Estimation of the End-to-End Delay in 5G Networks Through Gaussian Mixture Models
Abstract
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.
Domains
Computer Science [cs]Origin | Explicit agreement for this submission |
---|---|
Licence |