Graph Reinforcement Learning for QoS-Aware Load Balancing in Open Radio Access Networks

TL;DR

The paper tackles QoS-aware load balancing in multi-band O-RAN by formulating LB as a graph-based Markov decision process. It introduces a GNN-enabled off-policy dueling DQN that operates on RAN graphs with heterogeneous UE and cell nodes, and employs a subgraph inference technique to scale to large networks. The method optimizes GBR QoS and BE coverage through a reward designed from GBR QoS metrics and BE minimum rates, and evaluates performance in a detailed system-level simulator, achieving substantial gains over max-SINR and max-RSRP baselines (e.g., a 53% reduction in QoS violations and a 4x improvement in BE 5th percentile rate). The approach demonstrates strong scalability, topology generalization, and practical potential for deployment in near-real-time O-RAN xApps, with promising avenues for broader traffic models and multi-band coordination.

Abstract

Next-generation wireless cellular networks are expected to provide unparalleled Quality-of-Service (QoS) for emerging wireless applications, necessitating strict performance guarantees, e.g., in terms of link-level data rates. A critical challenge in meeting these QoS requirements is the prevention of cell congestion, which involves balancing the load to ensure sufficient radio resources are available for each cell to serve its designated User Equipments (UEs). In this work, a novel QoS-aware Load Balancing (LB) approach is developed to optimize the performance of Guaranteed Bit Rate (GBR) and Best Effort (BE) traffic in a multi-band Open Radio Access Network (O-RAN) under QoS and resource constraints. The proposed solution builds on Graph Reinforcement Learning (GRL), a powerful framework at the intersection of Graph Neural Network (GNN) and RL. The QoS-aware LB is modeled as a Markov Decision Process, with states represented as graphs. QoS consideration are integrated into both state representations and reward signal design. The LB agent is then trained using an off-policy dueling Deep Q Network (DQN) that leverages a GNN-based architecture. This design ensures the LB policy is invariant to the ordering of nodes (UE or cell), flexible in handling various network sizes, and capable of accounting for spatial node dependencies in LB decisions. Performance of the GRL-based solution is compared with two baseline methods. Results show substantial performance gains, including a $53\%$ reduction in QoS violations and a fourfold increase in the 5th percentile rate for BE traffic.

Figures (4)

• Figure 1: Proposed GNN-based dueling DQN.
• Figure 2: CDF of the QoS dissatisfaction rate.
• Figure 3: CDF of the achieved goodput per BE UE in Mbps.
• Figure 4: Comparison of average bandwidth utilization rate per cell.