Quality-driven evaluation of trigger conditions on streaming time series

For many applications, it is important to evaluate trigger conditions on time series streams. In a resource constrained environment, users' needs should ultimately decide how the evaluation system balances the competing factors such as evaluation speed, result precision, and load shedding level. This paper presents a basic framework for evaluation algorithms that takes user-specified quality requirements into consideration. Three optimization algorithms, each under a different set of quality requirements, are developed in the framework: (1) minimize the response time given accuracy requirements and without load shedding; (2) minimize the load shedding given a response time limit and accuracy requirements; and (3) minimize one type of accuracy errors given a response time limit and without load shedding. Experiments show that these optimization algorithms effectively achieve their optimization goals while satisfying the corresponding user-specified quality requirements. Copyright 2005 ACM.