Atlas: Automate Online Service Configuration in Network Slicing

TL;DR

Atlas is an online system that automates network slice configuration using learn-to-configure methods, reducing discrepancies between simulation and real networks, and improving resource efficiency and slice quality.

Contribution

The paper introduces Atlas, a novel online network slicing system that combines a learning-based simulator, offline policy training, and online policy adaptation with safe exploration.

Findings

Achieves 63.9% resource usage reduction

Achieves 85.7% slice quality improvement

Reduces regret compared to state-of-the-art solutions

Abstract

Network slicing achieves cost-efficient slice customization to support heterogeneous applications and services. Configuring cross-domain resources to end-to-end slices based on service-level agreements, however, is challenging, due to the complicated underlying correlations and the simulation-to-reality discrepancy between simulators and real networks. In this paper, we propose Atlas, an online network slicing system, which automates the service configuration of slices via safe and sample-efficient learn-to-configure approaches in three interrelated stages. First, we design a learning-based simulator to reduce the sim-to-real discrepancy, which is accomplished by a new parameter searching method based on Bayesian optimization. Second, we offline train the policy in the augmented simulator via a novel offline algorithm with a Bayesian neural network and parallel Thompson sampling. Third, we online learn the policy in real networks with a novel online algorithm with safe exploration and Gaussian process regression. We implement Atlas on an end-to-end network prototype based on OpenAirInterface RAN, OpenDayLight SDN transport, OpenAir-CN core network, and Docker-based edge server. Experimental results show that, compared to state-of-the-art solutions, Atlas achieves 63.9% and 85.7% regret reduction on resource usage and slice quality of experience during the online learning stage, respectively.