面向低空物联网的云-边协同演进模型与通信范式

An edge-cloud collaborative model evolution and communication paradigm in Internet of low-altitude UAV

低空物联网基于空地一体化网络,集成通信和计算功能,在低空场景可以高效地收集、传输和分析数据,为低空经济的发展持续赋能。在这一网络中,无人机(UAV,unmanned aerial vehicle)等空中平台利用机载传感器收集多模态感知数据,并进行基于人工智能(AI,artificial intelligence)的数据处理计算,以支持各种低空场景下的应用,如农业监控和环境建模。执行多模态数据的推理和内容生成任务需要大型AI模型。为了满足这些任务的需求,无人机需要具备强大的计算资源和大量数据支持。这些要求使得高效的推理模型训练和优化变得至关重要。然而,这给现有的低空物联网带来了巨大挑战。为解决这一问题,提出空地一体化云-边模型协同演化架构。在此架构中,无人机作为边缘节点,负责数据采集和小型模型的计算。云服务器通过无线信道与无人机进行信息交互,提供大型模型计算和边缘无人机的模型更新服务,从而实现空地协作。在有限的无线通信带宽限制下,该架构面临着边缘无人机与云服务器之间信息交换调度设计的挑战。为此,提出任务分配、传输资源管理、传输数据量化设计和边缘模型更新的联合策略。该策略通过最大化系统的平均精度(mAP,mean average precision)来提高空地一体化云-边模型协同演化架构的推理准确性。基于边缘模型的平均精度和云模型的平均精度推导出了所提出架构的平均精度闭式下界,并相应地提出了平均精度最大化问题的优化方案。基于视觉分类实验结果的仿真表明,在不同通信带宽和数据量条件下,相比于集中式云模型架构和分布式边缘模型架构,低空物联网在所提出的空地一体化云-边模型协同演化架构下的平均精度均有所提升。

The low-altitude Internet of things(IoT),based on an air-ground integrated network,combines communication and computing functions.This allows it to efficiently collect,transmit,and analyze data in low-altitude scenarios,continu‐ously empowering the development of the low-altitude economy.In this network,aerial platforms such as unmanned aerial vehicle(UAV)uses onboard sensors to gather multimodal perception data and perform AI-based data processing to support various low-altitude applications,such as agricultural monitoring and environmental modeling.Executing multi‐modal data inference and content generation tasks requires large AI models.To meet these demands,UAV needs powerful computing resources and vast data support,making efficient model training and optimization essential.However,this poses significant challenges to the current low-altitude IoT network.To address this,an integrated air-ground edge-cloud collaborative framework was proposed,where UAV function as edge nodes,collecting data and performing small-scale computations.Through wireless channels,cloud servers provide large-scale computations and update models for the UAV,enabling efficient collaborations.Given limited wireless communication bandwidth,the framework faces challenges in scheduling information exchange between the UAV and the cloud servers.To solve this,joint optimizations for task alloca‐tion,transmission resource management,data quantization,and edge model updates were presented,to improve inference accuracy by maximizing the mean average precision(mAP)of the proposed framework.A closed-form lower bound for the mAP based on the performance of the edge and cloud models were derived and a solution to mAP maximization was proposed.Simulations,based on visual classification experiments,show that the mAP of proposed framework under IoL‐oUA consistently outperforms centralized and distributed frameworks across various bandwidth and data conditions.