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.

Recently, individual electric mobility gains significance due to legislation and social discussion. Customers demand longer battery ranges. Advanced planning is a different and more sustainable approach. Potentially, they assist drivers in exploiting the installed range on long journeys. Earlier research of the authors showed that an optimal combination of speed, charging choice and amount potentially reduces overall traveling time on long trips. In this work, a dynamic programming algorithm controls this strategy set time-optimally on an all-electric route from Munich to Verona. For this, location-specific fleet-based data of over 600000 are used to improve the reliability of the strategy set in two ways. Firstly, the data provide more realistic location-and time-specific velocity bounds for speed control. Secondly, they provide fleet-sourced dynamics to a traceable analytical consumption model. These additional dynamics lead to 1.8 -2.3% more energy demand in the strategy planning compared to a less accurate consumption map-based approach. Here, the incorporation of dynamics increases the optimizations’ reliability. Also, the time-dependent fleet-data allows finding an optimal departure time for the given route. In total, the incorporation of fleet information enhances the robustness of the optimization. This enables a more seamless experience of electric mobility on long trips.

More electric vehicles are necessary to reach the goals set by international greenhouse gas legislation. However, low range, long charging time, and a sparse infrastructure compared to fuel-based individual mobility reduce customer acceptance of individual electric mobility. Energetic planning functions as range prediction can ease dealing with those drawbacks. These predictive functions need detailed information on energy demand along the route. To enable this prediction, we present a novel analytical method to energetically represent velocity profiles along a map's link by four parameters. This method has 63 % less error in energetic driving profile representation than other methods. We present a framework to aggregate the four parameters from geolocation records provided by a fleet of different vehicles. We analyze this framework concerning the energetic error introduced to range estimation. The analysis shows that the errors of the framework are lower or of equal magnitude than the ones introduced to range estimation by recent residual high-voltage-battery energy estimation algorithms. A precise route energy demand prediction based on the presented findings is the basis for a more reliable range prediction. This prediction will help to increase the acceptance of individual electric mobility.

The degree of electrification of vehicle powertrains rose significantly in the last years. For fully electric vehicles particularly longer trips are a problem because of limited range, the necessity to charge and consequently higher travel time. Thus, accurate data on energy consumption, driving and charging options and corresponding routing are critical for long trips. This requires innovations that foster the popularity of battery electric vehicles (BEVs). A combined strategy including route, charging and velocity suggestions can enable seamless use of electric vehicles on long distance trips. Based on a mixed-integer nonlinear program (MINLP) a heuristic approach is shown that calculates route and charger options in heterogeneous networks followed by charging amount and prospective velocities in a time-optimal way. For the comparison of the obtained route-charging-velocity plan, a second dynamic programming (DP) approach is shown. A realistic driving scenario serves for method evaluations. The optimal strategy’s aim is a minimum travel time, assuming a predefined final state of charge (SOC). The discussion evaluates both approaches concerning computing time and the obtained results, particularly velocity and charging time. The methods’ real-time applicability is shown by calculating optimal strategies.