Computer-implemented method for generating map data with energy consumption predictors, computer-readable storage medium, system for generating map data with energy consumption predictors

Abstract

The invention relates to a computer-implemented method for generating map data (K ') with energy consumption predictors, in particular for use in energy management of electric vehicles (10), a computer-readable storage medium and a system for implementing said method. The method comprises the following steps: a) loading basic map data (K) having a network of road segments (I1, I2, I3, I4, I5); b) performing the following steps for each road section (I1, I2, I3, I4, I5): b1) ascertaining a set (U) of adjacent road sections using the basic map data (K); b2) calculating a transition vector (d12, d13, d14) for each combination of the road sections (I1, I2, I3, I4, I5) and adjacent road sections using the basic map data (K); b3) calculating an energy consumption value (e12, e13, e14) for each transition vector (d12, d13, d14) using the energy consumption prediction model (M), b4) calculating an energy consumption prediction value (e1) for the road section (I1, I2, I3, I4, I5) using the calculated energy consumption values (e12, e13, e14), c) providing map data (K ') having a network of the road sections (I1, I2, I3, I4, I5) and the associated energy consumption prediction value (e1).

Description

Technical Field

[0001] The present invention relates to a computer-implemented method for generating map data with energy consumption prediction values, in particular for use in energy management of electric vehicles. The present invention also relates to a computer-readable storage medium and a system for implementing the method. Background Art

[0002] Electric vehicles, particularly battery-electric vehicles, are considered a significant contribution to the transformation of transportation and are now indispensable for modern mobility. Compared to vehicles with conventional internal combustion engines, battery-electric vehicles are driven by an electric motor powered by a battery. Therefore, the battery must be regularly charged. Typically, the vehicle's kinetic energy is also used to recirculate energy back into the battery during downhill driving or braking.

[0003] Various factors influence the capacity of batteries installed in electric vehicles. A crucial influencing factor is temperature. Batteries typically operate within a temperature range where their capacity is maximum, as electrochemical processes operate optimally. This temperature range can be, for example, between 20 and 40 degrees Celsius. Operating the battery outside the preferred temperature range can result in a reduced range for the electric vehicle, as the battery no longer has its full capacity. Furthermore, battery wear can occur, resulting in a gradual decrease (degradation) in battery capacity.

[0004] In order to counteract the aforementioned problems (degradation, reduction in range), solutions are known, for example, which heat the battery before driving so that the battery reaches its preferred temperature range at the start of driving. Summary of the Invention

[0005] The object of the present invention is to reduce the degradation of batteries of electric vehicles.

[0006] This object is achieved by a computer-implemented method according to claim 1 .

[0007] In particular, the object is achieved by a computer-implemented method for generating map data with energy consumption prediction values. The method or the generated map data can be used, in particular, for energy management of electric vehicles. The method comprises the following steps:

[0008] a) loading basic map data, wherein the basic map data has a network consisting of road segments;

[0009] b) Perform the following steps for each road segment:

[0010] b1) determining a set of adjacent road sections using basic map data;

[0011] b2) calculating a transition vector for each combination of the road segment and an adjacent road segment using basic map data;

[0012] b3) calculating an energy consumption value for each transition vector when applying the energy consumption prediction model;

[0013] b4) calculating a predicted energy consumption value for the road section by applying the calculated energy consumption value;

[0014] c) Providing map data having a network consisting of individual road sections and associated energy consumption forecast values.

[0015] Within the scope of the present invention, a network of road segments is understood to be a data structure that describes a collection of interconnected road segments. Such a data structure can be, for example, a directionality map. The basic map data can therefore be, in particular, digital map data, such as is commonly used for vehicle navigation. In addition to the network of road segments, such map data typically includes additional information for each road segment, such as its length, maximum permitted speed, road type, etc.

[0016] The concept of the present invention is to predict the energy demand of electric vehicles according to the respective road sections. Regarding degradation, a high power demand can be considered critical, especially if the battery is outside the preferred temperature range, for example when starting the vehicle in winter. Such a high power demand can be caused, for example, by strong acceleration, high speeds, or uphill driving.

[0017] According to the described method, each road segment is evaluated in the context of the surrounding road segments, and this overall consideration derives an energy consumption forecast for that road segment. This is based on the idea that the power demand of an electric vehicle on a current road segment can be influenced by the subsequent road segment. For example, at a highway entrance (the current road segment), a high power demand is expected because the driver accelerates the vehicle to a high speed that is suitable or permitted for the highway (the subsequent road segment). Conversely, at a highway exit, for example, only a low power demand or even energy recuperation can be expected because the vehicle is braked from a high speed and, if necessary, energy can be recovered through recuperation.

[0018] Generally, this approach is reflected in the method according to the invention by method steps b1) to b4), which are carried out separately for each individual road section.

[0019] To this end, according to step b1), a set of adjacent road segments is determined for the road segment under consideration using the base map data. Adjacent road segments are road segments in the base map data that are located in the vicinity of the road segment under consideration (e.g., directly preceding / following the road segment under consideration).

[0020] In step b2), a transition vector is then calculated for each combination of the road segment under consideration and its adjacent road segments. A transition vector can describe the change in relevant parameters (such as maximum speed or gradient) that occurs at the transition between the road segment under consideration and an adjacent road segment. The parameter values for each road segment are stored in the basic map data. This results in a set of transition vectors that describe the parameter change for each possible transition from the road segment to its adjacent road segment (or vice versa).

[0021] In step b3), an energy consumption value is determined for each considered transition vector, using an energy consumption prediction model. The calculated energy consumption value describes the expected energy consumption of the vehicle assuming that the vehicle travels from the selected road segment to an adjacent road segment or from an adjacent road segment to the selected road segment.

[0022] In step b4), an energy consumption forecast for the selected road section is calculated using the calculated energy consumption values. For example, one of the energy consumption values calculated in step b3) can be selected for this purpose, for example the highest one (for worst-case estimation).

[0023] Finally, the method provides map data containing the calculated energy consumption prediction value for each road segment. In particular, map data can be created based on basic map data, containing the calculated energy consumption prediction value as an additional attribute for each road segment. In this case, the provided map data can be understood as labeled (tagged) text of the basic map.

[0024] The method thus enables the generation of map data containing precise information about the power demand to be expected on each road section. This information can be used in the energy management of the electric vehicle to select an operating strategy that is suitable and efficient for the electric vehicle. For example, battery preheating can be performed (only) if a high power demand is expected on a road section that the electric vehicle (quickly) reaches after the starting process. This improves the energy efficiency of the electric vehicle.

[0025] In one embodiment, the set of adjacent road segments may include all road segments directly connected to the road segment. In this case, the adjacent road segments of the considered road segment may be considered as its immediate predecessor or successor in the network of road segments.

[0026] The definition of adjacent road sections as directly preceding / following based on this embodiment has proven in practical tests to be particularly suitable for generating precise energy consumption predictions.

[0027] Alternatively, the set of adjacent road segments can also include all road segments that are connected to the road segment via at least one further road segment. In this embodiment, the adjacent relationship is thus extended to indirectly connected road segments.

[0028] In another embodiment, the base map may include one or more of the following values for at least some of the road segments: speed limit, road type, gradient, length. Preferably, the base map data includes all of the aforementioned parameters for all road segments. This allows for the most comprehensive mapping of parameters relevant to the energy consumption of electric vehicles into the transition vectors.

[0029] In another specific embodiment, the transition vector may have one or more of the following values: a difference in speed limits, a change in road type, a gradient difference.

[0030] As already explained above, extensive modeling of the different parameters or their changes at the transitions between individual road sections contributes to the quality of the generated energy consumption prediction values.

[0031] In one embodiment, the energy consumption prediction model may include at least one regression model, which contains a mapping rule from transition vectors to energy consumption values.

[0032] In a simple implementation, the regression model can be given by a function which weights the components of the input transition vector and determines the energy consumption value from the weighted sum.

[0033] In particular, the regression model can be a trained model, for example a trained neural network. As training data, data records can be used that describe the actual energy requirements of electric vehicles on the corresponding road sections.

[0034] In one embodiment, the regression model may include at least one decision tree, preferably a random forest of decision trees.

[0035] The method and the energy consumption prediction model may implement regression according to a random forest method, wherein regression is performed based on a plurality of uncorrelated decision trees that are randomly grown during a training process.

[0036] The application of the random forest approach has been shown to have excellent performance in the present invention and offers the advantage of high-quality regression even with a small amount of training data.

[0037] In another embodiment, the energy consumption prediction value for the road section in step b4) corresponds to the maximum of the energy consumption values calculated in step b3). This means that the energy consumption prediction value for the road section is defined as the maximum energy consumption value that results from considering all possible combinations of the road section and its adjacent road sections.

[0038] The described embodiment results in a worst-case estimation, in which each road segment is assigned the maximum possible energy consumption resulting from a transition from or to a single adjacent road segment, regardless of how probable that transition is. Such a worst-case estimation can be useful, for example, in selecting an operating strategy for an electric vehicle that aims to prevent battery degradation.

[0039] In an alternative embodiment, the energy consumption forecast value determined in step b4) corresponds to a weighted average of the energy consumption values calculated in step b3). The weighting can, for example, represent the (statistical) probability that an electric vehicle will travel the corresponding transition of the road section.

[0040] This alternative embodiment allows for a more precise estimation of the energy consumption to be predicted.

[0041] In another embodiment, the method may further include the following steps:

[0042] d) Find out the GPS location of the electric vehicle;

[0043] e) determining a reference energy consumption forecast value, in particular a maximum reference energy consumption forecast value, in the environment of the electric vehicle according to the GPS location using map data;

[0044] According to this embodiment, the generated map data is used to determine a reference value for the energy consumption of the electric vehicle, which is expected in the electric vehicle's (current) environment. In particular, the reference value can be a predicted maximum energy consumption value for all road sections in the environment, used for worst-case estimation. This embodiment is based in particular on the understanding that the maximum power demand shortly after the start of the electric vehicle can accelerate battery degradation at low temperatures.

[0045] To determine the environment, the GPS location of the electric vehicle is first determined, for example by means of a GPS sensor integrated in the vehicle.

[0046] The vehicle's surroundings may be understood to be a set of road segments that are expected to be reachable within a short time and / or a short distance, triggered by the vehicle's current GPS position.

[0047] The environment can be understood, for example, as a collection of road segments within a predetermined radius from the electric vehicle's GPS location. The predetermined radius can be, for example, 5 kilometers. Alternatively, the environment can include all road segments that can be reached within a predetermined time (e.g., 10 minutes) after the electric vehicle starts. Furthermore, the environment can be defined based on a predetermined navigation objective.

[0048] In another embodiment, the method may further include the following steps:

[0049] f) Adapting an energy management configuration of the electric vehicle based on the reference energy consumption prediction value, in particular for preheating a battery of the electric vehicle.

[0050] The energy management configuration of the electric vehicle can, for example, control whether a preheating process of the battery of the electric vehicle is carried out before driving begins, possibly as a function of the external temperature.

[0051] A preheating process can be initiated based on the reference energy consumption prediction value, for example if the reference energy consumption prediction value exceeds a threshold value. In addition, further parameters can be taken into account, such as the current state of charge of the battery, the external temperature, the age of the battery, and the like.

[0052] In this embodiment, it is therefore possible, particularly in conjunction with the preceding embodiments, to use the generated energy consumption forecasts in the energy management of the electric vehicle in order to adapt its operating strategy accordingly. This improves the energy efficiency of the electric vehicle and can prevent the problems mentioned above, such as degradation and reduced range.

[0053] The object is furthermore achieved by a computer-readable storage medium comprising instructions which, when executed by at least one processor, cause the at least one processor to implement the method described above.

[0054] Similar advantages and technical effects result with respect to the computer-readable storage medium as those described in conjunction with the method according to the invention.

[0055] The object is further achieved by a system for generating map data with energy consumption prediction values, in particular for use in energy management of electric vehicles. The system has the following features:

[0056] at least one memory containing an energy consumption prediction model and / or basic map data, the basic map data having a network consisting of road segments;

[0057] - A back-end computing device, configured to perform the following steps:

[0058] a) Load basic map data;

[0059] b) Perform the following steps for each road segment:

[0060] b1) determining a set of adjacent road sections using basic map data;

[0061] b2) calculating a transition vector for each combination of the road segment and an adjacent road segment using basic map data;

[0062] b3) calculating an energy consumption value for each transition vector when applying the energy consumption prediction model;

[0063] b4) calculating a predicted energy consumption value for the road section by applying the calculated energy consumption value;

[0064] c) Providing map data having a network consisting of individual road sections and associated energy consumption forecast values.

[0065] Similar advantages and technical effects result with respect to the system as described in connection with the method according to the invention.

[0066] In one embodiment, the system may further include an electric vehicle having the following:

[0067] -GPS sensor;

[0068] -communication devices; and

[0069] -Vehicle computing device.

[0070] Here, the vehicle computing device is configured to:

[0071] - determining the position of the electric vehicle with the aid of a GPS sensor;

[0072] - transmitting the position to a back-end computing device by means of a communication device;

[0073] - Receive a reference energy consumption prediction value from a back-end computing device via a communication device.

[0074] Here, the backend computing device is further configured to determine the reference energy consumption prediction value based on the position and map data and transmit it to the communication device.

[0075] In particular, the reference energy consumption prediction value may be a maximum energy consumption prediction value of a road section that is located in the environment of the location of the vehicle.

[0076] In one embodiment, the electric vehicle may further include:

[0077] - Energy management devices; and

[0078] - A heating device for heating the battery of an electric vehicle.

[0079] Here, the energy management device is configured to control a heating device according to the reference energy consumption forecast value. Alternatively or additionally, a cooling device, such as a ventilator or air conditioning unit, may also be controlled, for example activated, according to the reference energy consumption forecast value.

[0080] This embodiment of the system results in similar advantages and technical effects as those already described in conjunction with the corresponding embodiment of the method.

[0081] It goes without saying that the features described with respect to the method according to the present invention and the advantages achievable thereby can be applied or transferred to the apparatus according to the present invention, and vice versa. Specifically, within the context of this description of the present invention, the components of the apparatus are designed to carry out the individual method steps according to the present invention. Similarly, the functions of the aforementioned components of the apparatus according to the present invention can be used as method steps of the method according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The present invention will be described below based on various embodiments, which will be explained in more detail with reference to the accompanying drawings.

[0083] Figure 1a shows basic map data according to one embodiment;

[0084] Figure 1b Shown in Figure 1a In the embodiment of , a set of adjacent road segments;

[0085] Figure 2 A flow chart showing a method according to one embodiment;

[0086] Figure 3 A system according to one embodiment is shown. DETAILED DESCRIPTION

[0087] In the following description, the same reference numerals are used for identical and identically acting parts.

[0088] Figure 1a A graphical representation of basic map data K according to one exemplary embodiment is shown.

[0089] Basic map data K includes five road sections I1, I2, I3, I4, and I5. Road sections I1, I2, I3, I4, and I5 extend in different directions and form a common intersection. Road section I4 is the entrance to the highway corresponding to road section I5.

[0090] Furthermore, the basic map data contain speed limits v1, v2, v3, v4 for the road sections I1, I2, I3 and I4, respectively:

[0091] - On road section I1 the speed limit v1 (=50 km / h) applies.

[0092] - On road section I2 the speed limit v2 (=30 km / h) applies.

[0093] - On road section I3 the speed limit v3 (=40 km / h) applies.

[0094] - On road section I4, speed limit v4 (=90 km / h) applies.

[0095] Figure 1b Show Figure 1a , for illustrating the adjacent road sections of the road section I1.

[0096] Road section I1 is connected to road sections I2, I3, and I4. A vehicle approaching the common intersection of road sections I1, I2, I3, and I4 on road section I1 can drive onto road section I2 by turning left, drive straight onto road section I4 and thus toward highway 15, or drive onto road section I3 by turning right.

[0097] Each of the road sections I2, I3, I4 is therefore connected to the directly subsequent road section of the road section I1. For the road section I1, the set U of adjacent road sections is therefore

[0098] U = {12, 13, 14}.

[0099] exist Figure 2 The process of the method according to one embodiment is shown in FIG. Figure 1a and 1b Example of .

[0100] In step a), basic map data K are loaded, which have the network of road sections I1 to I5 and the corresponding speed limits v1 to v4 as additional information (see Figure 1a ).

[0101] In step S2, any of the road sections I1 to I5 for which an energy consumption forecast has not yet been calculated is selected. To this end, the road sections still to be processed can be managed in a suitable data structure, such as a stack. According to this exemplary embodiment, it is assumed that road section I1 is selected. The subsequent steps S21, S22, S23, and S24 relate to the road section I1 selected in step S2.

[0102] In step S21, the set U of adjacent road segments of the road segment I1 is found. Figure 1b , it is shown that the set U in this exemplary embodiment contains precisely the road sections I2 , I3 , I4 .

[0103] In step S22, transition vectors d12, d13, d14 are calculated for each combination of the selected road segment I1 and its adjacent road segments I2, I3, and I4, i.e., for the combinations {I1, I2}, {I1, I3}, and {I1, I4}. Each component of the transition vectors d12, d13, d14 contains the difference in speed limits for the corresponding road segment.

[0104] The transition vector d14 (for the combination of road sections {I1, I4}) thus contains, for example, the following speed limit differences:

[0105] v4 – v1 = 90 km / h – 50 km / h = 40 km / h.

[0106] The corresponding transition vector is thus given by d14=(40 km / h).

[0107] The additional transition vectors d12 (combination {I1, I2}) and d13 (transition {I1, I3}) can be given by:

[0108] d12 = (v2 – v1) = (30 km / h – 50 km / h) = (-20 km / h); and

[0109] d13 = (v3 – v1) = (50 km / h – 50 km / h) = (0 km / h).

[0110] In step S23, an energy consumption prediction value e12, e13, e14 is determined for each of the previously calculated transition vectors d12, d13, d14 using the energy consumption prediction model, for example in joules per meter (J / m). The following values are assumed for this embodiment:

[0111] e12 = 50 J / m;

[0112] e13 = 1000 J / m; and

[0113] e14 = 3000 J / m.

[0114] These values correspond to the expected energy consumption values for the vehicle traveling from road section I1 to the corresponding subsequent road section, under the corresponding assumptions. The lowest energy consumption value occurs for transition I1-I2 because the vehicle brakes as expected, at least not accelerating, when changing from a road section with a permitted maximum speed of 50 km / h to a road section with a permitted maximum speed of 30 km / h. On the other hand, the highest energy consumption value occurs for transition I1-I4 because the vehicle accelerates as expected to reach the higher permitted maximum speed (90 km / h instead of 50 km / h).

[0115] In step S24, the energy consumption prediction value e1 for the road section I1 is calculated or selected. In this embodiment, the maximum of the previously calculated energy consumption values is selected. The energy consumption prediction value e1 for the road section I1 thus corresponds to:

[0116] e1 = max {e12, e13, e14} = e14 = 3000 J / m.

[0117] This corresponds to the assumption of the maximum possible energy consumption to be expected, ie the assumption that the vehicle changes from the road section I1 to the road section I4 .

[0118] This concludes the calculation of the energy consumption prediction value e1 for the road section I1 selected in step S2 .

[0119] In step S25 , it is checked whether there are still road sections for which no energy consumption forecast value is to be calculated. In this case, the method is continued in step S2 , otherwise it is continued in step S3 .

[0120] In step S3 , the calculated energy consumption prediction values are extended for the basic map data, in particular for the road section I1 by an energy consumption prediction value e1=3000 J / m. The extended basic map data are provided as map data K′.

[0121] Figure 3 One embodiment of a system according to the present invention is shown.

[0122] The system includes an electric vehicle 10 having the following components:

[0123] - a battery 11 for driving the electric vehicle 10;

[0124] - a heating device 13 for preheating the battery 11;

[0125] - Energy management device 12;

[0126] - On-board computer 14;

[0127] - GPS sensor 15; and

[0128] - A mobile radio communication device 16.

[0129] This exemplary embodiment assumes that components 12 to 16 of vehicle 10 can communicate via a common bus 18 .

[0130] The energy management device 12 is designed to carry out a preheating process of the battery 11 by means of a heating device 13 .

[0131] The system further comprises a backend computing device 21, which is in communication with two databases 22 and 23. The database 22 contains a trained energy consumption prediction model. The database 23 contains basic map data and / or map data with energy consumption prediction values, which are generated by the backend computing device, such as in combination with the energy consumption prediction model. Figure 2 The embodiments have been described.

[0132] The system shown is designed to carry out the method. In particular, it is possible in the system to operate a proactive energy management for the electric vehicle 10 by taking into account the calculated energy consumption forecast.

[0133] In particular, the onboard computer 16 is configured to detect the GPS location of the electric vehicle 10 using the GPS sensor 15 and transmit it to the backend computing device 21 using the mobile radio communication device 16. Based on the received GPS location, the backend computing device 21 can determine a reference energy consumption prediction value using map data and send it back to the vehicle. As described in conjunction with the method, this can, for example, be the maximum energy consumption prediction value within a 5-kilometer radius of the GPS location. The onboard computer 14 is configured to provide the received reference energy consumption value to the energy management device 12. The energy management device 12 is configured to preheat the battery 11 using the heating device 13 if the received reference energy consumption prediction value exceeds a specific threshold value.

[0134] The above-described exemplary embodiments are shown in a partially simplified manner and are to be understood as examples only. It goes without saying that numerous deviations and modifications are conceivable without departing from the essence of the invention.

[0135] 1 , only directly connected road sections I2 , I3 and I4 are considered as adjacent road sections of road section I1 . However, under the improved definition, road section I5 can also be considered as an adjacent road section of road section I1 , since both are connected to each other via road section I4 .

[0136] exist Figure 2 In the exemplary embodiment, the properties of the road segment or change vector are limited to speed values for simplicity. For comprehensive energy consumption prediction, it is naturally advantageous to consider additional properties (such as slope, road type, etc.). In this case, the change vector accordingly has multiple components, for which other types of regression or classification can be specified by the prediction model.

[0137] exist Figure 3 In the example, the vehicle components are connected to a common vehicle bus—for the sake of simplicity. Naturally, these components can also communicate via different bus systems or other means, as long as the vehicle computing device can access the corresponding data. Databases 22 and 23 can also be combined in a single database or memory.

[0138] It should be noted that all of the above-described features, individually and in combination or in each subcombination, can be considered as independent embodiments or developments of the present invention, as defined in particular in the introduction to the description and in the claims. Deviations from this are possible. In particular, it should be noted that the terms particularly or parentheses do not indicate mandatory features in the respective context.

[0139] Reference Signs List

[0140] 10 Electric vehicles

[0141] 11 batteries

[0142] 12Energy management device

[0143] 13 Heating device

[0144] 14 Onboard Computer

[0145] 15GPS sensor

[0146] 16 Mobile radio communication devices

[0147] 18 buses

[0148] 21 Backend computing device

[0149] 22, 23 database

[0150] K Basic map data

[0151] K'map data

[0152] d12, d13, d14 transition vectors

[0153] Energy consumption values of e12, e13, and e14

[0154] e1 energy consumption value (for road section I1)

[0155] I1, I2, I3, I4, I5 road sections

[0156] v1, v2, v3, v4 speed limits

[0157] U The set of adjacent road segments

[0158] S1 loads basic map data

[0159] S2 Select road section

[0160] S21 Identify adjacent road sections

[0161] S22 calculates the transition vector

[0162] S23 calculates energy consumption

[0163] S24 calculates energy consumption forecast value

[0164] S25 checks unprocessed road sections

[0165] S3: Provides map data

Claims

1. A computer-implemented method for generating map data (K') with energy consumption prediction values, in particular for use in energy management of electric vehicles (10), wherein: The method comprises the following steps: a) loading basic map data (K), the basic map data having a network consisting of road segments (I1, I2, I3, I4, I5); b) Perform the following steps for each road segment (I1, I2, I3, I4, I5): b1) determining a set (U) of adjacent road sections using basic map data (K); b2) calculating a transition vector (d12, d13, d14) for each combination of the road segment (I1, I2, I3, I4, I5) and an adjacent road segment using basic map data (K); b3) calculating an energy consumption value (e12, e13, e14) for each transition vector (d12, d13, d14) by applying the energy consumption prediction model (M); b4) calculating a predicted energy consumption value (e1) for the road section (I1, I2, I3, I4, I5) by applying the calculated energy consumption values (e12, e13, e14); c) providing map data (K′) comprising a network of road sections ( I1 , I2 , I3 , I4 , I5 ) and associated energy consumption prediction values ( e1 ).

2. The computer-implemented method of claim 1 , wherein: The set (U) of adjacent road segments includes all road segments (I1, I2, I3, I4, I5) that are directly connected to the road segment (I1, I2, I3, I4, I5).

3. The computer-implemented method according to any one of the preceding claims, wherein: The set (U) of adjacent road segments includes all road segments (I1, I2, I3, I4, I5) connected to the road segment (I1, I2, I3, I4, I5) via at least one further road segment (I1, I2, I3, I4, I5).

4. The computer-implemented method according to any one of the preceding claims, wherein: The basic map (K) has, for at least some of the road sections (I1, I2, I3, I4, I5), one or more of the following values: speed limit (v1, v2, v3, v4), road type, gradient, length.

5. The computer-implemented method according to any one of the preceding claims, wherein: The transition vector (d12, d13, d14) has one or more of the following values: a difference in the speed limits (v1, v2, v3, v4), a change in road type, a gradient difference.

6. The computer-implemented method according to any one of the preceding claims, wherein: The energy consumption prediction model (M) has at least one regression model, in particular a trained regression model, which contains a mapping rule from transition vectors (d12, d13, d14) to energy consumption values (e12, e13, e14).

7. The computer-implemented method according to claim 6 , wherein: The at least one regression model has at least one decision tree, preferably a random forest.

8. The computer-implemented method according to any one of the preceding claims, wherein: In step b4), the predicted energy consumption value (e1) of the road section (I1, I2, I3, I4, I5) corresponds to the maximum of the energy consumption values (e12, e13, e14) calculated in step b3).

9. The computer-implemented method according to any one of the preceding claims, wherein: The method further comprises the steps of: d) finding the GPS location of the electric vehicle (10); e) Using the map data (K'), determining a reference energy consumption prediction value, in particular a maximum reference energy consumption prediction value, in the surroundings of the electric vehicle (10) according to the GPS location.

10. The computer-implemented method according to claim 9, wherein: The method further comprises the steps of: f) Adapting the energy management configuration of the electric vehicle (10) based on the reference energy consumption prediction value (e1), in particular for preheating the battery (11) of the electric vehicle (10).

11. A computer-readable storage medium comprising instructions which, when executed by at least one processor, cause the at least one processor to implement the method according to one of the preceding claims.

12. System for generating map data (K') with energy consumption prediction values, in particular for use in energy management of electric vehicles (10), wherein: The system has the following features: - at least one memory (22, 23), containing an energy consumption prediction model (M) and / or basic map data (K), the basic map data having a network consisting of road segments (I1, I2, I3, I4, I5); - a back-end computing device (21), the back-end computing device being configured to perform the following steps: a) Load basic map data (K); b) Perform the following steps for each road segment (I1, I2, I3, I4, I5): b1) determining a set (U) of adjacent road sections using basic map data (K); b2) calculating a transition vector (d12, d13, d14) for each combination of the road segment (I1, I2, I3, I4, I5) and an adjacent road segment using basic map data (K); b3) calculating an energy consumption value (e12, e13, e14) for each transition vector (d12, d13, d14) by applying the energy consumption prediction model (M); b4) calculating a predicted energy consumption value (e1) for the road section (11, 12, 13, 14, 15) by applying the calculated energy consumption values (e12, e13, e14); c) providing map data (K′) comprising a network of road sections ( I1 , I2 , I3 , I4 , I5 ) and associated energy consumption prediction values ( e1 ).

13. The system according to claim 12, wherein: The system further comprises an electric vehicle (10) having the following: -GPS sensor (15); -communication means (16); and -Vehicle computing device (14); Wherein, the vehicle computing device (14) is configured to - determining the position of the electric vehicle with the aid of a GPS sensor (15); - transmitting the position to the back-end computing device (21) by means of the communication device (16); - receiving a reference energy consumption prediction value (e1) from a back-end computing device (16) by means of a communication device (16); and The back-end computing device (21) is further configured to determine the reference energy consumption prediction value (e1) based on the position and the map data (K') and transmit it to the communication device (16).

14. System according to one of the preceding claims, in particular according to claim 13, wherein The electric vehicle (10) further comprises the following: - Energy management device (12); and - a heating device (13) for heating a battery (11) of an electric vehicle (10), The energy management device (12) is configured to control the heating device (13) according to the reference energy consumption prediction value (e1).

Images