DRL Optimization Trajectory Generation via Wireless Network Intent-Guided Diffusion Models for Optimizing Resource Allocation

TL;DR

A wireless network intent (WNI)-guided trajectory generation model based on a generative diffusion model (GDM) that can be generated and fine-tuned in real time to achieve the objective and meet the constraints of target intent networks, significantly reducing state information exposure during wireless communication.

Abstract

With the rapid advancements in wireless communication fields, including low-altitude economies, 6G, and Wi-Fi, the scale of wireless networks continues to expand, accompanied by increasing service quality demands. Traditional deep reinforcement learning (DRL)-based optimization models can improve network performance by solving non-convex optimization problems intelligently. However, they heavily rely on online deployment and often require extensive initial training. Online DRL optimization models typically make accurate decisions based on current channel state distributions. When these distributions change, their generalization capability diminishes, which hinders the responsiveness essential for real-time and high-reliability wireless communication networks. Furthermore, different users have varying quality of service (QoS) requirements across diverse scenarios, and conventional online DRL methods struggle to accommodate this variability. Consequently, exploring flexible and customized AI strategies is critical. We propose a wireless network intent (WNI)-guided trajectory generation model based on a generative diffusion model (GDM). This model can be generated and fine-tuned in real time to achieve the objective and meet the constraints of target intent networks, significantly reducing state information exposure during wireless communication. Moreover, The WNI-guided optimization trajectory generation can be customized to address differentiated QoS requirements, enhancing the overall quality of communication in future intelligent networks. Extensive simulation results demonstrate that our approach achieves greater stability in spectral efficiency variations and outperforms traditional DRL optimization models in dynamic communication systems.

Figures (10)

• Figure 1: Three major applications of UAVs in the context of the low-altitude economy. In emergency communication scenarios, UAVs mainly serve as mobile base stations to provide communication services to users in emergency scenarios. In UAV networking, UAVs can communicate with vehicles and traffic management systems to improve the safety and efficiency of urban transportation, as well as communicate with terminal devices and control and command UAVs to perform tasks. In environmental monitoring, UAVs can collect real-time data to help governments and research institutions with environmental protection and resource management.
• Figure 2: Considered WNI-guided trajectory generation system model for wireless resource allocation optimization.
• Figure 3: An example for WNI-based data model distribution.
• Figure 4: WNI construction of wireless communication scenario.
• Figure 5: The structure of the attention-MLP network for WNI-guided trajectory generation.