Cascade Reinforcement Learning with State Space Factorization for O-RAN-based Traffic Steering

TL;DR

This paper introduces a novel cascade reinforcement learning framework with state space factorization for traffic steering in O-RAN networks, improving throughput by up to 24% over traditional policies.

Contribution

It proposes a state space factorization and policy decomposition approach in cascade RL for scalable, data-efficient traffic steering in O-RAN, with knowledge transfer for new regions.

Findings

CaRL outperforms heuristic and Q-table methods.

CaRL improves network throughput by up to 24%.

The approach is validated on real-world data-driven digital twins.

Abstract

The Open Radio Access Network (O-RAN) architecture empowers intelligent and automated optimization of the RAN through applications deployed on the RAN Intelligent Controller (RIC) platform, enabling capabilities beyond what is achievable with traditional RAN solutions. Within this paradigm, Traffic Steering (TS) emerges as a pivotal RIC application that focuses on optimizing cell-level mobility settings in near-real-time, aiming to significantly improve network spectral efficiency. In this paper, we design a novel TS algorithm based on a Cascade Reinforcement Learning (CaRL) framework. We propose state space factorization and policy decomposition to reduce the need for large models and well-labeled datasets. For each sub-state space, an RL sub-policy will be trained to learn an optimized mapping onto the action space. To apply CaRL on new network regions, we propose a knowledge transfer approach to initialize a new sub-policy based on knowledge learned by the trained policies. To evaluate CaRL, we build a data-driven and scalable RIC digital twin (DT) that is modeled using important real-world data, including network configuration, user geo-distribution, and traffic demand, among others, from a tier-1 mobile operator in the US. We evaluate CaRL on two DT scenarios representing two network clusters in two different cities and compare its performance with the business-as-usual (BAU) policy and other competing optimization approaches using heuristic and Q-table algorithms. Benchmarking results show that CaRL performs the best and improves the average cluster-aggregated downlink throughput over the BAU policy by 24% and 18% in these two scenarios, respectively.