An Empirical Model for the Assessment of Truck Driver Fuel Economy

Abstract

Effective management of fuel economy is of critical importance for road freight transport operators to ensure profitability.Empirical evidence indicates that a variety of factors, including route inclination, payload and truck driver behavior, have a significant impact on fuel consumption. This creates the need for an accurate and objective method to distinguish the impact of drivers from other factors, in order to enable reliable driver performance assessment. We first extracted descriptive statistics from a data set for 331 drivers completing trips over 21 routes to obtain evidence of the impact of route, payload and driver behaviour on fuel economy. We then extracted an empirical model for fuel economy to remove the impact of route inclination and payload, allowing the impact of driver performance to be measured more accurately. The empirical models were applied to unseen test data and were found to possess significant out-of-sample predictive ability. We demonstrated that by subtracting the impact of route inclination and payload, the remaining model error provided a more correct indication of driver performance. The significance of this method was verified by comparing the difference in driver performance ranking before and after compensating for route inclination and payload.