用图神经网络预测O-RAN中xApps的冲突，提前发现潜在问题。
O-RAN Xapps Conflict Prediction Using Graph Convolutional Networks
- 基于图卷积网络建模xApps间依赖关系，捕捉隐藏冲突线索。
- 在仅10%-40%冲突数据的不平衡数据上实现超98%的F1分数。
- 可定位冲突根源，适合网络优化与智能运维场景使用。
O-RAN平台运行大量称为eXtended Applications（xApps）的智能应用，这些应用利用先进算法动态决策以优化网络性能。各应用具有不同优化目标，由独立运营商管理，共享网络资源，当其目标相互干扰时便产生冲突，导致不兼容行为并影响网络表现。缺乏统一协调机制易引发多种冲突。本文提出一种基于图卷积网络的新型数据驱动方法——GRAPHICA，用于预测O-RAN中三类冲突并定位根本原因。该方法能捕捉xApps、控制参数与关键性能指标之间的复杂隐含依赖关系，实现冲突预判与成因分析。模型在高度不平衡的合成数据集上进行评估，其中冲突实例占比仅为10%至40%，更贴近真实环境中冲突罕见的场景。实验表明，在不同类别不平衡程度下，模型均达到超过98%的F1得分。
原文摘要 · Abstract (English)
O-RAN hosts many intelligent applications known as eXtended Applications (xApps). xApps are applications that leverage advanced 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 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 actions across different applications can lead to various types of conflicts. Conflict prediction in O-RAN is the proactive analytical process by which potential interactions or behaviors that may lead to conflicts between network applications are identified in advance, before they manifest in the operational system. In our paper, we introduce a novel data-driven Graph Convolutional Network-based method called GRAPH-based Intelligent xApp Conflict Prediction and Analysis (GRAPHICA). It predicts three types of conflicts and pinpoints the root causes. GRAPHICA captures the complex, hidden dependencies among the xApps, controlled parameters, and key performance indicators in O-RAN to predict potential conflicts. Then, it identifies the root causes 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 an F1-score over 98 % for the synthesized datasets with varying levels of class imbalance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。