Environment-Aware Transfer Reinforcement Learning for Sustainable Beam Selection

2025-11-10

AI Summary

To address the high training time and energy consumption of reinforcement learning (RL) models for beam selection in 5G/6G wireless systems across diverse propagation environments, this paper proposes an environment-aware transfer RL framework. Methodologically, it pioneers modeling wireless propagation environments as 3D point clouds and introduces the Chamfer distance to quantify structural similarity between environments, enabling effective cross-scenario knowledge transfer. It further integrates environment-aware feature extraction with a policy transfer mechanism to enhance model reusability. Experimental results demonstrate that the proposed approach maintains beam selection performance—measured by throughput and bit error rate—while reducing training time and computational overhead by 16×. This significantly lowers energy consumption and carbon emissions on edge devices. The framework establishes a scalable, low-power deployment paradigm for green AI–driven intelligent wireless communication systems.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper presents a novel and sustainable approach for improving beam selection in 5G and beyond networks using transfer learning and Reinforcement Learning (RL). Traditional RL-based beam selection models require extensive training time and computational resources, particularly when deployed in diverse environments with varying propagation characteristics posing a major challenge for scalability and energy efficiency. To address this, we propose modeling the environment as a point cloud, where each point represents the locations of gNodeBs (gNBs) and surrounding scatterers. By computing the Chamfer distance between point clouds, structurally similar environments can be efficiently identified, enabling the reuse of pre-trained models through transfer learning. This methodology leads to a 16x reduction in training time and computational overhead, directly contributing to energy efficiency. By minimizing the need for retraining in each new deployment, our approach significantly lowers power consumption and supports the development of green and sustainable Artificial Intelligence (AI) in wireless systems. Furthermore, it accelerates time-to-deployment, reduces carbon emissions associated with training, and enhances the viability of deploying AI-driven communication systems at the edge. Simulation results confirm that our approach maintains high performance while drastically cutting energy costs, demonstrating the potential of transfer learning to enable scalable, adaptive, and environmentally conscious RL-based beam selection strategies in dynamic and diverse propagation environments.

Problem

• Reducing training time and computational overhead for beam selection in 5G networks
• Enabling energy-efficient AI deployment in diverse wireless propagation environments
• Minimizing retraining needs and carbon emissions through transfer learning

Innovation

• Uses point cloud modeling for environment representation
• Employs Chamfer distance to identify similar environments
• Applies transfer learning to reuse pre-trained RL models