This paper describes the architecture and programming model of a semantic-service-oriented sensor information system platform. We argue that the key to enabling scalable sensor information access is to define an ontology and associated sensor information hierarchy for interpretation of raw data streams. The ontological abstraction allows a sensing system to optimize its resource utilization in collecting, storing, and processing data. We describe the SONGS architecture that uses an automatic service planning to convert declarative user queries into a service composition graph, and performs compile-time and run-time optimizations for resource-aware execution of the service composite in a sensor network, building on the sensor information hierarchy. We motivate and demonstrate the SONGS platform using a parking garage example