Automatic Network Planning with Digital Radio Twin

2025-09-15

AI Summary

Addressing challenges in cellular base station deployment—including joint coverage-capacity optimization difficulty, large simulation-to-reality gaps, and poor generalizability across scenarios—this paper proposes AutoPlan, a digital radio-frequency (RF) twin–based automated network planning framework. AutoPlan dynamically calibrates propagation models by fusing crowdsourced drive-test measurements with fine-grained building material parameters; it then employs Bayesian optimization to efficiently search the optimal base station configuration (e.g., location, mechanical/electrical downtilt, transmit power), avoiding computationally prohibitive exhaustive search. Evaluated across diverse real-world urban environments, AutoPlan achieves performance comparable to exhaustive search while reducing computation time by over 98%. The core contributions are: (i) a learnable and updatable digital RF twin that bridges simulation and reality, and (ii) a data-driven closed-loop optimization paradigm that enhances planning accuracy, efficiency, and cross-scenario adaptability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Motion and Path Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Network planning seeks to determine base station parameters that maximize coverage and capacity in cellular networks. However, achieving optimal planning remains challenging due to the diversity of deployment scenarios and the significant simulation-to-reality discrepancy. In this paper, we propose emph{AutoPlan}, a new automatic network planning framework by leveraging digital radio twin (DRT) techniques. We derive the DRT by finetuning the parameters of building materials to reduce the sim-to-real discrepancy based on crowdsource real-world user data. Leveraging the DRT, we design a Bayesian optimization based algorithm to optimize the deployment parameters of base stations efficiently. Using the field measurement from Husker-Net, we extensively evaluate emph{AutoPlan} under various deployment scenarios, in terms of both coverage and capacity. The evaluation results show that emph{AutoPlan} flexibly adapts to different scenarios and achieves performance comparable to exhaustive search, while requiring less than 2% of its computation time.

Problem

• Optimizing base station parameters for cellular network coverage
• Reducing simulation-to-reality discrepancy in network planning
• Efficiently determining deployment scenarios using digital radio twin

Innovation

• Digital radio twin finetuning with crowdsourced data
• Bayesian optimization for base station parameters
• Reduced computation time with exhaustive search performance