Cloud-Based Demand-Responsive Transportation System Using Forecasting Model

Abstract

Faced with the cost of local management of IT infrastructure, many transportation operators have decided to use Cloud Computing services via its providers. The latter make resources available to transportation operators in the form of Virtual Machine (VM). Thus, transportation operators only use a limited number of virtual machines capable of satisfying their needs. This contributes to the reduction in the costs of the customer IT infrastructure. However, in DRT Demand-Responsive Transportation system and in order to avoid service overload and largely unused resources, it is important to anticipate the number of future passenger demands. Considering the importance of these challenges, this paper presents a Cloud-based Demand-Responsive Transportation system. Such a system is based on two principles: (I) forecasting passenger demand, in order to prepare the conditions for exploiting resources and achieving their optimal efficiency. For this purpose, actual passenger demand is predicted by applying an artificial neural network based on a Multilayer Feed-Forward Neural Network (MLFF). It constitutes a reference predicting the future passenger demands based on past demands and thus, obtaining an appropriate prediction of future loads. (II) Pre-allocate resources, to avoid overloading or over-provisioning their capacity to better manage peaks in demand, all based on an estimation process that will help predetermine resource requirements. System evaluation is performed by using OpenNebula middleware, and real passenger demand data have shown performance gains ranging up to a 25% margin for utilization rate applied to forecasting future demand.