# 5G Traffic Forecasting: If Verticals and Mobile Operators Cooperate

**Authors:** Francesco Malandrino, Carla Fabiana Chiasserini

arXiv: 1901.00132 · 2019-01-03

## TL;DR

This paper explores how involving vertical industries in 5G traffic forecasting, instead of solely relying on mobile operators, can improve prediction accuracy and enhance resource orchestration.

## Contribution

It demonstrates that verticals performing traffic predictions lead to better accuracy and orchestration outcomes in 5G networks, challenging traditional assumptions.

## Key findings

- Vertical involvement reduces prediction errors.
- Improved orchestration decisions with vertical predictions.
- Real-world trace validates the benefits of vertical participation.

## Abstract

In 5G research, it is traditionally assumed that vertical industries (a.k.a verticals) set the performance requirements for the services they want to offer to mobile users, and the mobile operators alone are in charge of orchestrating their resources so as to meet such requirements. Motivated by the observation that successful orchestration requires reliable traffic predictions, in this paper we investigate the effects of having the verticals, instead of the mobile operators, performing such predictions. Leveraging a real-world, large-scale, crowd-sourced trace, we find that involving the verticals in the prediction process reduces the prediction errors and improves the quality of the resulting orchestration decisions.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/1901.00132/full.md

## Figures

7 figures with captions in the complete paper: https://tomesphere.com/paper/1901.00132/full.md

## References

14 references — full list in the complete paper: https://tomesphere.com/paper/1901.00132/full.md

---
Source: https://tomesphere.com/paper/1901.00132