Efficient Data Processing With Exogeni For The Casa Dfw Urban Testbed

As the CASA DFW Urban Testbed has evolved from a small, Doppler radar network to an operational system providing user decision support, multi-sensor data, images thereof, and a real time alerting mechanism, it has become necessary to make use of the Compute Cloud to efficiently process and classify products in a timely and cost effective manner. The Global Environment for Network Innovations (GENI), was selected for this purpose and this manuscript shall describe how compute resources are managed to reduce idle time, how networks are configured dynamically to maximize performance, and how diverse products are accumulated and processed to serve the diverse user base in the DFW metroplex. We find that the GENI cloud offers superior networking, resource acquisition speed than several commodity clouds, and hardware performance on par.