Fuel distribution planning for disasters: Models and case study for Puerto Rico

In this study, we propose an optimization approach for the storage and distribution of fuel after a disaster. This problem is of particular concern in island settings. Our approach models the uncertainty of the problem through a set of disaster scenarios. The scenarios capture which fuel storage locations are unavailable and which regions face higher demands for fuel due to the impact of a disaster. We develop mixed-integer programs to determine how to allocate fuel to the different regions, the value of prepositioning additional fuel in the current and new locations, and the best fuel volumes to store in different geographical locations. Our models consider both maximizing equity and output. For our case study, we examine how these different strategies could benefit Puerto Rico, given ten recent disasters that have hit this island. We are able to demonstrate the importance of prepositioning fuel in new locations.