Enhancing Node Localization Accuracy in Wireless Sensor Networks for Tsunami Early Warning Using Metaheuristic Algorithms
Kottu Santosh Kumar
Asst. Professor,
Information Technology, Vardhaman College of Engineering, Hyderabad, India
santoshkumar1208@gmail.com
Vankaramani Amogh Bhushan
Information Technology, Vardhaman College of Engineering, Hyderabad, India
amoghv952@gmail.com
Kandakurthi Lokesh
Information Technology, Vardhaman College of Engineering, Hyderabad, India
lokeshkandakurthi@gmail.com
Sheshi vardhan
Information Technology,
Vardhaman College of
Engineering, Hyderabad, India
sheshivardhan984@gmail.com
Abstract— Accurate node localization plays a critical role in wireless sensor networks used for tsunami early warning, where timely and dependable information can help reduce the impact of approaching waves. Sensor nodes in such environments are spread across wide and unpredictable ocean regions, which makes localization difficult when only a few anchor nodes are available and when distance measurements are noisy. To improve the precision of range‑based localization in these conditions, this study applies metaheuristic optimization methods to estimate the positions of unknown nodes.
Our approach Three population based algorithms are examined within a single simulation setup: Ant Colony Optimization, Differential Evolution, and the Jellyfish Optimization Algorithm, which serves as the main focus of the work. Each method is tested on the same node deployment and environmental settings to ensure consistency. The aim of the study is to understand how these algorithms search for optimal positions, how stable their localization process is, and how suitable they are for large scale early warning sensor networks placed in marine regions. The work forms a foundation for choosing effective optimization based strategies that can enhance the reliability of localization in critical warning applications.
Keywords— Wireless Sensor Networks, Tsunami Early Warning, Node Localization, Metaheuristic Optimization, Differential Evolution, Jellyfish Optimization Algorithm.
