多源异构传感器数据融合和算力优化研究

丁凯; 蒋超越; 陶铭; 谢仁平

doi:10.11959/j.issn.2096-3750.2024.00449

您当前的位置：

首页 >

文章列表页 >

多源异构传感器数据融合和算力优化研究

专题：算力物联网 | 更新时间：2025-01-20

- 多源异构传感器数据融合和算力优化研究
- Research on heterogeneous data fusion and arithmetic optimization in multi-sensor systems
- 物联网学报 2024年8卷第4期页码：23-33
- 作者机构：
  
  1.东莞理工学院计算机科学与技术学院，广东东莞 523808
  2.人工智能与数字经济广东省实验室（深圳），广东深圳 518107
- 作者简介：
  
  [ "丁凯（1985‒ ），男，博士，东莞理工学院计算机科学与技术学院副教授，主要研究方向为物联网、智慧城市、机器人技术和移动互联应用等。" ]
  [ "蒋超越（2000‒ ），男，东莞理工学院计算机科学与技术学院硕士生，主要研究方向为物联网工程、异常检测和人工智能等。" ]
  [ "陶铭（1986‒ ），男，博士，东莞理工学院计算机科学与技术学院教授、副院长，主要研究方向为人工智能、边缘计算和云计算等。" ]
  [ "谢仁平（1989‒ ），男，博士，东莞理工学院计算机科学与技术学院特聘副研究员，主要研究方向为计算机视觉、图像处理、目标检测、图像分割、图像融合、图像拼接和桥梁检测机器人等。" ]
- 基金信息：
  
  国家自然科学基金资助项目(62001113);广东省基础与应用基础研究基金项目(2021A1515010656)
- DOI：10.11959/j.issn.2096-3750.2024.00449
  中图分类号：
- 纸质出版日期：2024-12-10，
  
  收稿日期：2024-10-14，
  
  修回日期：2024-12-09，
- 稿件说明：
移动端阅览
丁凯, 蒋超越, 陶铭, 等. 多源异构传感器数据融合和算力优化研究[J]. 物联网学报, 2024,8(4):23-33.

DING KAI, JIANG CHAOYUE, TAO MING, et al. Research on heterogeneous data fusion and arithmetic optimization in multi-sensor systems. [J]. Chinese journal on internet of things, 2024, 8(4): 23-33.
丁凯, 蒋超越, 陶铭, 等. 多源异构传感器数据融合和算力优化研究[J]. 物联网学报, 2024,8(4):23-33. DOI： 10.11959/j.issn.2096-3750.2024.00449.

DING KAI, JIANG CHAOYUE, TAO MING, et al. Research on heterogeneous data fusion and arithmetic optimization in multi-sensor systems. [J]. Chinese journal on internet of things, 2024, 8(4): 23-33. DOI： 10.11959/j.issn.2096-3750.2024.00449.

摘要

多传感器系统通过整合多种传感器数据，实现了全面且精准的环境感知，然而，如何有效融合异构数据并实现实时处理的高效性，仍然是当前研究的热点和难点问题。为此，围绕多源异构传感器的数据融合和算力优化展开研究，提出了一种创新的解决方案。首先，基于主/从架构设计数据融合系统，解决多源异构数据处理难题；其次，构建了“云—边—端”3层架构，利用边缘服务器分担云服务器的计算压力，权衡任务调度策略，实现网络资源与计算资源的协同管理；最后，针对任务的时延与能耗需求进行建模，在资源约束下构建最小化系统成本的优化问题，将问题转化为马尔可夫决策过程（MDP

Markov decision process），使用深度确定性策略梯度（DDPG

deep deterministic policy gradient）算法进行求解。仿真结果表明，所提出的架构和调度策略在降低时延和能耗方面表现优异，为多传感器系统中的高效数据融合与算力优化提供了新思路。

Abstract

Multi-sensor systems integrate diverse sensor data to achieve comprehensive and accurate environmental perception. However

how to effectively fuse heterogeneous data and realize the efficiency of real-time processing is still a hot and difficult issue in current research. Therefore

focusing on data fusion and arithmetic optimization of multi-source heterogeneous sensors

an innovative solution was proposed. Firstly

a data fusion system based on master-slave architecture was designed to solve the problem of multi-source heterogeneous data processing. Secondly

a three-layer "cloud-edge-end" architecture was implemented

leveraging edge servers to offload computational pressure from cloud servers

optimizing task scheduling strategies

and enabling coordinated management of network and computing resources. Finally

the delay and energy consumption requirements of tasks were modeled

and the optimization problem of minimizing system cost was constructed under resource constraints

which was transformed into Markov decision process (MDP) and solved with deep deterministic policy gradient (DDPG) algorithm. Simulation experiments show that the proposed architecture and scheduling algorithm exhibit excellent performance in reducing both latency and energy consumption

and provide a new idea for efficient data fusion and arithmetic optimization in multi-sensor systems.

关键词

多源异构数据数据融合传感器算力优化

Keywords

multi source heterogeneous datadata fusionsensorarithmetic optimization

references

黄媛, 牛传俊, 余博. 基于多源异构数据融合的高速公路建设项目可视化管理关键技术研究[J]. 价值工程, 2024, 43(26): 7-9.

HUANG Y, NIU C J, YU B. Research on key technology of visualization management of expressway construction project based on multi-source heterogeneous data fusion[J]. Value Engineering, 2024, 43(26): 7-9.

宋慧欣.” 新基建”, 工业物联网发展新引擎[J]. 自动化博览, 2020, 37(6): 3.

SONG H X. “New infrastructure”, the new engine of industrial Internet of things development[J]. Automation Panorama, 2020, 37(6): 3.

余文科, 程媛, 李芳, 等. 物联网技术发展分析与建议[J]. 物联网学报, 2020, 4(4): 105-109.

YU W K, CHENG Y, LI F, et al. Analysis and suggestions on the development of IoT technology[J]. Chinese Journal on Internet of Things, 2020, 4(4): 105-109.

闫佳怡, 赵宝奇, 汤陈, 等.基于信息熵和优劣解距离法的多传感器信息评价融合算法[J].电光与控制, 2024: 1-9.

YAN J Y, ZHAO B Q, TANG C, et al. Multi-sensor information evaluation fusion algorithm based on information entropy and TOPSIS[J]. Electronics Optics & Control, 2024: 1-9.

亓晋, 王微, 陈孟玺, 等. 工业互联网的概念、体系架构及关键技术[J]. 物联网学报, 2022, 6(2): 38-49.

QI J, WANG W, CHEN M X, et al. Concept, architecture and key technologies of industrial Internet[J]. Chinese Journal on Internet of Things, 2022, 6(2): 38-49.

TRAN M Q, LIU M K, ELSISI M. Effective multi-sensor data fusion for chatter detection in milling process[J]. ISA Transactions, 2022, 125: 514-527.

CAO K Y, LIU Y F, MENG G J, et al. An overview on edge computing research[J]. IEEE Access, 2020, 8: 85714-85728.

王旭, 陈南希, 张柔佳. 智能自适应边缘系统: 探索与挑战[J]. 物联网学报, 2021, 5(1): 1-10.

WANG X, CHEN N X, ZHANG R J. Intelligent adaptive edge systems: exploration and open issues[J]. Chinese Journal on Internet of Things, 2021, 5(1): 1-10.

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, 8(3): 76-90.

YU X B, ZHANG S H, ZHANG H L. An edge-cloud collaborative model evolution and communication paradigm in Internet of low-altitude UAV[J]. Chinese Journal on Internet of Things, 2024, 8(3): 76-90.

庞笛, 魏喆, 陈墨, 等.一种基于场景人物数量的任务卸载方案：针对云边协同的智能监控系统[J]. 工程设计学报, 2024: 1-8.

PANG D, WEI Z, CHEN M, et al. A task offloading scheme based on the number of scene characters: forcloud-edge collaborative intelligent surveillance system[J]. Chinese Journal of Engineer Design, 2024: 1-8.

孙国玮, 许方敏, 朱瑾瑜, 等. 算力网络中的确定性调度与路由联合智能优化方案[J]. 北京邮电大学学报, 2023, 46(2): 9-14.

SUN G W, XU F M, ZHU J Y, et al. Deterministic scheduling and routing joint intelligent optimization scheme in computing first network[J]. Journal of Beijing University of Posts and Telecommunications, 2023, 46(2): 9-14.

熊凯, 冷甦鹏, 张可, 等. 车联雾计算中的异构接入与资源分配算法研究[J]. 物联网学报, 2019, 3(2): 20-27.

XIONG K, LENG S P, ZHANG K, et al. Research on heterogeneous radio access and resource allocation algorithm in vehicular fog computing[J]. Chinese Journal on Internet of Things, 2019, 3(2): 20-27.

SUN D Y, LI Y B, JIA S X, et al. Non-contact diagnosis for gearbox based on the fusion of multi-sensor heterogeneous data[J]. Information Fusion, 2023, 94: 112-125.

赵小强, 李森. 基于多传感器数据融合的互异网络轴承故障诊断方法[J]. 计算机工程与应用, 2024: 1-14.

ZHAO X Q, LI S. Heterogeneous network bearing fault diagnosis method based on multi-sensor data fusion[J]. Computer Engineering and Applications, 2024: 1-14.

于继江, 姜杰斯, 董中平. 基于异构数据源的信息网络安全态势感知方法[J]. 自动化与仪器仪表, 2024(8): 55-58.

YU J J, JIANG J S, DONG Z P. Information network security situation awareness method basedon heterogeneous data sources[J]. Automation & Instrumentation, 2024(8): 55-58.

邢文革, 桂佑林, 顾万里. 多传感器系统误差特性匹配的动态估计与补偿算法[J]. 电子科技大学学报, 2021, 50(2): 186-192.

XING W G, GUI Y L, GU W L. A dynamic estimation and compensation algorithm for matching the error characteristics of multi-sensor system[J]. Journal of University of Electronic Science and Technology of China, 2021, 50(2): 186-192.

黄莹. 复杂系统多传感器数据智能融合方法研究[J]. 机械工程学报, 2024: 1-7.

HUANG Y. Research on intelligent fusion method for multi sensor data in complex systems[J]. Journal of Mechanical Engineering, 2024: 1-7.

杨澳钦, 宫傲宇, 房婷, 等. 传输时限约束下的能量收集无线传感器网络多址接入优化[J]. 物联网学报, 2022, 6(3): 58-70.

YANG A Q, GONG A Y, FANG T, et al. Optimization of multiple access in the energy harvesting wireless sensor network with delivery deadline constraint[J]. Chinese Journal on Internet of Things, 2022, 6(3): 58-70.

史先传, 张本阳, 卢鸿运, 等. 基于Modbus RTU协议的多传感器数据采集系统设计[J]. 仪表技术与传感器, 2024(7): 46-50, 76.

SHI X C, ZHANG B Y, LU H Y, et al. Design of multi-sensor data acquisition system based on modbus RTU protocol[J]. Instrument Technique and Sensor, 2024(7): 46-50, 76.

GĂITAN V G, ZAGAN I. Modbus protocol performance analysis in a variable configuration of the physical fieldbus architecture[J]. IEEE Access, 2022, 10: 123942-123955.

宋海鹰, 陈志文, 邱佰平, 等. 基于物联网和边缘计算的智能化建筑管理系统及应用[J]. 物联网学报, 2020, 4(4): 98-104.

SONG H Y, CHEN Z W, QIU B P, et al. Building intelligent integrated management system based on Internet of Things and edge computing and its application[J]. Chinese Journal on Internet of Things, 2020, 4(4): 98-104.

吴善滨, 曹灵芝, 禹晋. 基于雾计算节点的智能交通管控平台的设计与实现[J]. 交通世界, 2024(22): 14-17.

WU S B, CAO L Z, YU J. Design and implementation of intelligent traffic management and control platform based on fog computing node[J]. TranspoWorld, 2024(22): 14-17.

陈星延, 张雪松, 谢志龙, 等. 面向“云-边-端” 算力系统的计算和传输联合优化方法[J]. 计算机研究与发展, 2023, 60(4): 719-734.

CHEN X Y, ZHANG X S, XIE Z L, et al. A computing and transmission integrated optimization method for cloud-edge-end computing first system[J]. Journal of Computer Research and Development, 2023, 60(4): 719-734.

SUN Y K, LEI B, LIU J L, et al. Computing power network: a survey[J]. China Communications, 2024, 21(9): 109-145.

韩坤, 王政, 段俊勇, 等. 基于雾计算的制造物联网数据处理技术综述[J]. 计算机与现代化, 2024(1): 13-20.

HAN K, WANG Z, DUAN J Y, et al. Overview of data processing techniques for MIoT based on fog computing[J]. Computer and Modernization, 2024(1): 13-20.

袁培燕, 邵赛珂, 魏然, 等. 基于时延和能耗约束的感知数据协作卸载策略研究[J]. 物联网学报, 2023, 7(1): 109-117.

YUAN P Y, SHAO S K, WEI R, et al. Research on the cooperative offloading strategy of sensory data based on delay and energy constraints[J]. Chinese Journal on Internet of Things, 2023, 7(1): 109-117.

JIN C Q, BAI X L, YANG C, et al. A review of power consumption models of servers in data centers[J]. Applied Energy, 2020, 265: 114806.

RAEISI-VARZANEH M, DAKKAK O, HABBAL A, et al. Resource scheduling in edge computing: architecture, taxonomy, open issues and future research directions[J]. IEEE Access, 2023, 11: 25329-25350.

HUANG H C, LIAO W H, LEI X H, et al. An urban DEM reconstruction method based on multisource data fusion for urban pluvial flooding simulation[J]. Journal of Hydrology, 2023, 617: 128825.

LI Y J, HUYNH D V, NGUYEN V L, et al. Multiagent UAV-aided URLLC mobile edge computing systems: a joint communication and computation optimization approach[J]. IEEE Systems Journal, 2024(99): 1-11.

申怡飞. 极化码译码算法与实现研究[D]. 南京：东南大学, 2022.

SHEN Y F. Decoding algorithms and implementations for polar codes[D]. Nanjing: Southeast University, 2022.

JAIN A, SINGHAL P. Fog computing: Driving force behind the emergence of edge computing[C]//Proceedings of the 2016 International Conference System Modeling & Advancement in Research Trends (SMART). Piscataway: IEEE Press, 2017: 294-297.

肖易寒, 陈志亮, 李虎, 等. 基于双重竞争深度正则化Q学习的干扰探测一体化波形设计[J].应用科技, 2024: 1-8.

XIAO Y H, CHEN Z L, LI H, et al. Design of jamming-detection shared waveform based on double dueling deep Q-learning network based on regularization[J]. Applied Science and Technology, 2024: 1-8.

王琴, 宁洛函, 张钰瑄, 等. 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 [J]. 物联网学报, 2024, 8(3): 26-35.

WANG Q, NING L H, ZHANG Y X, et al. Joint optimization method for UAV trajectory and charging/discharging in cell-free mMIMO system on WPT[J]. Chinese Journal on Internet of Things, 2024, 8(3): 26-35.

GAO H H, WANG X J, WEI W, et al. Com-DDPG: task offloading based on multiagent reinforcement learning for information-communication-enhanced mobile edge computing in the Internet of vehicles[J]. IEEE Transactions on Vehicular Technology, 2024, 73(1): 348-361.

刘延飞, 李超, 王忠, 等.多智能体深度强化学习及可扩展性研究进展[J].计算机工程与应用, 2024: 1-27.

LIU Y F, LI C, WANG Z, et al. Research progress on multi-agent deep reinforcement learning and scalability[J]. Computer Engineering and Applications, 2024: 1-27.

HU H, WU D G, ZHOU F H, et al. Intelligent resource allocation for edge-cloud collaborative networks: a hybrid DDPG-D3QN approach[J]. IEEE Transactions on Vehicular Technology, 2023, 72(8): 10696-10709.

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

基于卡尔曼滤波器和多层感知器的大麦幼苗最优生长参数预测