Enhanced Localization Model in Wireless Sensor Network Using Self Adaptive-Barnacles Mating Optimization

Wireless sensor network (WSN) has more demand nowadays because of their diverse applications. In WSN, sensor node localization has become an interesting topic. The nodes are placed randomly to explore, and the determination of accurate nodes' positions is required. Fixed cost and energy are the main challenges with the sensor, as the location of all nodes that are not maintained. The main aim of this research work is to plan for a new localization method in WSN using a new meta-heuristic concept. The proposed model focuses on two phases: (a) localizing the target nodes and (b) localizing the rest nodes. The optimal selection of target nodes is initially determined by the proposed meta-heuristic model by considering the displacement among the nodes. For performing the optimal localization of rest nodes regarding anchor nodes, the weight of each anchor node is determined, which is done by recurrent neural network (RNN). Furthermore, an objective function concerning the distance and the weight is derived for localizing the rest nodes. The new algorithm called Self Adaptive-Barnacles Mating Optimization (SA-BMO) is used for performing the optimal node localization. The desired outcome proves the developed method is attaining an increase in efficiency.