摘要
物联网相关技术的快速发展产生了大规模传感流数据和对流数据的高并发处理需求,云边端协同计算正成为低延迟、高可靠的流数据处理的有效途径。为了提升流数据处理系统的灵活性和可扩展性,降低流数据处理延迟,本文提出一种基于服务的分散式云边端协同流数据处理体系结构,设计了面向大规模流数据的主动式数据服务模型,流数据及流数据处理被抽象为合适粒度、可被独立部署和动态调度的服务,解耦数据与计算。引入事件驱动机制,提出了基于事件驱动的云边端服务动态协作机制,有效提升了系统的灵活性。基于真实的电能质量传感流数据验证了本文所提出架构的正确性和有效性。
The rapid development of Internet of Things technologies has generated large-scale sensor streaming data and high-concurrency processing requirements for streaming data.The cloud-edge collaborative computing is becoming an effective approach for low-latency,highly reliable stream data processing.In order to improve the flexibility and scalability of stream data processing system,reduce the delay of stream data processing,this paper proposes a decentralized architecture for streaming data processing with a service-based method in cloud-edge collaborative environment.A proactive data service model for large-scale streaming data services is designed.The streaming data and streaming data processing are abstracted into appropriate grained services that can be independently deployed and dynamically scheduled,decoupling data from computation.By introducing the event-driven mechanism,we proposed the event-driven based cloud edge service dynamic collaboration mechanism to improve the flexibility of the system effectively.A simulation-based evaluation based on realworld power quality sensor streaming data verified the effectiveness and efficiency of our approach.
作者
张守利
刘晨
ZHANG Shou-li;LIU Chen(College of Information Science and Engineering/Shandong Agricultural University,Tai'an 271018,China;Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data,North China University of Technology,Beijing 100049,China)
出处
《山东农业大学学报（自然科学版）》
北大核心
2024年第3期385-395,共11页
Journal of Shandong Agricultural University：Natural Science Edition
关键词
流数据处理
云边端协同
服务计算
事件驱动
服务协作
Streaming data processing
cloud-edge collaboration
service computing
event driven
service collaboration
