A new low complexity bus travel time estimator for fleet management system

Improving the experience of using the public transportation system canbe done by estimating the arrival time of the bus and notifying thepassengers. Consequently, the accuracy of the estimation affects thisexperience. As the number of buses, stations, and service areas increases,the data collected in the cloud makes travel time estimation-relateddata processing more challenging. Despite this challenge, a distributedmethod for estimating the arrival time of the bus is considered in thispaper. Also, we present a way to decentralize data processing and distributeit on each bus. Besides, using the Kalman filter and updating theestimated values at short intervals improves the estimation error. Examinationof the degree of complexity shows that the proposed methodhas significantly reduced the complexity in the cloud, which makesthe proposed method implementable in metropolitan areas. The implementationresults on a dataset show that the proposed method has agood performance in terms of mean square error and root mean square.