【摘要】 在当今的网络监控、通信服务、传感网络和金融服务等应用领域中产生了大量的流数据。当流数据的输入速率超过系统的容量,系统性能就会下降。在这种情形下,降载虽然降低了结果的准确性,但可以改善系统的性能。本文讨论了流数据降载的研究现状,对相关技术进行了总结和对比。降载的关键是确定降载的方式和实施的降载计划,本文把降载方式概括为语义降载、随机降载和自适应降载,降载计划包含降载的时间、降载的位置和降载的量等。讨论了面临的挑战和未来研究的发展方向。更多还原

【Abstract】 Data streams arise in a number of monitoring applications in domain such as networking, telephone, sensor networks and financial services. Various Quality-of-Service (QoS)requirements should be meet in the process of querying in Data Stream Management Systems(DSMS). When input rates exceed system capacity, the system will become overloaded and cannot meet quality requirement. Under these conditions, the system will shed load to improve the observed latency of the results. This paper discusses the load shedding technology, and concludes that the load shedding should contain the mode and plan. This paper proposes that the mode of load shedding includes random shedding, semantic shedding and adaptive shedding. The plan of load shedding contains when, where to shed load and how much load to shed. Finally, some of the important open issues are addressed.更多还原