Efficient Stream Routing in Quality- and Resource-Adaptive Flow Architectures.
K. Selçuk Candan, Lina Peng, Kyung Dong Ryu, Karam S. Chatha, Christopher B. Mayer · 2004
In this paper, we address challenges faced when optimizing data and object streams in the presence of quality and resource adaptable operators on the flow network. We present the qStream 1 flow architecture that processes, filters, and fuses sensory inputs and actuates responses in real-time while providing various Quality of Service (QoS) guarantees. The components of the architecture are programmable and adaptable; i.e, the delay, size, frequency, and quality/precision characteristics of individual operators can be controlled via a number of parameter values. Therefore, each data object streamed between components is subject to transformations and quality changes based on these parameters. The quality of an output data object and the corresponding delay and resource usage depend on the values assigned to parameters of the operators in the object flow path. In this paper, we develop performance models for the quality-adaptive stream optimization. We introduce a class of route optimization problems that promote creation and delivery of high precision, small delay, and small resource-usage objects to the actuators. We develop QoS, resource, and deadline aware flow optimization techniques. We experimentally show the effectiveness of the algorithms.