Energetic Map Data Imputation: A Machine Learning Approach

Tobias Straub, Mandy Nagy, Maxim Sidorov, Leonardo Tonetto, Michael Frey and Frank Gauterin
Additional contact information
Tobias Straub: Institute of Vehicle System Technology, Karlsruhe Institute of Technology (KIT), 76131 Karlsruhe, Germany
Mandy Nagy: Department of Informatics, Technical University of Munich, 85748 Garching, Germany
Maxim Sidorov: BMW Group, 80788 Munich, Germany
Leonardo Tonetto: Department of Informatics, Technical University of Munich, 85748 Garching, Germany
Michael Frey: Institute of Vehicle System Technology, Karlsruhe Institute of Technology (KIT), 76131 Karlsruhe, Germany
Frank Gauterin: Institute of Vehicle System Technology, Karlsruhe Institute of Technology (KIT), 76131 Karlsruhe, Germany

Energies, 2020, vol. 13, issue 4, 1-23

Abstract: Despite a rapid increase of public interest for electric mobility, several factors still impede Battery Electric Vehicles’ (BEVs) acceptance. These factors include their limited range and inconvenient charging. For mitigating these limitations to users, certain BEV-specific services are required. Therefore, such services provide a reliable range prediction and routing, including charging-stop planning. The basis of these services is a precise and reliable Energy Demand (ED) prediction. For that matter, aggregated fleet-vehicle data combined with map-specific data (e.g., road slope) form an energetic map, which can serve for precise ED predictions. However, data coverage is paramount for these predictions, more specifically regarding gapless energetic maps. This work aims to eliminate the energetic map’s gaps using two Machine Learning (ML) approaches: regression and classification. The proposed ML solution builds upon the synergy between map-information and crowdsourced driving profiles of 4.6 million kilometres of training and test traces. For evaluation, two test-scenarios capture the models’ performance for the analysed problem in two perspectives. First, we evaluate our ML models, followed by the problem-specific energetic evaluation perspective for better interpretability. From the latter, the results indicate energetic map data imputation performs promisingly better when using the regression instead of the classification model.

Keywords: electric mobility; big data; artificial intelligence; supervised machine learning; regression; classification; missing data imputation (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/13/4/982/pdf (application/pdf)
https://www.mdpi.com/1996-1073/13/4/982/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:13:y:2020:i:4:p:982-:d:323920

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().