A Modified study on Genetic Algorithm in sensing orientations among the multi-directional Wireless Sensor Networks

Achieving maximum coverage of targets in a sensing network while minimizing the usage of directional sensors presents a formidable challenge. The rising popularity of pivoting directional sensors, capable of scanning signals from multiple angles, offers a promising solution to reduce sensor count while preserving or enhancing coverage quality. To address this challenge, we propose the development of a scheduling strategy that optimally leverages a limited set of directional sensors to cover a wide array of targets. By employing Genetic Algorithms and Average Differential Evolution algorithms (GADE), we successfully devised pragmatic layouts for directional sensors that are nearly optimal, along with identifying optimal routes for an array of detectors, facilitating efficient data collection. Through the implementation of GADE simulations, we conducted a comparative analysis against the traditional greedy approach. Our results reveal that the hybrid GADE approach consistently achieves a superior balance between the expanse of monitored areas and the operational sensors, outperforming greedy algorithms by a margin ranging from 44% to 8%. Notably, the simulation experiments underscore that the hybrid GADE method consistently generates more effective schedules and directions in contrast to the conventional greedy technique.