面向低空物联网的云-边协同演进模型与通信范式

于馨博; 张舒航; 张泓亮

doi:10.11959/j.issn.2096-3750.2024.00425

您当前的位置：

首页 >

文章列表页 >

面向低空物联网的云-边协同演进模型与通信范式

理论与技术 | 更新时间：2025-03-13

- 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
- 物联网学报 2024年8卷第3期页码：76-90
- 作者机构：
  
  1.北京大学信息科学技术学院，北京 100871
  2.鹏城实验室，广东深圳 518055
  3.北京大学电子学院，北京 100871
- 作者简介：
  
  [ "于馨博（2005‒ ），男，北京大学信息科学技术学院在读，主要研究方向为无线通信。" ]
  [ "张舒航（1993‒ ），男，鹏城实验室助理研究员、博士生导师，主要研究方向为无线网络、人工智能、空地一体化网络等。" ]
  [ "张泓亮（1992‒ ），男，北京大学电子学院助理教授、博士生导师，主要研究方向为智能超表面、空地一体化网络等。" ]
- 基金信息：
  
  国家自然科学基金项目(62401302;62371011);北京市自然科学基金项目(L243002)
- DOI：10.11959/j.issn.2096-3750.2024.00425
  中图分类号： TN92
- 收稿日期：2024-08-19，
  
  修回日期：2024-09-10，
  
  纸质出版日期：2024-09-10
- 稿件说明：
移动端阅览
于馨博,张舒航,张泓亮.面向低空物联网的云-边协同演进模型与通信范式[J].物联网学报,2024,08(03):76-90.

YU Xinbo,ZHANG Shuhang,ZHANG Hongliang.An edge-cloud collaborative model evolution and communication paradigm in Internet of low-altitude UAV[J].Chinese Journal on Internet of Things,2024,08(03):76-90.
于馨博,张舒航,张泓亮.面向低空物联网的云-边协同演进模型与通信范式[J].物联网学报,2024,08(03):76-90. DOI： 10.11959/j.issn.2096-3750.2024.00425.

YU Xinbo,ZHANG Shuhang,ZHANG Hongliang.An edge-cloud collaborative model evolution and communication paradigm in Internet of low-altitude UAV[J].Chinese Journal on Internet of Things,2024,08(03):76-90. DOI： 10.11959/j.issn.2096-3750.2024.00425.

摘要

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。

Abstract

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

continuously 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 multimodal 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 allocation

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 IoLoUA consistently outperforms centralized and distributed frameworks across various bandwidth and data conditions.

关键词

Keywords

references

WARGO C A , CHURCH G C , GLANEUESKI J , et al . Unmanned Aircraft Systems (UAS) research and future analysis [C ] // Proceedings of the 2014 IEEE Aerospace Conference . Piscataway : IEEE Press , 2014 : 1 - 16 .

HOSSEIN MOTLAGH N , TALEB T , AROUK O . Low-altitude unmanned aerial vehicles-based Internet of Things services: comprehensive survey and future perspectives [J ] . IEEE Internet of Things Journal , 2016 , 3 ( 6 ): 899 - 922 .

LIU Z S , WANG L Y , LI B . Quality assessment of ecological environment based on google earth engine: a case study of the Zhoushan Islands [J ] . Frontiers in Ecology and Evolution , 2022 , 10 : 918756 .

孟婵媛 , 熊轲 , 高博 , 等 . 面向6G的生成对抗网络研究进展综述 [J ] . 物联网学报 , 2024 , 8 ( 1 ): 1 - 16 .

MENG C Y , XIONG K , GAO B , et al . Survey on the research progress of generative adversarial networks for 6G [J ] . Chinese Journal on Internet of Things , 2024 , 8 ( 1 ): 1 - 16 .

SHEN Y F , SHAO J W , ZHANG X J , et al . Large language models empowered autonomous edge AI for connected intelligence [J ] . IEEE Communications Magazine , 2024 , 62 ( 10 ): 140 - 146 .

栾宁 , 熊轲 , 张煜 , 等 . 6G: 典型应用、关键技术与面临挑战 [J ] . 物联网学报 , 2022 , 6 ( 1 ): 29 - 43 .

LUAN N , XIONG K , ZHANG Y , et al . 6G: typical applications, key technologies and challenges [J ] . Chinese Journal on Internet of Things , 2022 , 6 ( 1 ): 29 - 43 .

PAL O K , SHOVON M S H , MRIDHA M F , et al . A comprehensive review of AI-enabled unmanned aerial vehicle: trends, vision, and challenges [J ] . arXiv preprint arXiv: 2310. 16360 , 2023 .

BOTH C B , BORGES J , GONÇALVES L , et al . System intelligence for UAV-based mission critical with challenging 5G/B5G connectivity [J ] . arXiv preprint arXiv: 2102.02318 , 2021 .

YANG B , CAO X L , YUEN C , et al . Offloading optimization in edge computing for deep-learning-enabled target tracking by Internet of UAVs [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 12 ): 9878 - 9893 .

LIU Z , ZHAN C , CUI Y , et al . Robust edge computing in UAV systems via scalable computing and cooperative computing [J ] . IEEE Wireless Communications , 2021 , 28 ( 5 ): 36 - 42 .

KOUBAA A , AMMAR A , ABDELKADER M , et al . AERO: AI-enabled remote sensing observation with onboard edge computing in UAVs [J ] . Remote Sensing , 2023 , 15 ( 7 ): 1873 .

VARGHESE R , SAMBATH M . YOLOv8: a novel object detection algorithm with enhanced performance and robustness [C ] // Proceedings of the 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS) . Piscataway : IEEE Press , 2024 : 1 - 6 .

AKKUS C , CHU L , DJAKOVIC V , et al . Multimodal deep learning [J ] . arXiv preprint arXiv: 2301.04856 , 2024 .

LIU Y , ZHANG K , LI Y , et al . Sora: A review on background, technology, limitations, and opportunities of large vision models [J ] . arXiv preprint arXiv: 2402.17177 , 2024 .

Gemini Team Google . Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context [J ] . arXiv preprint arXiv: 2403.05530 , 2024 .

YUAN Y Z , GAO S C , ZHANG Z T , et al . Edge-cloud collaborative UAV object detection: edge-embedded lightweight algorithm design and task offloading using fuzzy neural network [J ] . IEEE Transactions on Cloud Computing , 2024 , 12 ( 1 ): 306 - 318 .

NARAYANA TINNALURI V S , VYANKATESH GHAMANDE M , SINGH S , et al . Edge-cloud computing systems for unmanned aerial vehicles capable of optimal work offloading with delay [C ] // Proceedings of the 2023 Second International Conference on Electronics and Renewable Systems (ICEARS) . Piscataway : IEEE Press , 2023 : 844 - 849 .

XU M R , NIYATO D , ZHANG H L , et al . Sparks of generative pretrained transformers in edge intelligence for the metaverse: caching and inference for mobile artificial intelligence-generated content services [J ] . IEEE Vehicular Technology Magazine , 2023 , 18 ( 4 ): 35 - 44 .

LI B , FEI Z S , ZHANG Y . UAV communications for 5G and beyond: recent advances and future trends [J ] . IEEE Internet of Things Journal , 2019 , 6 ( 2 ): 2241 - 2263 .

YANG B , CAO X L , LI X F , et al . Lessons learned from accident of autonomous vehicle testing: an edge learning-aided offloading framework [J ] . IEEE Wireless Communications Letters , 2020 , 9 ( 8 ): 1182 - 1186 .

ZHANG S H , ZHANG H L , SONG L Y . Beyond D2D: full dimension UAV-to-everything communications in 6G [J ] . IEEE Transactions on Vehicular Technology , 2020 , 69 ( 6 ): 6592 - 6602 .

ZHANG S H , LIU Q Y , CHEN K , et al . Large models for aerial edges: an edge-cloud model evolution and communication paradigm [J ] . IEEE Journal on Selected Areas in Communications ， 2024 : 1 - 16 .

LI J , LI B , LU Y . Deep contextual video compression [J ] . Advances in Neural Information Processing Systems , 2021 , 34 : 18114 - 18125 .

CHEN B , BAKHSHI A , BATISTA G , et al . Update compression for deep neural networks on the edge [C ] // Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway : IEEE Press , 2022 : 3075 - 3085 .

YANG G , TANG Y , WU Z J , et al . DMKD: improving feature-based knowledge distillation for object detection via dual masking augmentation [C ] // Proceedings of the ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE Press , 2024 : 3330 - 3334 .

MOYA OSORIO D P , AHMAD I , SÁNCHEZ J D V , et al . Towards 6G-enabled Internet of vehicles: security and privacy [J ] . IEEE Open Journal of the Communications Society , 2022 , 3 : 82 - 105 .

REAL E , MOORE S , SELLA A , et al . Large scale evolution of image classifiers [C ] // Proceedings of the International Conference on Machine Learning , Sydney, Australia : Association for Computing Machinery: 2017 : 2902 - 2911 .

YANG W H , HUANG H F , HU Y Y , et al . Video coding for machines: compact visual representation compression for intelligent collaborative analytics [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 , 46 ( 7 ): 5174 - 5191 .

BALLÉ J , MINNEN D , SINGH S , et al . Variational image compression with a scale hyperprior [J ] . arXiv preprint arXiv:1802. 01436 , 2018 .

LI W G , SUN W Y , ZHAO Y D , et al . Deep image compression with residual learning [J ] . Applied Sciences , 2020 , 10 ( 11 ): 4023 .

CHENG Z X , SUN H M , TAKEUCHI M , et al . Learned image compression with discretized Gaussian mixture likelihoods and attention modules [C ] // Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2020 : 7936 - 7945 .

DU D ， ZHU P , WEN Let al . VisDrone-DET2019: The vision meets drone object detection in image challenge results [C ] // 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) . Seoul, Korea : IEEE Press: 2019 : 213 - 226 .

CHEN Z Q , DUAN L Y , WANG S Q , et al . Toward knowledge as a service over networks: a deep learning model communication paradigm [J ] . IEEE Journal on Selected Areas in Communications , 2019 , 37 ( 6 ): 1349 - 1363 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

空地协同通信定位一体化无人机应急部署优化

基于WPT的去蜂窝mMIMO系统中无人机轨迹与充放电联合优化方法

面向3GPP ISAC标准化的低空无人机场景路径损耗测量与建模

车联网边缘智能：概念、架构、问题、实施和展望

基于DNN卷积核分割的边缘协作推理性能分析