Data-Driven Analysis of the Fuel Saving Potentialof Road Vehicle Platooning : A data-driven approach for quantifying the fuel saving effects of platooning based ondata collected in real traffic conditions.

Platooning with trucks is showing promising theoretical results in itsability to lower fuel consumption due to reduction in air drag. Currently,Scania is test driving their trucks in convoys in order to evaluatethe concept, in terms of driving behavior and actual fuel saving, underrealistic conditions. However, due to traffic conditions it is hard to keepthe convoys intact for longer routes and therefore the actual fuel savingeffect is hard to evaluate. In this thesis, data collected from a fleetof long haulage trucks is analyzed with four different machine learningpredictors in order quantify the fuel saving potential of platooning. Theanalyzed machine learning methods are Support Vector regression, MultilayerPerceptrons, Random Forests and Decision Trees. The modelsobtained from the methods coherently suggest that platooning reducesthe average fuel consumption by several percent.