Graph Attention Preemptive Traffic Aware Sparse Neural Autoencoder-Based Secured Data Transmission in Cloud Computing

With the development of several services, traffic signal preemption is carried out for emergency tasks. For performing workflow intent, cloud systems offer unlimited virtual resources for designing the traffic signal preemption in emergency tasks. While some efforts have been made to implement traffic signal preemption for emergencies, more attention must be given to improving response times. A hybrid method called Graph Attention Preemptive Traffic-aware Sparse Neural Autoencoder (GAPT-SNA) is proposed for secured data transmission in the cloud platform. The GAPT-SNA method is split into the preemptive traffic-aware relocation model and secure data transmission in the CC environment. Initially, the Graph Attention Recurrent Preemptive Relocation model is designed with an Enhanced Healthcare Monitoring System (EHMS) testbed dataset. The decision is forwarded to the discriminator network for scheduling. The Sparse Gradient Neural Auto-encoder is designed to ensure secure data transmission by utilizing preemptive traffic-aware relocated results. The sparse gradient neural function ensures sparsity on prediction tasks for boosting data integrity. Java Software was used to simulate and validate performance metrics, including response time, Throughput, data confidentiality, and data integrity, using the EHMS testbed dataset.