Network Slice-based Low-Altitude Intelligent Network for Advanced Air Mobility

TL;DR

This work tackles the challenge of efficient, low-latency task offloading for eVTOLs operating in layered low-altitude airspace where onboard computing is limited. It introduces a Network Slice-based Low-Altitude Intelligent Network (LAIN) that combines access pairing, a resource pre-assessment module, and a MADDPG-based slice orchestration to dynamically allocate bandwidth, beam alignment, and computing resources in response to 3D mobility and task variability, with the offloading delay expressed as $t_{i,N_j,q}=t_{i,N_j,q,tran}+t_{i,N_j,q,comp}$. Key contributions include (i) a low-altitude NS slice lifecycle with initialization, scaling, and disposal, (ii) an eVTOL–BS–Slice prioritization (eBAP) mechanism for agile access, (iii) a pre-assessment strategy to minimize resource waste, and (iv) a MADDPG-based orchestration framework that models slices as agents in a multi-agent MDP to optimize $Sat_q$ while managing $C_q$. Simulation results show that MADDPG-based orchestration achieves higher rewards, lower operation/violation costs, and better resource efficiency than benchmark methods across varying eVTOL velocities, demonstrating the practical impact of intelligent network slicing for future AAM systems.

Abstract

Advanced Air Mobility (AAM) is transforming transportation systems by extending them into near-ground airspace, offering innovative solutions to mobility challenges. In this space, electric vertical take-off and landing vehicles (eVTOLs) perform a variety of tasks to improve aviation safety and efficiency, such as collaborative computing and perception. However, eVTOLs face constraints such as compacted shape and restricted onboard computing resources. These limitations necessitate task offloading to nearby high-performance base stations (BSs) for timely processing. Unfortunately, the high mobility of eVTOLs, coupled with their restricted flight airlines and heterogeneous resource management creates significant challenges in dynamic task offloading. To address these issues, this paper introduces a novel network slice-based Low-Altitude Intelligent Network (LAIN) framework for eVTOL tasks. By leveraging advanced network slicing technologies from 5G/6G, the proposed framework dynamically adjusts communication bandwidth, beam alignment, and computing resources to meet fluctuating task demands. Specifically, the framework includes an access pairing method to pre-schedule optimal eVTOL-BS-slice assignments, a pre-assessment algorithm to avoid resource waste, and a deep reinforcement learning-based slice orchestration mechanism to optimize resource allocation and lifecycle management. Simulation results demonstrate that the proposed framework outperforms existing benchmarks in terms of resource allocation efficiency and operational/violation costs across varying eVTOL velocities. This work provides valuable insights into intelligent network slicing for future AAM transportation systems.

Figures (15)

• Figure 1: Intelligent Network Slice Framework.
• Figure 2: Aviation behaviors of eVTOLs in AAM.
• Figure 3: Demonstration of Intelligent Slicing Orchestration.
• Figure 4: Relations of the proposed three algorithms.
• Figure 5: MADDPG-based Resource Allocation Framework.