Optimizing 6G Dense Network Deployment for the Metaverse Using Deep Reinforcement Learning

TL;DR

This work addresses the challenge of deploying Integrated Access and Backhaul (IAB) nodes in dense 6G urban environments to support Metaverse-grade connectivity. It formulates the problem as an MDP and applies DRL with DQN, DDQN, and Dueling DQN architectures, augmented by action elimination to manage large action spaces, aiming to minimize deployed nodes while guaranteeing coverage and backhaul data-rate constraints. Key contributions include defining a detailed state representation (deployment map, rates, and connectivity), a bespoke reward structure that balances coverage and deployment cost, and demonstrating that Dueling DQN achieves faster convergence and lower node counts than standard DQN and DDQN, outperforming a greedy heuristic across multiple urban donor configurations. The results suggest a practical, adaptive planning framework for 6G IAB deployment in the Metaverse era, with potential extensions to ORAN and transfer learning for cross-environment knowledge transfer.

Abstract

As the Metaverse envisions deeply immersive and pervasive connectivity in 6G networks, Integrated Access and Backhaul (IAB) emerges as a critical enabler to meet the demanding requirements of massive and immersive communications. IAB networks offer a scalable solution for expanding broadband coverage in urban environments. However, optimizing IAB node deployment to ensure reliable coverage while minimizing costs remains challenging due to location constraints and the dynamic nature of cities. Existing heuristic methods, such as Greedy Algorithms, have been employed to address these optimization problems. This work presents a novel Deep Reinforcement Learning ( DRL) approach for IAB network planning, tailored to future 6G scenarios that seek to support ultra-high data rates and dense device connectivity required by immersive Metaverse applications. We utilize Deep Q-Network (DQN) with action elimination and integrate DQN, Double Deep Q-Network ( DDQN), and Dueling DQN architectures to effectively manage large state and action spaces. Simulations with various initial donor configurations demonstrate the effectiveness of our DRL approach, with Dueling DQN reducing node count by an average of 12.3% compared to traditional heuristics. The study underscores how advanced DRL techniques can address complex network planning challenges in 6G-enabled Metaverse contexts, providing an efficient and adaptive solution for IAB deployment in diverse urban environments.

Figures (4)

• Figure 1: Deep Q Network with Action Elimination for IAB Network Planning
• Figure 2: Reward vs Episodes Comparison in five-dice distribution donor environment.
• Figure 3: Final network planning for three models in vertical distribution donor environment.
• Figure 4: Deployed Nodes vs Different Initial Donor Environment.