The Weather Channel (TWC) uses an internally developed application for weather prediction and reporting. The HiRAD system extrapolates the weather at 1.9 million points of interest in the United States.
TWC wanted HiRAD to increase data output from the 10,000-data-point level up to 1.9 million observations while staying at 5-7 minutes per cycle.
The Weather Channel selected Moab Cluster Suite® from Adaptive Computing to run its memory-intensive application.
Moab allows The Weather Channel to specify exactly when it wants a calculation to run, how often, and on which hardware—in an easy-to-use manner. This fine-grained control lets administrators extract the maximum value from their clusters.