# ONETS: Online Network Slice Broker From Theory to Practice

arXiv: https://arxiv.org/abs/1801.03484 · HTML: https://mlsanity.com/paper/1801.03484/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jan 2018.

## Built on by (most cited first, 1 of 1)

- [Multi-Objective Provisioning of Network Slices using Deep Reinforcement Learning](https://mlsanity.com/paper/2207.13821/) (2022)

## Abstract (arXiv)

Network slicing allows mobile network operators to open their physical network infrastructure platform to the concurrent deployment of multiple logical self-contained networks, i.e., network slices. In this paper we propose and analyze ONETS: an Online NETwork Slicing solution that (i) builds on the budgeted lock-up multi-armed bandit mathematical model and properties, (ii) derives its analytical bounds in our proposed extension for network slicing, (iii) seamlessly integrates into the 3GPP architecture, (iv) proves its feasibility through a proof-of-concept implementation on commercial hardware considering three network slices and (v) allows for the design of a low-complexity online network slice brokering solution that maximizes multiplexing gains.