The Open Radio Access Network (O-RAN) architecture enables the deployment of third-party applications on the RAN Intelligent Controllers (RICs) to provide Mobile Network Operators (MNOs) with different functionality. However, the operation of third-party applications in the Near Real-Time RIC (Near-RT RIC), known as xApps, can result in conflicting interactions. Each xApp can independently modify the same control parameters to achieve distinct outcomes, which has the potential to cause performance degradation and network instability. The current conflict detection and mitigation solutions in the literature assume that all conflicts are known a priori, which does not always hold due to complex and often hidden relationships between control parameters and Key Performance Indicators (KPIs). In this paper, we introduce a novel data-driven Graph Neural Network (GNN)-based method for reconstructing conflict graphs. Specifically, we leverage GraphSAGE, an inductive learning framework, to dynamically learn the hidden relationships between xApps, control parameters, and KPIs. Our experimental results validate our proposed method for reconstructing conflict graphs and identifying all types of conflicts in O-RAN.

翻译：开放无线接入网（O-RAN）架构支持在无线接入网智能控制器（RICs）上部署第三方应用，从而为移动网络运营商（MNOs）提供多样化功能。然而，在近实时无线接入网智能控制器（Near-RT RIC）中运行的第三方应用（称为xApps）可能产生冲突性交互。每个xApp可独立修改相同的控制参数以实现不同目标，这可能导致性能下降和网络不稳定。现有文献中的冲突检测与缓解方案均假设所有冲突均为先验已知，但由于控制参数与关键性能指标（KPIs）之间存在复杂且往往隐含的关联，该假设并非始终成立。本文提出一种基于图神经网络（GNN）的新型数据驱动方法，用于重构冲突图。具体而言，我们采用归纳学习框架GraphSAGE动态学习xApps、控制参数与KPIs之间的隐含关系。实验结果验证了所提方法在重构冲突图及识别O-RAN中各类冲突的有效性。