摘要
降载可以有效地解决数据流流速的突变所引发的系统的过载问题。为此,分析现有降载策略在实时性方面的不足,不仅考虑系统的处理能力,同时结合数据的处理延迟,提出基于延迟时间的降载策略(DSP)。实验结果表明,DSP可以有效地解决系统的过载,同时具有较高的实时性。
Load shedding is one of promising approaches when the system becomes overloaded because of irregular changes of the arrival rate of tuples. This paper proposes a data stream load shedding model called Delay-based Shedding Policy(DSP) which not only considers the processing capacity of system, but also the delay of processing data. The new policy based on delay-time is to fetch up the insufficiency of real time of existing load shedding policy. Experimental result shows that the DSP not only resolves overload efficiently, but also has high delay-time.
出处
《计算机工程》
CAS
CSCD
北大核心
2010年第21期49-51,共3页
Computer Engineering
基金
国家自然科学基金资助项目(60873047)
江苏省自然科学基金资助项目(BK2008154)
关键词
数据流
降载策略
数据流管理系统
data stream
load shedding policy
data stream management system