University of Massachusetts
Since today's weather forecasts only cover large regions every few hours, their use in severe weather is limited. In this paper, the authors present CloudCast, an application that provides short-term weather forecasts depending on user's current location. Since severe weather is rare, CloudCast leverages pay-as-you-go cloud platforms to eliminate dedicated computing infrastructure. CloudCast has two components: an architecture linking weather radars to cloud resources, and a Nowcasting algorithm for generating accurate short-term weather forecasts. They study CloudCast's design space, which requires significant data staging to the cloud. Their results indicate that serial transfers achieve tolerable throughput, while parallel transfers represent a bottleneck for real-time mobile Nowcasting.