EvacSys: A Cloud-Based Service for Emergency Evacuation

Abstract

Natural or man-made disasters wreak havoc, whether they're floods, earthquakes, tornados, hurricanes, or wild fires. One of the major challenges in emergency situations is to guide people through safe routes away from the disaster site on the basis of the available information. To do this, data from multiple sources-such as roadside sensory units, emergency vehicles, and satellite imagery-must be processed in real time to compute the appropriate routes. However, to process the huge volumes of sensory data in real time also requires higher computational resources. For many years, cloud computing has been well established as a reliable solution to meet higher data and computational demands. In this article, the authors discuss the architecture of EvacSys, a scalable cloud-based emergency evacuation service. EvacSys uses the power of cloud computing to process large volumes of real-time sensory data gathered during disaster; it then computes appropriate routes for evacuees, giving priority to emergency vehicles. The authors also present a case study testing the service on a real city transportation network.