HOA-OBL: hybrid opposition-based hippopotamus optimization framework for efficient UAV task allocation.

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Operations Research

Background:

• Unmanned Aerial Vehicles (UAVs) are increasingly deployed in critical applications like disaster recovery and surveillance.
• Existing task allocation frameworks for UAVs often exhibit suboptimal resource utilization and lack adaptability in dynamic environments.
• Addressing these limitations is crucial for enhancing the efficiency and scalability of UAV operations.

Purpose of the Study:

• To develop an efficient UAV task allocation optimization framework.
• To improve upon the limitations of conventional task-allocation methods, specifically the tendency towards local optima in population-based algorithms.
• To enhance resource utilization and adaptability in dynamic operational settings.

Main Methods:

• A novel hybrid algorithm, Hippopotamus Optimization Algorithm with Opposition-Based Learning (HOA-OBL), was developed for UAV task allocation.
• Opposition-Based Learning (OBL) was integrated with the Hippopotamus Optimization Algorithm (HOA) to improve exploration and prevent premature convergence.
• Simulations were conducted in dynamic environments involving 20 UAVs and 100 tasks to evaluate the framework's performance.

Main Results:

• The proposed HOA-OBL framework demonstrated significant improvements compared to existing methods (HOA, GA, PSO, GWO).
• Energy consumption was reduced by approximately 17% to 33%.
• Load balancing performance enhancements ranged from 33% to 50%.

Conclusions:

• The HOA-OBL framework offers a more balanced and scalable solution for UAV task assignment.
• The proposed approach enhances efficiency and consistency in real-world UAV missions.
• This optimization strategy effectively addresses the challenges of dynamic environments and resource allocation in UAV swarms.