Collision detection and mitigation based on optimization and Kronecker recurrent neural network in WSN

Abstract

Nowadays, wireless sensor networks (WSNs) have paid huge attention among researchers due to their wide applications. WSNs possess multiple sensor nodes that transmit data to each other by using constrained energy resources. The sensor nodes are highly affected by collision due to the transmission of packets over the network by one or two nodes at the same time. Collision detection is necessary to increase network security and enhance the lifetime of sensor nodes. In most of the previous research, efficiently implementing collision detection algorithms while minimizing resource usage remains a significant challenge. Thus, a hybrid deep learning model deep Kronecker recurrent neural network (DKRNN) is developed in this research. Here, the cluster head is selected using the chronological skill optimization algorithm (CSOA) algorithmic approach by considering multi-objective parameters like energy, distance, delay, and trust. The network-based parameters are then extracted from the network. Later, the collision is detected using the DKRNN approach and the collision is mitigated finally using a packet pre-scheduling model named Dolphin Ant Lion Optimization (Dolphin ALO). Moreover, the detection performance of CSOA+ DKRNN is validated, and it achieved superior performance with a collision detection rate (CDR) of 0.940, packet delivery ratio (PDR) of 0.660, throughput of 0.850Mbps, and energy consumption of 0.110 J.