AutoBS: Autonomous Base Station Deployment Framework with Reinforcement Learning and Digital Twin Network

2025-02-27

AI Summary

To address the challenge of base station (BS) deployment in dynamic 6G networks—requiring simultaneous optimization of coverage, capacity, real-time responsiveness, and computational efficiency—this paper proposes an autonomous deployment framework integrating digital twin (DT) technology with lightweight reinforcement learning (RL). Methodologically, we pioneer the tight coupling of the PMNet path-loss model into the Proximal Policy Optimization (PPO) training loop, preserving prediction accuracy while drastically accelerating decision latency; DT-enabled simulation further supports closed-loop policy refinement. Compared to exhaustive search, our approach achieves 95% and 90% of optimal single- and multi-BS capacity, respectively, while reducing inference latency from hours to milliseconds—enabling large-scale online deployment. The core contributions are: (i) the first tight integration of physics-informed path-loss modeling with PPO-based RL, and (ii) a low-overhead, ultra-low-latency BS deployment paradigm tailored for 6G networks.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This paper introduces AutoBS, a reinforcement learning (RL)-based framework for optimal base station (BS) deployment in 6G networks. AutoBS leverages the Proximal Policy Optimization (PPO) algorithm and fast, site-specific pathloss predictions from PMNet to efficiently learn deployment strategies that balance coverage and capacity. Numerical results demonstrate that AutoBS achieves 95% for a single BS, and 90% for multiple BSs, of the capacity provided by exhaustive search methods while reducing inference time from hours to milliseconds, making it highly suitable for real-time applications. AutoBS offers a scalable and automated solution for large-scale 6G networks, addressing the challenges of dynamic environments with minimal computational overhead.

Problem

• Optimal base station deployment in 6G networks
• Balancing coverage and capacity efficiently
• Reducing inference time for real-time applications

Innovation

• Reinforcement Learning for BS deployment
• Proximal Policy Optimization algorithm
• Digital Twin Network integration