Metaheuristic Optimization of Node Localization in Wireless Sensor Networks for Tsunami Detection

Wireless Sensor Networks (WSNs) frequently face challenges in locating detector bumps directly while conserving limited energy coffers. This work explores how three well- known optimization styles inheritable Algorithm (GA), flyspeck mass Optimization (PSO), and Grey Wolf Optimizer (GWO) can ameliorate localization in WSN surroundings. A simulation model was created to observe how different figures of anchor bumps affect network performance. Several parameters, including energy use, outturn, packet delivery, detention, jitter, continuance, connectivity, content, and delicacy, were recorded for analysis. Among the tested algorithms, the GWO system showed more harmonious localization delicacy and balanced energy operation under varying network sizes. The study highlights that mass- grounded optimization can give a dependable path toward erecting energy-effective and adaptive WSNs suitable for long- term deployment.