The measurement and monitoring of Quality of service based on security analysis in wireless sensor network using deep learning architecture

Wireless sensor networks comprise of unattended little sensor hubs having low energy and low scope of correspondence. Machine learning has demonstrated its effectiveness in creating proficient cycles to deal with complex issues in different organization perspectives. This exploration propose novel procedure in wireless sensor network routing and security improvement by network observing utilizing profound learning model. The organization routing is done utilizing cluster based scalable hierarchical energy routing protocol (CSHERP) and the organization checking is completed utilizing fuzzy Boltzmann adversarial learning (FBAL). This routing protocol adopts an information driven strategy, with moderate hubs collecting information and sending it to a sink hub. The arrangement gave is valuable to additional investigation of expanded WSN networks. The trial examination is completed as far as energy efficiency, throughput, end-end delay, latency, QoS. The proposed technique attained energy efficiency of 96%, throughput of 91%, end-end delay of 86%, latency of 85%, QoS of 96%.

Automated summary

This research proposes a novel approach for routing and security improvement in wireless sensor networks using deep learning models. The routing is done using a cluster-based scalable hierarchical energy routing protocol (CSHERP), and the monitoring is carried out using fuzzy Boltzmann adversarial learning (FBAL). The proposed method achieves good results in terms of energy efficiency, throughput, end-to-end delay, latency, and QoS.