《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (10): 3259-3269.DOI: 10.11772/j.issn.1001-9081.2024101431

• 先进计算 • 上一篇    

无人机群辅助的移动感知自适应并行计算任务卸载系统MATOS

孙鉴1,2, 张伟1, 马宝全1(), 吴隹伟1, 杨晓焕1, 武涛1   

  1. 1.北方民族大学 计算机科学与工程学院,银川 750021
    2.图像图形智能处理国家民委重点实验室(北方民族大学),银川 750021
  • 收稿日期:2024-10-09 修回日期:2025-03-06 接受日期:2025-03-10 发布日期:2025-03-26 出版日期:2025-10-10
  • 通讯作者: 马宝全
  • 作者简介:孙鉴(1982—),男,山东烟台人,副教授,博士,CCF会员,主要研究方向:大数据存储与管理
    张伟(2000—),男,宁夏银川人,硕士研究生,CCF会员,主要研究方向:边缘缓存
    马宝全(1998—),男(回族),宁夏银川人,硕士研究生,CCF会员,主要研究方向:移动边缘计算、大数据存储与管理 Email:1945706641@qq.com
    吴隹伟(1999—),男,湖南长沙人,硕士研究生,CCF会员,主要研究方向:大数据存储与管理
    杨晓焕(1998—),女,山西平遥人,硕士研究生,CCF会员,主要研究方向:大数据存储与管理
    武涛(1998—),男,山西大同人,硕士研究生,CCF会员,主要研究方向:任务调度。
  • 基金资助:
    国家自然科学基金资助项目(62062002);宁夏自然科学基金资助项目(2024AAC03192);宁夏自然科学基金资助项目(2022AAC03245)

MATOS: UAV swarm assisted moving-aware adaptive-parallel computing task offloading system

Jian SUN1,2, Wei ZHANG1, Baoquan MA1(), Zhuiwei WU1, Xiaohuan YANG1, Tao WU1   

  1. 1.School of Computer Science and Engineering,North Minzu University,Yinchuan Ningxia 750021,China
    2.The Key Laboratory of Image and Graphic Intelligent Processing of the State Ethnic Affairs Commission (North Minzu University),Yinchuan Ningxia 750021,China
  • Received:2024-10-09 Revised:2025-03-06 Accepted:2025-03-10 Online:2025-03-26 Published:2025-10-10
  • Contact: Baoquan MA
  • About author:SUN Jian, born in 1982, Ph. D., associate professor. His research interests include big data storage and management.
    ZHANG Wei, born in 2000, M. S. candidate. His research interests include edge cache.
    MA Baoquan, born in 1998, M. S. candidate. His research interests include mobile edge computing, big data storage and management.
    WU Zhuiwei, born in 1999, M. S. candidate. His research interests include big data storage and management.
    YANG Xiaohuan, born in 1998, M. S. candidate. Her research interests include big data storage and management.
    WU Tao, born in 1998, M. S. candidate. His research interests include task scheduling.
  • Supported by:
    National Natural Science Foundation of China(62062002);Ningxia Natural Science Foundation(2024AAC03192)

摘要:

无人机群(UAV swarm)结合5G网络成为携带计算资源的集群飞行工具后可以为移动边缘计算(MEC)网络提供额外算力支持。在半连接网络中,针对基础设施算力稀缺、海量任务数据、移动物联网(IoT)设备分布不均和利用正交频分多址(OFDMA)技术进行通信的复杂场景等挑战,提出由地面设备层、无人机(UAV)层和边缘计算层构成的移动感知自适应并行计算任务卸载系统(MATOS),以降低任务的卸载时延和能耗,从而提升任务卸载的成功率。所提系统利用UAV swarm作为空中基站(ABS)完成任务卸载和任务中继服务。首先,为了提升地面设备与UAV swarm之间的任务传输质量,结合任务属性与区域服务设备移动感知思想提出任务协同收集机制;其次,提出自适应并行遗传蚁群优化(AGACO)任务卸载机制,同时结合UAV swarm航迹规划思想,使ABS负载均衡并降低任务卸载时延;最后,以UAV swarm航迹规划、任务卸载时延和任务卸载能耗为联合优化指标,提升任务卸载成功率。实验结果表明,与基于分层云团架构的飞行器系统RESERVE(hieRarchical cloudlEt-baSed aERial Vehicle systEm)、智能可信任务卸载系统(STMTO)和无人机边缘计算物联网网络(UECIN)、多无人机辅助卸载系统(MAOS)和移动感知在线任务卸载(MOTO)系统相比,MATOS在飞行能耗上最大降低了40%,在任务卸载时延上相较于RESERVE最大降低了38.8%,在任务卸载能耗上相较于RESERVE最大降低了44.1%,验证了MATOS的优越性。

关键词: 移动边缘计算, 无人机群, 任务卸载, 负载均衡, 航迹规划, 集群并行计算

Abstract:

Unmanned Aerial Vehicle swarm (UAV swarm), integrated with 5G networks, serves as a swarm flying tool carrying computational resources, providing additional computing power support for Mobile Edge Computing (MEC) networks. For semi-connected networks, where there are challenges such as lack of infrastructure computing power, massive task data, uneven distribution of mobile Internet of Things (IoT) devices, and complex communication scenarios using Orthogonal Frequency Division Multiple Access (OFDMA) technology, a Moving-aware Adaptive-parallel Task Offloading System (MATOS) was proposed. The system was comprised of a ground equipment layer, an Unmanned Aerial Vehicle (UAV) layer, and an edge computing layer, aiming to reduce task offloading latency and energy consumption, thus enhancing the task offloading success rate. In the proposed system, UAV swarm was utilized as Airborne Base Station (ABS) to handle task offloading and relay services. Firstly, to improve the task transmission quality between ground devices and the UAV swarm, a task collaborative collection mechanism was proposed by combining task attributes with mobile perception idea of regional service devices. Secondly, an Adaptive-parallel Genetic Ant Colony Optimization (AGACO) task offloading mechanism was proposed, and UAV swarm track planning idea was integrated to achieve load balancing for ABS and reduce task offloading latency. Finally, by jointly optimizing UAV swarm track planning, task offloading latency, and task offloading energy consumption, the task offloading success rate was improved. Experimental results show that MATOS reduces the flight energy consumption by 40% at most compared to energy efficient edge cloud architecture hieRarchical cloudlEt-baSed aERial Vehicle systEm (RESERVE), Smart and Trusted Multi-UAV Task Offloading system (STMTO), UAV Edge Computing IoT Network (UECIN), Multi-UAV Assisted Offloading System (MAOS), and Mobility-aware Online Task Offloading (MOTO); compared with RESERVE, MATOS has the task offloading latency reduced by 38.8% at most, and the task offloading energy consumption reduced by 44.1% at most, which verifies the superiority of MATOS.

Key words: Mobile Edge Computing (MEC), Unmanned Aerial Vehicle swarm (UAV swarm), task offloading, load balancing, track planning, cluster parallel computing

中图分类号: