Towards Intelligent Low-Altitude Wireless Network Deployment: Differentiable Channel Knowledge Map Construction and Trajectory Design

TL;DR

This paper introduces a differentiable channel knowledge map construction method and a joint optimization framework for trajectory planning in low-altitude wireless networks, enhancing accuracy and throughput.

Contribution

It proposes a novel location-oriented CKM construction using neural networks and a joint optimization method for multi-UAV systems, improving deployment efficiency and communication performance.

Findings

The differentiable CKM achieves higher accuracy than environmental feature-free methods.

The proposed CKM-JPBTO significantly increases minimum throughput compared to traditional models.

The framework enables location-aware differentiability for better UAV deployment.

Abstract

Channel knowledge map (CKM) has emerged as a promising technique to leverage prior propagation knowledge in low-altitude wireless networks (LAWNs), yet state-of-the-art grid-based CKM construction methods struggle to support efficient LAWN deployment due to their lack of differentiability with respect to continuous locations of unmanned aerial vehicles (UAVs). To overcome this limitation, we propose a differentiable CKM-triggered trajectory optimization framework for LAWNs. Firstly, we propose a location-oriented CKM construction method that directly maps continuous spatial coordinates to channel gain. In particular, a shared convolutional neural network (CNN) is employed to encode high-level environmental features from conditional inputs. These features are then sampled based on location information to form a fused regressor-conditional multilayer perceptron (c-MLP) or conditional Kolmogorov-Arnold network (cKAN)-for channel gain prediction. We further propose a joint power, bandwidth, and trajectory optimization (JPBTO) method for multi-UAV systems, with the constructed differentiable CKM employed to evaluate the communication performance. The formulated non-convex problem is solved via alternating optimization and successive convex approximation. Numerical results show that the proposed framework enables location-aware differentiability of the CKM, while achieving higher accuracy than the methods without environmental features. Furthermore, the proposed CKM-JPBTO achieves a significantly higher minimum throughput than the conventional statistical channel model-based JPBTO.