light-weight mobile devices, by allowing them to offload compute-intensive tasks to the network [6].…”

Section: Introductionmentioning

confidence: 99%