Cost Effective Road Traffic Prediction Model using Apache Spark

Objectives: We proposed a cost effective model to predict the traffic to inform the public about the current traffic condition to all persons who are entering the same lane. Analysis: In real time application like traffic monitoring, it needs to process huge volume of data in huge size. We analyzed the traffic prediction using the current technologies Apache Hadoop and Apache Spark framework. Spark is processing the 10 Terabytes of data in half-a-second. The main uniqueness from our approach is that we can predict the road traffic using Spark within half-a-second. Findings: Road traffic is predicted using Ultrasonic and PIR sensor within a half second. The proposed system uses the vehicle count and speed to predict the traffic condition. Existing system using hadoop will predict the traffic in few seconds. Whereas in the proposed system performance gets increased using Spark. Therefore, the results are more helpful in finding the road traffic condition. Improvement: The proposed system predicts it in a half a second by using Spark whereas the existing system predicted the road traffic by consuming more time.