Robust Base Station Placement in Agricultural IoT via Bayesian Optimization

2026-07-01

AI Summary

This study addresses the challenge of maintaining reliable communication coverage throughout the entire crop growth cycle in agricultural IoT, where dynamic vegetation changes significantly alter the radio propagation environment. The authors formulate base station deployment as a robust optimization problem aimed at maximizing the worst-season coverage ratio. They introduce Gaussian process Bayesian optimization—applied for the first time to agricultural 5G network planning—to efficiently handle channel uncertainty induced by vegetation. By integrating ray-tracing simulations with a multi-crop zoning model at the 3.5 GHz band, the proposed approach achieves a worst-season coverage ratio of 72.8% using only three base stations and fewer than 50 ray-tracing evaluations over a 1 km² multi-crop farm, outperforming existing methods by at least 4.6 percentage points.

Abstract

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 $K$-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 $1\,\text{km}^2$ multi-crop farm with three distinct crop zones at $3.5\,\text{GHz}$, the proposed scheme achieves $72.8\%$ worst-case coverage with $K{=}3$ BSs in fewer than fifty ray-tracing evaluations, outperforming budget-matched state-of-the-art approaches by at least $4.6\,\text{pp}$ across all four seasonal stages.

Problem

• Base Station Placement
• Agricultural IoT
• Seasonal Coverage
• Propagation Environment
• Robust Connectivity

Innovation

• Bayesian Optimization
• Robust Base Station Placement
• Maximin Coverage
• Ray-Tracing Surrogate
• Agricultural IoT