An optimal UAV height localization for maximum target coverage using improved deer hunting optimization algorithm

Unmanned Aerial Vehicles (UAV) is generally employed for several application-oriented tasks and also for aerial cinematography. Though, utilizing UAVs for several applications need the cooperation of various people, which reduces shooting flexibility and needs a higher cost that also increases the cognitive load of UAV operators. Examining the static or mobile targets in the field with flying UAVs is a general task for military and civilian applications. Moreover, the optimal assignment of several monitoring devices is more complicated, wherein several cases; it has been considered to be NP-Hard. It is complicated to implement autonomous, efficient, and fast techniques for supporting pervasive, “anyplace, anytime,” services in such mobile environments, but those are vulnerable to space and time evolution. A novel UAV localization model is introduced in a two-dimensional area using the improved meta-heuristic algorithm. The proposed model for UAV localization encompasses the cost minimization concerning with number of UAVs and their energy consumption (altitude), which is mathematically solved by the proposed optimization algorithm with the Adaptive Fitness-assisted Wind angle-based Deer Hunting Optimization Algorithm (AFW-DHOA). It is a novel variant of meta-heuristic or optimization algorithm called AFW-DHOA for optimal UAV height localization with a single objective function with the target coverage by each UAV. The fundamental objective of optimizing these parameters is to maximize the target coverage for surveillance of all the targets. From the experimental results, the performance of the designed AFW-DHOA is 4%, 3.4%, 3.2%, and 4.5% superior to GWO, DA, HHO, and DHOA, respectively in case 3. Extensive simulations and computational studies are done to assess the behavior of the designed solutions when compared to the conventional models.