Sustainable Time Series Model for Vehicular Traffic Trends Prediction in Metropolitan Network

Abstract

With the widespread of technological evolution in transportation industry, the escalation of vehicular traffic has increasingly become prevalent in the metropolitan cities. Developments of automobile technology and rise in vehicles on the streets have made the traffic management quite challenging. This makes time series analysis of traffic-flows, an integral part of Intelligent Transportation System (ITS). The main objective is to focus on managing traffic conditions and preventing congestion havoc on roads. Our research focuses on analysis of the traffic patterns for predicting transport trends in future, subject to the trend of initial traffic instances. For implementing the aspects of ITS effectively, our proposed approach includes access to the online sensor data of traffic flows recorded in specific location. The analysis of sensory data helps to build traffic prediction model, which can be further used to recommend alternative routes, thereby responding to traffic congestions effectively.