Unmanned aerial vehicle routing based on frog-leaping optimization algorithm.

Area of Science:

• Computer Science
• Network Engineering
• Artificial Intelligence

Background:

• Unmanned Aerial Vehicle (UAV) networks face challenges with existing routing algorithms, including high latency, poor route selection, and energy inefficiency.
• Dynamic network topologies in UAVs require adaptive routing strategies for optimal performance.

Purpose of the Study:

• To propose a new routing strategy using the Shuffled Frog Leaping Algorithm (SFLA) to enhance UAV network performance.
• To address limitations of current UAV routing algorithms by improving latency, energy consumption, and route selection.

Main Methods:

• Implemented a two-phase optimization approach incorporating Quality of Service (QoS) for global exploration and local exploitation.
• Utilized SFLA's self-adaptive population-based search mechanism for accelerated convergence and premature standstill elimination.
• Enabled dynamic trajectory adjustments for UAVs to select optimal paths in changing environments.

Main Results:

• Achieved a 3.11% improvement in energy use compared to benchmark methods.
• Reduced latency by 5.14% through optimized routing paths.
• Increased network lifetime by 2.25% by enhancing energy economy.

Conclusions:

• The proposed SFLA-based routing strategy effectively improves UAV network performance by optimizing energy consumption, latency, and throughput.
• This approach is well-suited for real-time applications like aerial surveillance and disaster response demanding high data rates and energy efficiency.