Causal Online Learning of Safe Regions in Cloud Radio Access Networks

2026-02-05

AI Summary

This work addresses the challenge of dynamic scaling in cloud radio access networks, where frequent resource adjustments often violate service-level agreements and operational constraints, thereby hindering the safe deployment of adaptive controllers. To overcome this, the paper proposes a Causal Online Learning (COL) framework that uniquely integrates causal inference with online active learning. COL first constructs an initial safe region by combining passive observations with causal inference and Gaussian process regression, then progressively expands this region through intervention-based Bayesian optimization. This approach guarantees provable safety and converges efficiently to the full safe set. Experimental validation on a 5G testbed demonstrates that COL achieves up to tenfold higher sample efficiency compared to existing methods, while simultaneously reducing operational costs and enabling rapid convergence.

Technology Category

• Machine Learning: Causal Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Security and Privacy: Large-scale security measurements

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.

Problem

• Cloud RAN
• safe learning
• dynamic scaling
• operational constraints
• service agreements

Innovation

• Causal Inference
• Online Learning
• Safe Region Learning
• Bayesian Optimization
• Cloud RAN