Opposition based learning-lyrebird optimisation approach for optimal path planning in UAV-WSN environment

The rapid advancement in wireless sensor networks (WSNs) has prompted the need for efficient data collection, particularly using unmanned aerial vehicles (UAVs). However, selecting an optimal path for UAVs to collect data from sensor nodes while avoiding obstacles is a significant challenge. Thus, this research introduces a novel meta-heuristic optimisation approach for UAV path planning to address these challenges. Initially, a system model is designed that includes a UAV and a set of sensor nodes randomly deployed within a specified area. The proposed method focuses on UAV path planning using a novel opposition-based learning-lyrebird optimisation approach (OBL-LOA). The proposed approach offers a significant improvement in efficiency and performance for UAV path planning in terms of average flight time (s), network life time (rounds), task completion time, average path length (m), average energy consumption (J), and average data collection efficiency (%) and accomplished 27.5801, 2605.63, 1.03425, 33.716, 0.025, and 0.945 respectively.