Bio-Inspired Approaches for Energy-Efficient Localization and Clustering in UAV Networks for Monitoring Wildfires in Remote Areas

In dynamic unmanned aerial vehicle (UAV) networks, localization and clustering are fundamental functions for cooperative control. this article, we propose bio-inspired (BIL) (BIC) schemes in UAV networks wildfire detection monitoring. First, develop a hybrid gray wolf optimization (HGWO) method an energy-efficient three-dimensional BIL algorithm based on the HGWO, which reduces errors, avoids flip ambiguity bounded distance measurement achieves high accuracy. BIL, bounding cube is applied to reduce initial search space. Second, BIC HGWO. The utilizes leadership hierarchy improve efficiency. We also analytical model determining optimal number of clusters that provide minimum transmissions. Finally, GWO-based compressive sensing (CS-GWO) transmit data from cluster heads (CHs) base station (BS). proposed CS-GWO constructs efficient routing tree CHs BS, thereby reducing delay Our performance evaluation shows significantly outperform conventional terms various metrics under different scenarios.