Generative AI for Network Planning: From Text Descriptions to Optimal Deployments
Dr. Rui Li, Dr. Xu Chen, Prof. Yong Liang Guan
NTU Singapore
Abstract
We propose a generative AI system that converts natural language descriptions of coverage requirements into optimal network deployment plans. The system uses a fine-tuned vision-language model to understand geographic constraints from satellite imagery and a diffusion model to generate base station placement configurations. Comparison with human network planners shows that the AI system produces plans with 12% better coverage uniformity and 18% lower cost while reducing planning time from weeks to hours.
AI Summary
- Generative AI converting text-based coverage requirements into optimal deployment plans.
- 12% better coverage uniformity and 18% lower cost than human planners.
- Reduces network planning time from weeks to hours.
- Uses vision-language models with satellite imagery for geographic understanding.
Key Findings
- 1Vision-language models effectively interpret geographic constraints from satellite data.
- 2Diffusion-based generation produces diverse high-quality deployment configurations.
- 3The system handles complex constraints including zoning, terrain, and budget limits.
Industry Implications
Dramatically accelerates network rollout planning for 6G deployments.
Democratizes network planning by reducing need for specialized expertise.
Enables rapid scenario analysis for different deployment strategies.
Read the Original Paper
Access the full paper on arXiv for complete methodology, results, and references.
Open on arXivRelated Papers
AI-Driven Energy Optimization in 6G Networks: A Multi-Objective Approach
Poznan University of Technology / Princeton University — 22 citations
AI + Network PapersAI-Native Air Interface Design: End-to-End Learning for 6G Physical Layer
University of Stuttgart — 41 citations
AI + Network PapersDigital Twin Networks: AI-Driven Real-Time Network Simulation for 6G
Oulu University / Ruhr University Bochum — 29 citations