Energetic Map Data Imputation: A Machine Learning Approach

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.

[1]  Frank Gauterin,et al.  Influence of Measurement and Prediction Uncertainties on Range Estimation for Electric Vehicles , 2018, IEEE Transactions on Intelligent Transportation Systems.

[2]  Leonardo Franco,et al.  Missing data imputation using statistical and machine learning methods in a real breast cancer problem , 2010, Artif. Intell. Medicine.

[3]  Tshilidzi Marwala,et al.  Modeling of missing data prediction: Computational intelligence and optimization algorithms , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[4]  Q. Yan,et al.  Research on Real Purchasing Behavior Analysis of Electric Cars in Beijing Based on Structural Equation Modeling and Multinomial Logit Model , 2019, Sustainability.

[5]  Ivan Glesk,et al.  Machine learning for estimation of building energy consumption and performance: a review , 2018, Visualization in Engineering.

[6]  Markus Lienkamp,et al.  Range Prediction for EVs via Crowd-Sourcing , 2014, 2014 IEEE Vehicle Power and Propulsion Conference (VPPC).

[7]  Kristin L. Sainani,et al.  Dealing with missing data , 2002 .

[8]  Michael E. Theologou,et al.  Machine-learning methodology for energy efficient routing , 2012 .

[9]  Lifeng Wu,et al.  Empirical and machine learning models for predicting daily global solar radiation from sunshine duration: A review and case study in China , 2019, Renewable and Sustainable Energy Reviews.

[10]  Javier Del Ser,et al.  On the imputation of missing data for road traffic forecasting: New insights and novel techniques , 2018 .

[11]  Li-Der Chou,et al.  Electric-Vehicle Navigation System Based on Power Consumption , 2016, IEEE Transactions on Vehicular Technology.

[12]  S. Seo A Review and Comparison of Methods for Detecting Outliers in Univariate Data Sets , 2006 .

[13]  Kashem M. Muttaqi,et al.  A Real-Time Range Indicator for EVs Using Web-Based Environmental Data and Sensorless Estimation of Regenerative Braking Power , 2018, IEEE Transactions on Vehicular Technology.

[14]  Yanyun Zhao,et al.  Imputation of missing data using ensemble algorithms , 2011, 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[15]  Michael E. Theologou,et al.  Mesoscopic forecasting of vehicular consumption using neural networks , 2015, Soft Comput..

[16]  John Krumm,et al.  Hidden Markov map matching through noise and sparseness , 2009, GIS.

[17]  J. Fox,et al.  Applied Regression Analysis and Generalized Linear Models , 2008 .

[18]  Phil Blythe,et al.  Use of ITS to overcome barriers to the introduction of electric vehicles in the North East of England , 2012 .

[19]  Tariq Samad,et al.  Imputation of Missing Data in Industrial Databases , 1999, Applied Intelligence.

[20]  Kristen A. Severson,et al.  Data-driven prediction of battery cycle life before capacity degradation , 2019, Nature Energy.

[21]  Ling-Jyh Chen,et al.  Missing data handling for meter data management system , 2013, e-Energy '13.

[22]  Joeri Van Mierlo,et al.  A Model for Range Estimation and Energy-Efficient Routing of Electric Vehicles in Real-World Conditions , 2020, IEEE Transactions on Intelligent Transportation Systems.

[23]  Gilles Louppe,et al.  Independent consultant , 2013 .

[24]  Noel A. Card,et al.  Best practices for missing data management in counseling psychology. , 2010, Journal of counseling psychology.

[25]  Guoyuan Wu,et al.  Data-driven decomposition analysis and estimation of link-level electric vehicle energy consumption under real-world traffic conditions , 2017, Transportation Research Part D: Transport and Environment.

[26]  M. Braga,et al.  Exploratory Data Analysis , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[27]  S.塞尔朔普 Predicting an energy consumption of a vehicle , 2014 .

[28]  Henk Nijmeijer,et al.  Battery electric vehicle energy consumption prediction for a trip based on route information , 2018 .