Multi-UAV path planning considering multiple energy consumptions via an improved bee foraging learning particle swarm...

Area of Science:

• Robotics and Automation
• Wireless Sensor Networks
• Optimization Algorithms

Background:

• Unmanned aerial vehicles (UAVs) are increasingly used in wireless sensor networks for data collection.
• Accurate energy consumption modeling is crucial for multi-UAV path planning.
• Existing models often overlook dynamic flight states like acceleration and turning.

Purpose of the Study:

• To develop a multi-UAV path planning model (MUAVPP-MEC) that accounts for diverse energy consumption factors.
• To minimize total UAV flight time under energy constraints.
• To propose an efficient optimization algorithm for solving the MUAVPP-MEC problem.

Main Methods:

• Developed the Multi-UAV Path Planning Considering Multiple Energy Consumptions (MUAVPP-MEC) model.
• Proposed an improved Bee Foraging Learning Particle Swarm Optimization (IBFLPSO) algorithm.
• Integrated bee-foraging concepts with particle swarm optimization and employed an energy-constrained 2-opt local search.

Main Results:

• The MUAVPP-MEC model accurately reflects increased time and energy consumption with more data collection points.
• The IBFLPSO algorithm demonstrated superior performance compared to traditional PSO, PSO-2OPT, GA, and BFLPSO.
• IBFLPSO achieved significantly better optimal solutions, outperforming others by up to 54.64%.

Conclusions:

• The proposed MUAVPP-MEC model and IBFLPSO algorithm are effective for energy-aware multi-UAV path planning.
• IBFLPSO offers a robust and efficient solution for complex optimization problems in UAV networks.
• The findings highlight the importance of comprehensive energy modeling for optimizing UAV operations.