O-RAN Xapps Conflict Prediction Using Graph Convolutional Networks

Open Radio Access Network (O-RAN) adopts a flexible, open, and virtualized architecture with standardized interfaces, reducing dependency on a single supplier. O-RAN hosts many intelligent applications known as eXtended Applications (xApps). xApps are applications deployed at the RAN Intelligent Controller (RIC) that leverage advanced Artificial Intelligence/Machine Learning (AI/ML) algorithms to make dynamic decisions for network optimization. Each application operates with distinct optimization objectives and is managed by independent operators while accessing shared network resources. Conflicts in this context occur when a deployed xApp’s objective interferes with another xApp, resulting in incompatible actions or decisions that may negatively impact network performance. The lack of a unified mechanism to coordinate and prioritize the actions of different applications can create three types of conflicts (direct, indirect, and implicit). Conflict prediction in O-RAN refers to the proactive analytical process through which potential interactions or behaviors that may lead to conflicts between network applications are identified in advance, prior to their manifestation within the operational system. In our paper, we introduce a novel data-driven Graph Convolutional Network (GCN)-based method called GRAPH-based Intelligent xApp Conflict Prediction and Analysis (GRAPHICA). It predicts three types of conflicts (direct, indirect, and implicit) and pinpoints the root causes (xApps). GRAPHICA captures the complex and hidden dependencies among the xApps, controlled parameters, and key performance indicators (KPIs) in O-RAN to predict possible conflicts. Then, it identifies the root causes (xApps) contributing to the predicted conflicts. The proposed method is evaluated using highly imbalanced synthetic datasets, in which conflict instances constitute between 40% and merely 10% of the data. This evaluation setting is designed to reflect realistic operational environments where conflicts are infrequent, thereby enabling a comprehensive assessment of the model’s performance under real-world conditions. Experimental results demonstrate a high F1-score over 98% for the synthesized datasets with different levels of class imbalance.