中文

Robust Base Station Placement in Agricultural IoT via Bayesian Optimization

网络与互联网体系结构 2026-07-01 v1 信号处理

摘要

Precision-agriculture networks based on private 5G NR should ensure reliable connectivity for IoT sensor nodes throughout the crop growing season, yet the propagation environment changes dramatically as vegetation grows and matures. We formulate KK-base-station~(BS) placement as a \textit{maximin seasonal coverage} problem that maximizes the worst-case coverage fraction across all crop growth stages. Since each objective evaluation requires expensive ray-tracing simulations across all stages, we adopt a Gaussian-process Bayesian optimization~(GPBO) framework that builds a probabilistic surrogate of the robust objective using ray tracing. On a 1km21\,\text{km}^2 multi-crop farm with three distinct crop zones at 3.5GHz3.5\,\text{GHz}, the proposed scheme achieves 72.8%72.8\% worst-case coverage with K=3K{=}3 BSs in fewer than fifty ray-tracing evaluations, outperforming budget-matched state-of-the-art approaches by at least 4.6pp4.6\,\text{pp} across all four seasonal stages.

引用

@article{arxiv.2607.00549,
  title  = {Robust Base Station Placement in Agricultural IoT via Bayesian Optimization},
  author = {Gourav Prateek Sharma and Durgesh Singh and James Gross},
  journal= {arXiv preprint arXiv:2607.00549},
  year   = {2026}
}