Time Series Prediction with Digital Twins in Public Transportation Systems

Abstract

Classical traffic and transportation control centres are becoming insufficient with the rapid spread of electric, intelligent, autonomous, and software-defined vehicles. Existing traffic management strategies have significant drawbacks in public safety, predictive maintenance, tuning the core functionality of vehicles, and managing mobility. We can renovate this system with next-generation intelligent Digital Twin (DT) technologies. This research proposes a timeseries prediction system through Digital Twins to manage public transportation system with Facebook’s Prophet. This study presents a model framework to build Digital Twin application in Intelligent Public Transportation Systems and used a public data set to validate model with Facebook’s Prophet library by forecasting metro lines usage. Obtained results presented in the study and it is shown that forecasting error interms of Mean Absolute Percentage Error (MAPE) is 0.017 for 1 day horizon.