Large Vision Model-Enhanced Digital Twin with Deep Reinforcement Learning for User Association and Load Balancing in Dynamic Wireless Networks

2024-10-10

AI Summary

In dynamic wireless networks, real-time variations in user count, spatial distribution, and mobility patterns pose significant challenges for user association and load balancing. Existing deep reinforcement learning (DRL) approaches are constrained by assumptions of fixed user scale and incur prohibitively high trial-and-error costs, hindering practical deployment. Method: This paper proposes a large vision model (LVM)-enhanced digital twin (DT) framework. It introduces Map2Traj—a novel zero-shot diffusion model that synthesizes high-fidelity user trajectories directly from radio maps—and designs a parallel DT training architecture to mitigate environmental non-stationarity and eliminate DRL’s reliance on static user population assumptions. Contribution/Results: Experiments demonstrate that the system achieves training fidelity comparable to real-world networks; the parallel architecture improves edge-user performance by nearly 20%. To our knowledge, this is the first framework enabling scalable, low-overhead intelligent association and load balancing in open, dynamically evolving wireless environments.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Optimization of user association in a densely deployed cellular network is usually challenging and even more complicated due to the dynamic nature of user mobility and fluctuation in user counts. While deep reinforcement learning (DRL) emerges as a promising solution, its application in practice is hindered by high trial-and-error costs in real world and unsatisfactory physical network performance during training. Also, existing DRL-based user association methods are typically applicable to scenarios with a fixed number of users due to convergence and compatibility challenges. To address these limitations, we introduce a large vision model (LVM)-enhanced digital twin (DT) for wireless networks and propose a parallel DT-driven DRL method for user association and load balancing in networks with dynamic user counts, distribution, and mobility patterns. To construct this LVM-enhanced DT for DRL training, we develop a zero-shot generative user mobility model, named Map2Traj, based on the diffusion model. Map2Traj estimates user trajectory patterns and spatial distributions solely from street maps. DRL models undergo training in the DT environment, avoiding direct interactions with physical networks. To enhance the generalization ability of DRL models for dynamic scenarios, a parallel DT framework is further established to alleviate strong correlation and non-stationarity in single-environment training and improve training efficiency. Numerical results show that the developed LVM-enhanced DT achieves closely comparable training efficacy to the real environment, and the proposed parallel DT framework even outperforms the single real-world environment in DRL training with nearly 20% gain in terms of cell-edge user performance.

Problem

• Optimizing user association in dynamic wireless networks with deep reinforcement learning
• Addressing high trial-and-error costs and poor performance during DRL training
• Enhancing generalization for dynamic user counts and mobility patterns

Innovation

• LVM-enhanced digital twin for dynamic wireless networks
• Zero-shot generative user mobility model Map2Traj
• Parallel DT-driven DRL for improved training efficiency