Adaptive Control of Extreme-scale Stream Processing Systems
ICDCS '06 Proceedings of the 26th IEEE International Conference on Distributed Computing Systems
SPADE: the system s declarative stream processing engine
Proceedings of the 2008 ACM SIGMOD international conference on Management of data
CLASP: collaborating, autonomous stream processing systems
Proceedings of the ACM/IFIP/USENIX 2007 International Conference on Middleware
Harmony: holistic messaging middleware for event-driven systems
IBM Systems Journal
Real-Time Sensor Signal Capture from a Harsh Environment
DS-RT '12 Proceedings of the 2012 IEEE/ACM 16th International Symposium on Distributed Simulation and Real Time Applications
A real-time stream storage and analysis platform for underwater acoustic monitoring
IBM Journal of Research and Development
Hi-index | 0.00 |
Multiparameter and multiscale real-time environmental monitoring of a river and estuary system will be realized through the River and Estuary Observatory Network (REON) for the Hudson River in New York. In this paper, we describe a system under development that provides a holistic view of this complex and dynamic natural environment for scientific research, education, management, and environmental policy-related applications. The system incorporates a complex array of sensor technologies encompassing the physical, chemical, and biological measurement domains. REON supports Lagrangian, Eulerian, and autonomous robot sensor deployments, as well as flexible telemetry options through an open and consistent middleware architecture with advanced device management capabilities. Multimodal data streams are ingested and analyzed by an intelligent distributed streaming data analysis system known as System S. The challenges of managing high volumes of complex heterogeneous data are addressed via a distributed network of intelligent computational nodes that incorporate both autonomic algorithms and active knowledge management including a temporal component. REON provides an adaptive computing environment that provides isotropy in terms of data access and collaborative computation in contrast to traditional hierarchical control systems for sensor environments. Also presented is the underlying information infrastructure that supports a robust and integrated data modeling, simulation, and visualization manifold.