Quantum-Ai Hybrid Architecture for Intelligent Fault Detection and Auto-Remediation in Distributed Cloud Systems

The growing use of distributed cloud-edge computing architectures for high-availability and latency-sensitive applications has created a new class of fault management and system reliability issues. Modern cloud-edge systems are dynamic, varied, and decentralised, making traditional fault detection techniques-which frequently rely on rule-based or thresholddriven mechanisms-unable to keep up. In order to detect, locate, and forecast defects in real time across cloud and edge layers, this study presents a fault detection framework driven by Quantum AI (QAI) that combines deep learning. Hardware-in-the-loop, or HIL, testing is a crucial technique for evaluating the reliability and security of ASS (automotive software systems). However, the traditional data evaluation methods utilised for issue identification and classification using human specialists are unfeasible because of the complicated and massive volume of data generated by the platform of HIL throughout the process of testing. Employing hybrid DL approaches, this study suggests a novel intelligent failure detection and classification (FDC) methodology that may be used during the integration testing phase or the V-cycle phase of development. Moreover, the model structure was developed using a combination of Recurrent Neural Networks (RNN) and Generative Adversarial Networks (GAN). The results have shown that the proposed method outperformed previous stand-alone QDL techniques in detection and classification. Specifically, the proposed structure showed overall accuracies of 99.2% precision, 99.9 % recall, and 99.2% F1-score regarding detection. The experimental results show superiority in average classification accuracy with a rate of 99.1 % with unseen test data.