Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information
This paper presents a novel approach to distinguishing driving styles with respect to their energy efficiency. A distinct property of our method is that it relies exclusively on the global positioning system (GPS) logs of drivers. This setting is highly relevant in practice as these data can easily...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Modelling |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-3951/3/3/25 |
| _version_ | 1797484411628814336 |
|---|---|
| author | Michael Breuß Ali Sharifi Boroujerdi Ashkan Mansouri Yarahmadi |
| author_facet | Michael Breuß Ali Sharifi Boroujerdi Ashkan Mansouri Yarahmadi |
| author_sort | Michael Breuß |
| collection | DOAJ |
| description | This paper presents a novel approach to distinguishing driving styles with respect to their energy efficiency. A distinct property of our method is that it relies exclusively on the global positioning system (GPS) logs of drivers. This setting is highly relevant in practice as these data can easily be acquired. Relying on positional data alone means that all features derived from them will be correlated, so we strive to find a single quantity that allows us to perform the driving style analysis. To this end we consider a robust variation of the so-called "jerk" of a movement. We give a detailed analysis that shows how the feature relates to a useful model of energy consumption when driving cars. We show that our feature of choice outperforms other more commonly used jerk-based formulations for automated processing. Furthermore, we discuss the handling of noisy, inconsistent, and incomplete data, as this is a notorious problem when dealing with real-world GPS logs. Our solving strategy relies on an agglomerative hierarchical clustering combined with an L-term heuristic to determine the relevant number of clusters. It can easily be implemented and delivers a quick performance, even on very large, real-world datasets. We analyse the clustering procedure, making use of established quality criteria. Experiments show that our approach is robust against noise and able to discern different driving styles. |
| first_indexed | 2024-03-09T23:03:39Z |
| format | Article |
| id | doaj.art-187e70307d304ac9847c0fdc2210032f |
| institution | Directory Open Access Journal |
| issn | 2673-3951 |
| language | English |
| last_indexed | 2024-03-09T23:03:39Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Modelling |
| spelling | doaj.art-187e70307d304ac9847c0fdc2210032f2023-11-23T17:57:07ZengMDPI AGModelling2673-39512022-09-013338539910.3390/modelling3030025Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS InformationMichael Breuß0Ali Sharifi Boroujerdi1Ashkan Mansouri Yarahmadi2BTU Cottbus-Senftenberg, Institute for Mathematics, Platz der Deutschen Einheit 1, 03046 Cottbus, GermanyVolkswagen Infotainment GmbH, 44799 Bochum, GermanyBTU Cottbus-Senftenberg, Institute for Mathematics, Platz der Deutschen Einheit 1, 03046 Cottbus, GermanyThis paper presents a novel approach to distinguishing driving styles with respect to their energy efficiency. A distinct property of our method is that it relies exclusively on the global positioning system (GPS) logs of drivers. This setting is highly relevant in practice as these data can easily be acquired. Relying on positional data alone means that all features derived from them will be correlated, so we strive to find a single quantity that allows us to perform the driving style analysis. To this end we consider a robust variation of the so-called "jerk" of a movement. We give a detailed analysis that shows how the feature relates to a useful model of energy consumption when driving cars. We show that our feature of choice outperforms other more commonly used jerk-based formulations for automated processing. Furthermore, we discuss the handling of noisy, inconsistent, and incomplete data, as this is a notorious problem when dealing with real-world GPS logs. Our solving strategy relies on an agglomerative hierarchical clustering combined with an L-term heuristic to determine the relevant number of clusters. It can easily be implemented and delivers a quick performance, even on very large, real-world datasets. We analyse the clustering procedure, making use of established quality criteria. Experiments show that our approach is robust against noise and able to discern different driving styles.https://www.mdpi.com/2673-3951/3/3/25clusteringenergy efficiencydriving style analysisjerk-based featureGPS data |
| spellingShingle | Michael Breuß Ali Sharifi Boroujerdi Ashkan Mansouri Yarahmadi Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information Modelling clustering energy efficiency driving style analysis jerk-based feature GPS data |
| title | Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information |
| title_full | Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information |
| title_fullStr | Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information |
| title_full_unstemmed | Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information |
| title_short | Modelling the Energy Consumption of Driving Styles Based on Clustering of GPS Information |
| title_sort | modelling the energy consumption of driving styles based on clustering of gps information |
| topic | clustering energy efficiency driving style analysis jerk-based feature GPS data |
| url | https://www.mdpi.com/2673-3951/3/3/25 |
| work_keys_str_mv | AT michaelbreuß modellingtheenergyconsumptionofdrivingstylesbasedonclusteringofgpsinformation AT alisharifiboroujerdi modellingtheenergyconsumptionofdrivingstylesbasedonclusteringofgpsinformation AT ashkanmansouriyarahmadi modellingtheenergyconsumptionofdrivingstylesbasedonclusteringofgpsinformation |