Base Station Deployment under EMF constrain by Deep Reinforcement learning
Mohammed Mallik, Guillaume Villemaud
TL;DR
The work tackles EMF-constrained base station deployment in ultra-dense 5G/6G environments by introducing NPE-GAN, a conditional GAN that rapidly predicts site-specific $RSS$ and RF-EMF exposure from network topology. These predictions power GAN-DQN, a deep Q-network framework that performs sequential BS placement under coverage goals while respecting exposure limits, yielding real-time deployment decisions. Empirical results show NPE-GAN achieves RMSE around $7.3$ dB for RSS, MAE around $4$ dB, and SSIM ≈ $0.87$, outperforming prior DL baselines; GAN-DQN approaches brute-force optimality with substantial speedups (seconds vs hours) and maintains EMF safety. The combined NPE-GAN and GAN-DQN system acts as a digital twin for fast, EMF-aware network optimization, scalable to dynamic scenarios and extensible to other deployment tasks.
Abstract
As 5G networks rapidly expand and 6G technologies emerge, characterized by dense deployments, millimeter-wave communications, and dynamic beamforming, the need for scalable simulation tools becomes increasingly critical. These tools must support efficient evaluation of key performance metrics such as coverage and radio-frequency electromagnetic field (RF-EMF) exposure, inform network design decisions, and ensure compliance with safety regulations. Moreover, base station (BS) placement is a crucial task in the network design, where satisfying coverage requirements is essential. To address these, based on our previous work, we first propose a conditional generative adversarial network (cGAN) that predicts location specific received signal strength (RSS), and EMF exposure simultaneously from the network topology, as images. As a network designing application, we propose a Deep Q Network (DQN) framework, using the trained cGAN, for optimal base station (BS) deployment in the network. Compared to conventional ray tracing simulations, the proposed cGAN reduces inference and deployment time from several hours to seconds. Unlike a standalone cGAN, which provides static performance maps, the proposed GAN-DQN framework enables sequential decision making under coverage and exposure constraints, learning effective deployment strategies that directly solve the BS placement problem. Thus making it well suited for real time design and adaptation in dynamic scenarios in order to satisfy pre defined network specific heterogeneous performance goals.
