A statistical evaluation model for driver-bus-route combinatorial optimization

Abstract

Bus fuel economy is closely related to driver's habits and driving conditions. How to efficiently arrange drivers, buses and routes with better fuel economy is a difficult problem for bus companies. This paper aims to propose a statistical evaluation model for this problem. The features of bus configurations, driver operations and driving routes were analyzed, and 6 key factors were defined to represent their effects on fuel economy, which are bus design optimal velocity, bus design optimal acceleration, driver desiring velocity, driver desiring acceleration, mean velocity of bus route and mean acceleration of bus route. Based on the power balance of driver-bus-route, the problem of driverbus-route optimization can be depicted by driver, bus and route statistical points. The sum of weighted distance of three points can be set as the evaluation index of driver-bus-route arrangement. This statistical valuation model was finally applied with the monitor data from 11 drivers, 2 bus lines and 2 typical buses for more than one year. The data analysis results show that the sorting result of evaluation index is consistent with fuel economy and the proposed evaluation index can effective predict the fuel economy level of driver-bus-route arrangement. By comparing the evaluation index of the statistical evaluation model, a relatively optimal arrangement of bus-driver-routes for fuel saving can be achieved.

Route-Sensitive Fuel Consumption Models for Heavy-Duty Vehicles

“…Despite being one of the main motivations behind the increasing popularity of data-driven models, this aspect has not been extensively investigated. The focus of previous studies has been primarily on demonstrating the accuracy of data-driven models for a single vehicle or a group of similar vehicles [7,8,15,16]. As a result, there is limited understanding of the ability of data-driven models to, for instance, reliably estimate the difference in fuel consumption between two vehicles from the same fleet.…”

“…This model estimates average fuel consumption for a fleet of vehicles with similar operating conditions over extended distances. A second PAR model based on the probability distribution of the vehicle speed, the vehicle acceleration, and the accelerator pedal position is described in [16]. This model was developed by using two routes (control and test), six buses, and eleven drivers.…”

“…The models are trained using one of the duty cycles and tested against the remaining three. All of the abovementioned models [7,8,16] focus on estimating the average fuel consumption over extended distances for a group of vehicles in a fleet.…”