Machine-Learning methodology for energy efficient routing

Demestichas, K.; Masikos, M.; Adamopoulou, E.; Dreher, S.; Diaz De Arkaya, A.

Machine-Learning methodology for energy efficient routing

Identifiers

URI: https://hdl.handle.net/11556/4722

Publication date

2012

Authors

Citations

Export

Abstract

Eco-driving assistance systems encourage economical driving behaviours and support the driver in optimizing his driving style to achieve fuel economy and consequently emission reduction. Energy efficient routing is one of the especially pertinent issues related to the autonomy of Fully Electric Vehicles (FEVs). This paper introduces a novel methodology for energy efficient routing, based on the realization of dependable energy consumption predictions for the various road segments constituting an actual or potential vehicle route, and it is mainly performed by means of machine-learning functionality, through the use of the so-called Machine-Learning Engines. The proposed methodology, the functional architecture implementing it, as well as first experimental results are presented in detail.

Keywords

Consumption prediction , Energy efficiency , Machine-learning , Routing , Computer Networks and Communications , Computer Science Applications , Control and Systems Engineering , Electrical and Electronic Engineering , Mechanical Engineering , Transportation , SDG 7 - Affordable and Clean Energy

Type

conference output

Citation

Demestichas , K , Masikos , M , Adamopoulou , E , Dreher , S & Diaz De Arkaya , A 2012 , ' Machine-Learning methodology for energy efficient routing ' , Paper presented at 19th Intelligent Transport Systems World Congress, ITS 2012 , Vienna , Austria , 22/10/12 - 26/10/12 pp. EU-00226 .
conference

Full item page