Scholarship 22/08143-4 - Redes de computadores, Redes definidas por software - BV FAPESP
Advanced search
Start date
Betweenand

Communication model evaluation for optimization IoT in 5G through network programmability

Grant number: 22/08143-4
Support Opportunities:Scholarships in Brazil - Post-Doctoral
Start date until: August 01, 2022
End date until: July 31, 2023
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computer Systems
Agreement: MCTI/MC
Principal Investigator:Cristiano Bonato Both
Grantee:Sivasankari S A
Host Institution: Unidade Acadêmica de Pesquisa e Pós-Graduação. Unisinos. São Leopoldo , SP, Brazil
Associated research grant:20/05182-3 - PORVIR-5G: programability, orchestration and virtualization in 5G networks, AP.TEM

Abstract

The objective of this work is to evaluate the programmable machine-to-machine mass communication model for IoT in LPWAN, giving a more scientific and robust character to the use of LPWAN technologies to the 5G networks. For this, the scholarship holder must review the previous work and compare it with the current literature, in order to refine and improve the quality of the previous proposal. A sliced resource orchestration system in networks to optimize IoT applications should be developed using experimental environments provided bye the consortium.The fellow will investigate several techniques to propose new QoS agreements: optimization models, multi-agent machine learning systems, negotiation protocols. The problem becomes resonant from the research point of view, why it is necessary to understand how the user behaves before to a service degradation, but without him participating in the decision (user out of the loop). To climb to modeling, the fellow must employ innovative machine learning concepts, such as knowledge transfer and few-shot learning. Both concepts work with the dichotomy of current Artificial Intelligence technologies. Thus, knowledge transfer and few-shot learning seek to use the deeper layers of neural networks (in the case of knowledge transfers) or classifying new unlabeled inputs into clusters known (few-shot learning) to increase effectiveness in scenarios where we have little data. THE proposed solution should be able to identify network traffic characteristic of IoT applications and change the network infrastructure so that it improves the quality of service if necessary. (AU)

News published in Agência FAPESP Newsletter about the scholarship:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Please report errors in scientific publications list using this form.