Causal Online Learning of Safe Regions in Cloud Radio Access Networks
Preprint
Abstract
Cloud radio access networks (RANs) enable cost-effective management of mobile networks by dynamically scaling their capacity on demand. However, deploying adaptive controllers to implement such dynamic scaling in operational networks is challenging due to the risk of breaching service agreements and operational constraints. To mitigate this challenge, we present a novel method for learning the safe operating region of the RAN, i.e., the set of resource allocations and network configurations for which its specification is fulfilled. The method, which we call (C)ausal (O)nline (L)earning, operates in two online phases: an inference phase and an intervention phase. In the first phase, we passively observe the RAN to infer an initial safe region via causal inference and Gaussian process regression. In the second phase, we gradually expand this region through interventional Bayesian learning. We prove that COL ensures that the learned region is safe with a specified probability and that it converges to the full safe region under standard conditions. We experimentally validate COL on a 5G testbed. The results show that COL quickly learns the safe region while incurring low operational cost and being up to 10x more sample-efficient than current state-of-the-art methods for safe learning.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Understanding O-RAN: Architecture, Interfaces, Algorithms, Security, and Research ChallengesIEEE Communications Surveys & Tutorials, 2023
- Zero Touch Management: A Survey of Network Automation Solutions for 5G and 6G NetworksIEEE Communications Surveys & Tutorials, 2022
- Algorithmic Learning in a Random World2022
- Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing SystemsIEEE Transactions on Mobile Computing, 2020
- Delay-Aware Microservice Coordination in Mobile Edge Computing: A Reinforcement Learning ApproachIEEE Transactions on Mobile Computing, 2019
- Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing NetworksIEEE Transactions on Mobile Computing, 2019
- Predictive Control for Linear and Hybrid Systems2017
- Cloud RAN for Mobile Networks—A Technology OverviewIEEE Communications Surveys & Tutorials, 2014
- Controllers for reachability specifications for hybrid systemsAutomatica, 1999
- Uppaal in a nutshellInternational Journal on Software Tools for Technology Transfer, 1997