物联网学报2024，Vol.8Issue(4)：23-33,11.DOI:10.11959/j.issn.2096-3750.2024.00449
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
摘要
Abstract
Multi-sensor systems integrate diverse sensor data to achieve comprehensive and accurate environmental per-ception.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 architec-ture 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.Fi-nally,the delay and energy consumption requirements of tasks were modeled,and the optimization problem of minimiz-ing 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 ar-chitecture 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Key words
multi source heterogeneous data/data fusion/sensor/arithmetic optimization分类
信息技术与安全科学引用本文复制引用
丁凯,蒋超越,陶铭,谢仁平..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):23-33,11.基金项目
国家自然科学基金资助项目(No.62001113) （No.62001113）
广东省基础与应用基础研究基金项目(No.2021A1515010656)The National Natural Science Foundation of China(No.62001113),The Basic and Applied Basic Research Fund-ing Program of Guangdong Province(No.2021A1515010656) （No.2021A1515010656）
