# Spatial Deep Learning for Site-Specific Movement Optimization of Aerial Base Stations

arXiv: https://arxiv.org/abs/2312.10490 · HTML: https://mlsanity.com/paper/2312.10490/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 16 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Adam Can Converge Without Any Modification On Update Rules](https://mlsanity.com/paper/2208.09632/) (2022)
- [Convolutional Neural Networks at Constrained Time Cost](https://mlsanity.com/paper/1412.1710/) (2014)
- [Convergence rates for the stochastic gradient descent method for non-convex objective functions](https://mlsanity.com/paper/1904.01517/) (2019)
- [Spatial Deep Learning for Wireless Scheduling](https://mlsanity.com/paper/1808.01486/) (2018)
- [Accessing From The Sky: A Tutorial on UAV Communications for 5G and Beyond](https://mlsanity.com/paper/1903.05289/) (2019)
- [Simultaneous Navigation and Radio Mapping for Cellular-Connected UAV with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.07574/) (2020)
- [Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-assisted Mobile Edge Computing](https://mlsanity.com/paper/1911.03887/) (2019)
- [Trajectory Design and Power Control for Multi-UAV Assisted Wireless Networks: A Machine Learning Approach](https://mlsanity.com/paper/1812.07665/) (2018)
- [Reinforcement Learning in Multiple-UAV Networks: Deployment and Movement Design](https://mlsanity.com/paper/1904.05242/) (2019)
- [Learning Site-Specific Probing Beams for Fast mmWave Beam Alignment](https://mlsanity.com/paper/2107.13121/) (2021)
- [Network-Connected UAV: 3D System Modeling and Coverage Performance Analysis](https://mlsanity.com/paper/1901.07887/) (2019)
- [Placement Optimization of Aerial Base Stations with Deep Reinforcement Learning](https://mlsanity.com/paper/1911.08111/) (2019)
- [Aerial Base Station Placement Leveraging Radio Tomographic Maps](https://mlsanity.com/paper/2109.07372/) (2021)
- [Radio Map Based Path Planning for Cellular-Connected UAV](https://mlsanity.com/paper/1905.05046/) (2019)

## Built on by (most cited first, 1 of 1)

- [Intelligent Base Station Deployment in Urban Wireless Networks: A Geographic Data-Informed Digital Twin Approach](https://mlsanity.com/paper/2608.14599/) (2026)

## Abstract (arXiv)

Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations (ABSs) to provide wireless connectivity for ground users (GUs) in various emergency scenarios. However, it is a NP-hard problem with exponential complexity in M and N, in order to maximize the coverage rate of M GUs by jointly placing N ABSs with limited coverage range. The problem is further complicated when the coverage range becomes irregular due to site-specific blockages (e.g., buildings) on the air-ground channel, and/or when the GUs are moving. To address the above challenges, we study a multi-ABS movement optimization problem to maximize the average coverage rate of mobile GUs in a site-specific environment. The Spatial Deep Learning with Multi-dimensional Archive of Phenotypic Elites (SDL-ME) algorithm is proposed to tackle this challenging problem by 1) partitioning the complicated ABS movement problem into ABS placement sub-problems each spanning finite time horizon; 2) using an encoder-decoder deep neural network (DNN) as the emulator to capture the spatial correlation of ABSs/GUs and thereby reducing the cost of interaction with the actual environment; 3) employing the emulator to speed up a quality-diversity search for the optimal placement solution; and 4) proposing a planning-exploration-serving scheme for multi-ABS movement coordination. Numerical results demonstrate that the proposed approach significantly outperforms the benchmark Deep Reinforcement Learning (DRL)-based method and other two baselines in terms of average coverage rate, training time and/or sample efficiency. Moreover, with one-time training, our proposed method can be applied in scenarios where the number of ABSs/GUs dynamically changes on site and/or with different/varying GU speeds, which is thus more robust and flexible compared with conventional DRL-based methods.