"Explainable Performance Anomaly Detection and Rectification in 5G-ORAN"

"Owing to the increasing reliance on black-box artificial intelligence (AI) and machine learning techniques for performance anomaly detection and rectification (PADR) in Fifth-Generation (5G) Open Radio Access Networks (O-RAN), concerns have arisen regarding the transparency and trustworthiness of such AI-driven systems. To address this challenge, a transparent 5G O-RAN framework is developed that leverages explainable AI (eXAI) metrics to interpret and validate the PADR process. In this framework, a novel Self-Learning Attention Mechanism (SLAM) integrated with a long short-term memory (LSTM) network is proposed to accurately identify and predict the key features that trigger performance anomalies. The output of the SLAM\u2013LSTM is subsequently utilized as input to a proximal policy optimization (PPO) algorithm for anomaly rectification and error mitigation. Furthermore, a centralized learning paradigm is adopted, wherein network statistics produced by the PPO agent are  polled into a centralized registry and subsequently sampled by extended applications (xAPPs) for model training. Using the sampled data, the xAPP computes eXAI metrics\u2014including confidence, comprehensiveness, entropy, and sensitivity\u2014to identify and explain the features responsible for triggering anomalies. Extensive simulation results demonstrate that the proposed approach consistently outperforms existing baseline methods."