The International Conference for High Performance Computing, Networking, Storage and Analysis
A Cloud-Based Interactive Data Infrastructure for Sensor Networks.
Authors: Tonglin Li (Illinois Institute of Technology), Kate Keahey (Argonne National Laboratory), Rajesh Sankaran (Argonne National Laboratory), Pete Beckman (Argonne National Laboratory), Ioan Raicu (Illinois Institute of Technology)
Abstract: Small specialized sensor devices capable of both reporting on environmental factors and interacting with the environment are becoming increasingly ubiquitous, reliable and inexpensive. This transformation has enabled domain sciences to create "instruments at large" – dynamic and often self-organizing groups of sensors whose outputs are capable of being aggregated and correlated to support experiments organized around specific questions. This calls for an infrastructure that supports remote administration of sensors, relies on protocols that withstand unreliable communications, and extend storage capability that scales to support many data producing sensors, many different
data types, and many end user requests. In this work we present protocols and a cloud-based data store called "WaggleDB" that address the above challenges. The system efficiently aggregates and stores data from sensor networks and enables users to query the data sets. The "WaggleDB" data store incorporates a scalable multi-tier architecture with individually scalable tiers toward overcoming the challenges.