Exploiting application semantics in monitoring real-time data streams

Real-time stream processing applications must be prepared to operate under overloaded conditions. Existing load shedding techniques are not suitable for processing real-time data streams because their tuple dropping policies may violate application deadlines in an uncontrolled way. We'd argue that a more precise load shedding model, e.g., the (m, k) deadline model adopted in this paper, is much appropriate than the commonly used random dropping policy. Based on the (m, k) load shedding model and a novel load shedding approach, we propose a concrete (m, k) scheduling algorithm called SOSA-DBP by exploiting application semantics. Experimental results show that SOSA-DBP has significant performance gain over the existing (m, k) scheduling algorithm.