%0 Conference Proceedings
%T Estimation of the End-to-End Delay in 5G Networks Through Gaussian Mixture Models
%+ Universidade Nova de Lisboa = NOVA University Lisbon (NOVA)
%+ Instituto de Telecomunicações [Lisboa, Portugal]
%A Fadhil, Diyar
%A Oliveira, Rodolfo
%Z Part 2: Cyber-Physical Systems
%< avec comité de lecture
%@ 978-3-031-07519-3
%( IFIP Advances in Information and Communication Technology
%B 13th Doctoral Conference on Computing, Electrical and Industrial Systems (DoCEIS)
%C Caparica, Portugal
%Y Luis M. Camarinha-Matos
%I Springer International Publishing
%3 Technological Innovation for Digitalization and Virtualization
%V AICT-649
%P 83-91
%8 2022-06-29
%D 2022
%R 10.1007/978-3-031-07520-9_8
%K End-to-End delay
%K Quality of service
%K Gaussian mixture model
%Z Computer Science [cs]Conference papers
%X Network analytics provide a comprehensive picture of the network's Quality of Service (QoS), including the End-to-End (E2E) delay. In this paper, we characterize the E2E delay of heterogeneous networks when a single known probabilistic density function (PDF) is not adequate to model its distribution. To this end, multiple PDFs, denominated as components, are assumed in a Gaussian Mixture Model (GMM) to represent the distribution of the E2E delay. The accuracy and computation time of the GMM is evaluated for a different number of components. The results presented in the paper consider a dataset containing E2E delay traces sampled from a 5G network, showing that the GMM’s accuracy allows addressing the rich diversity of probabilistic patterns found in 5G networks and its computation time is adequate for real-time applications.
%G English
%Z TC 5
%Z WG 5.5
%2 https://inria.hal.science/hal-04308396/document
%2 https://inria.hal.science/hal-04308396/file/528070_1_En_8_Chapter.pdf
%L hal-04308396
%U https://inria.hal.science/hal-04308396
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-WG5-5
%~ IFIP-DOCEIS
%~ IFIP-AICT-649