C. M. Nalayini

Abstract Edge-assisted cognitive radio networks require efficient scheduling mechanisms to jointly manage opportunistic spectrum access, task offloading, energy consumption, and latency constraints. Existing multi-agent scheduling approaches often rely on fixed penalty terms or average queue-based constraints, which may not effectively control service-level violations under uncertain spectrum availability and dynamic edge-resource contention.

Intrusion Detection System (IDS) is considered as a security tool for continuously monitoring the network traffic to detect dangerous activity and suspicious activity. Here, the deep features are extracted with the support of Spatial Attention Based Convolutional Autoencoder (SAB-CA). The feature extraction phase helps to boost the reliability of IDS by focusing on relevant data, which significantly reduces the time required for training.