Resource Optimization for Multi-Unmanned Aerial Vehicle Formation Communication Based on an Improved Deep Q-Network

Area of Science:

• Electrical Engineering
• Computer Science
• Aerospace Engineering

Background:

• Unmanned Aerial Vehicle (UAV) formation technology requires efficient communication under power and spectrum constraints.
• Maintaining high data transmission rates and successful data transfer is crucial for UAV operations.

Purpose of the Study:

• To enhance communication quality in UAV formations by optimizing power and spectrum allocation.
• To maximize transmission rates and the probability of successful data transfer simultaneously.

Main Methods:

• A deep Q-network (DQN) was employed for UAV formation communication.
• Convolutional Block Attention Module (CBAM) and Value Decomposition Network (VDN) algorithms were integrated with DQN.
• Frequency reuse between UAV-to-base station (U2B) and UAV-to-UAV (U2U) links was considered.

Main Results:

• The integrated system demonstrated significant improvements in data transfer rate.
• The probability of successful data transfer was substantially increased.
• CBAM improved training by considering channel and spatial aspects, while VDN addressed partial observability.

Conclusions:

• The proposed method effectively optimizes resource allocation for UAV communication systems.
• Integration of DQN, CBAM, and VDN offers a robust solution for enhancing UAV formation communication quality.
• The findings support the advancement of reliable and efficient UAV communication networks.