A Novel Routing Equipment Fault Diagnosis Scheme Based On Machine Learning In Short Distance Communication Scenario

In the short distance communication scenario, the stable and efficient operation of routing equipment is very important, but there is no method to achieve high fault identification accuracy. In this paper, a fault diagnosis scheme for routing equipment based on machine learning in short distance communication scenarios is proposed. A generative adversarial network based on quantum state optimization is adopted for data augmentation, a neural network based on locally sensitive honeypot optimization algorithm is adopted to effectively identify and extract key features, and an improved autoencoder is adopted for feature dimension reduction. The classification performance is optimized by support vector machine based on covariate matrix. The experimental results show that this scheme can achieve a high accuracy of fault identification of routing equipment, and has greater deployment and promotion value.