EP-4737196-A1 - ENERGY CONTROL FOR A CHARGING INFRASTRUCTURE FOR ELECTRIC VEHICLES

EP4737196A1EP 4737196 A1EP4737196 A1EP 4737196A1EP-4737196-A1

Abstract

Summarizing the invention, a computer-implemented method is provided. The computer-implemented method comprises: obtaining a first dataset comprising first charging transaction records relative to a plurality of charging transactions of first electric vehicles that have been charged at one or more charging stations of a charging infrastructure, wherein each first charging transaction record of the first dataset comprises: an initial state of charge of a battery of a respective first electric vehicle, the initial state of charge being recorded at the start of a respective charging transaction of the respective first electric vehicle, and a final state of charge of the battery of the respective first electric vehicle, the final state of charge being recorded at the end of the respective charging transaction of the respective first electric vehicle; - obtaining a second dataset comprising second charging transaction records relative to a plurality of charging transactions of second electric vehicles that have been charged at the one or more charging stations of the charging infrastructure, wherein each second charging transaction record of the second dataset comprises: an initial timestamp indicating the start of a respective charging transaction of a respective second electric vehicle, a final timestamp indicating the end of the respective charging transaction of the respective second electric vehicle, and a total energy provided to a battery of the respective second electric vehicle during the charging transaction; using the first dataset and the second dataset to generate a third dataset relative to the plurality of charging transactions of the second electric vehicles, wherein, for each charging transaction of a respective second electric vehicle, the third dataset comprises at least one of: an estimated used capacity of the battery of the respective second electric vehicle as a function of time for a time interval between the initial timestamp and the final timestamp, and an estimated free capacity of the battery of the respective second electric vehicle as a function of time for a time interval between the initial timestamp and the final timestamp; using the second dataset and the third dataset to predict a number of electric vehicles charging at a given timepoint at the one or more charging stations of the charging infrastructure.

Inventors

SCHERT, Kelaja

Assignees

SAP SE

Dates

Publication Date: 20260506
Application Date: 20241030

Claims (15)

A computer-implemented method comprising: - obtaining a first dataset comprising first charging transaction records relative to a plurality of charging transactions of first electric vehicles that have been charged at one or more charging stations of a charging infrastructure, wherein each first charging transaction record of the first dataset comprises: -- an initial state of charge of a battery of a respective first electric vehicle, the initial state of charge being recorded at the start of a respective charging transaction of the respective first electric vehicle, and -- a final state of charge of the battery of the respective first electric vehicle, the final state of charge being recorded at the end of the respective charging transaction of the respective first electric vehicle; - obtaining a second dataset comprising second charging transaction records relative to a plurality of charging transactions of second electric vehicles that have been charged at the one or more charging stations of the charging infrastructure, wherein each second charging transaction record of the second dataset comprises: -- an initial timestamp indicating the start of a respective charging transaction of a respective second electric vehicle, -- a final timestamp indicating the end of the respective charging transaction of the respective second electric vehicle, and -- a total energy provided to a battery of the respective second electric vehicle during the charging transaction; - using the first dataset and the second dataset to generate a third dataset relative to the plurality of charging transactions of the second electric vehicles, wherein, for each charging transaction of a respective second electric vehicle, the third dataset comprises at least one of: -- an estimated used capacity of the battery of the respective second electric vehicle as a function of time for a time interval between the initial timestamp and the final timestamp, and -- an estimated free capacity of the battery of the respective second electric vehicle as a function of time for a time interval between the initial timestamp and the final timestamp; - using the second dataset and the third dataset to predict a number of electric vehicles charging at a given timepoint at the one or more charging stations of the charging infrastructure.
The computer-implemented method of claim 1, wherein using the first dataset and the second dataset to generate the third dataset comprises: determining, for each charging transaction of the second electric vehicles, an estimated initial state of charge and an estimated final state of charge based on the initial states of charge and the final states of charge of the first charging transaction records.
The computer-implemented method of claim 2, wherein determining the estimated initial state of charge and the estimated final state of charge comprises: - computing an average initial state of charge from the initial states of charge of the first charging transaction records; - computing an average final state of charge from the final states of charge of the first charging transaction records; - setting the estimated initial state of charge to the average initial state of charge; - setting the estimated final state of charge to the average final state of charge.
The computer-implemented method of claim 2 or 3, wherein using the first dataset and the second dataset to generate the third dataset further comprises, for each charging transaction of the second electric vehicles: - computing an estimated state of charge difference between the estimated final state of charge and the estimated initial state of charge; - computing an estimated total capacity of the battery from the estimated state of charge difference and the total energy; - computing an estimated initial used capacity of the battery at the initial timestamp from the estimated total capacity of the battery and the estimated initial state of charge; - computing an estimated final used capacity of the battery at the final timestamp from the estimated total capacity of the battery and the estimated final state of charge.
The computer-implemented method of claim 4, wherein: - computing the estimated total capacity of the battery comprises using the geometrical proportion (estimated state of charge difference) : (100%) = (total energy) : (estimated total capacity); - computing the estimated initial used capacity of the battery comprises using the geometrical proportion (estimated initial state of charge) : (100%) = (estimated initial used capacity) : (estimated total capacity); - computing the estimated final used capacity of the battery comprises using the geometrical proportion (estimated final state of charge) : (100%) = (estimated final used capacity) : (estimated total capacity).
The computer-implemented method of any one of the preceding claims, wherein using the first dataset and the second dataset to generate the third dataset comprises using a mathematical model defining the time dependence of the estimated used capacity of the battery.
The computer-implemented method of claim 6, wherein the mathematical model defines a linear time dependence.
The computer-implemented method of any one of the preceding claims, wherein using the second dataset and the third dataset to predict the number of electric vehicles comprises applying a machine-learning model.
The computer-implemented method of claim 8, wherein using the second dataset and the third dataset to predict the number of electric vehicles comprises: - computing, from the second dataset, a past number of second electric vehicles charging at the one or more charging stations of the charging infrastructure as a function of time over a predetermined time interval; - computing, from the third dataset, a cumulative estimated used capacity as a function of time over the predetermined time interval and/or a cumulative estimated free capacity as a function of time over the predetermined time interval; - providing the past number and at least one of the cumulative estimated used capacity and the cumulative estimated free capacity as input data to the machine-learning model.
The computer-implemented method of any one of the preceding claims, the method further comprising: - using the predicted number of electric vehicles to determine a threshold quantity of energy to be supplied to the charging infrastructure, and - causing at least the threshold quantity of energy to be supplied to the charging infrastructure.
The computer-implemented method of any one of the preceding claims, the method further comprising: - using the predicted number of electric vehicles to control a quantity of energy provided by each charging station of the charging infrastructure.
The computer-implemented method of claim 11, the method further comprising: - detecting an actual number of electric vehicles charging at the one or more charging stations of the charging infrastructure at a later timepoint subsequent to the given timepoint; - using a difference between the predicted number of electric vehicles and the actual number of electric vehicles to adjust the quantity of energy provided by each charging station of the charging infrastructure.
One or more non-transitory computer-readable media storing computerexecutable instructions that, when executed by a computing system, cause the computing system to perform the method of any one of claims 1 to 12.
A computing system comprising at least one processor configured to perform the method of any one of claims 1 to 12.
A system comprising: the computing system of claim 14; and a charging infrastructure comprising one or more charging stations, wherein the one or more charging stations are configured to charge electric vehicles; wherein the computing system is configured to control a quantity of energy provided by and/or to the charging infrastructure during charging transactions of the electric vehicles.

Description

The technical field of the present application relates to battery electric vehicles and relative charging infrastructures. According to a first aspect, a computer-implemented method is provided. The method comprises: obtaining a first dataset comprising first charging transaction records relative to a plurality of charging transactions of first electric vehicles that have been charged at one or more charging stations of a charging infrastructure, wherein each first charging transaction record of the first dataset comprises: -- an initial state of charge of a battery of a respective first electric vehicle, the initial state of charge being recorded at the start of a respective charging transaction of the respective first electric vehicle, and-- a final state of charge of the battery of the respective first electric vehicle, the final state of charge being recorded at the end of the respective charging transaction of the respective first electric vehicle;obtaining a second dataset comprising second charging transaction records relative to a plurality of charging transactions of second electric vehicles that have been charged at the one or more charging stations of the charging infrastructure, wherein each second charging transaction record of the second dataset comprises: -- an initial timestamp indicating the start of a respective charging transaction of a respective second electric vehicle,-- a final timestamp indicating the end of the respective charging transaction of the respective second electric vehicle, and-- a total energy provided to a battery of the respective second electric vehicle during the charging transaction;using the first dataset and the second dataset to generate a third dataset relative to the plurality of charging transactions of the second electric vehicles, wherein, for each charging transaction of a respective second electric vehicle, the third dataset comprises at least one of: -- an estimated used capacity of the battery of the respective second electric vehicle as a function of time for a time interval between the initial timestamp and the final timestamp, and-- an estimated free capacity of the battery of the respective second electric vehicle as a function of time for a time interval between the initial timestamp and the final timestamp;using the second dataset and the third dataset to predict a number of electric vehicles charging at a given timepoint at the one or more charging stations of the charging infrastructure. According to the present disclosure, the computer-implemented method may be carried out by at least one computing device, wherein a computing device may comprise at least one processor. It may further comprise at least one memory or be in communication with at least one memory. A computing device may also comprise one or more input/output units. In the present disclosure, "obtaining a (first/second) dataset" may comprise retrieving the dataset e.g. from the at least one memory of the computing device that carries out the step of obtaining the dataset, from the memory of another computing device, or from another remote data storage (a database, a secondary memory, a cloud storage or the like). Both the first and second datasets comprise charging transactions records. Generally, a charging transaction record comprises data that have been collected in connection with (e.g. during) a charging transaction or charging activity of an electric vehicle. Thus, there may be a one-to-one relation between a charging transaction record and a charging transaction. An electric vehicle is a vehicle propelled by an electric motor; in particular, an electric vehicle may be a battery electric vehicle, i.e. the electric vehicle may comprise a rechargeable battery configured to store energy, which is used to power the electric motor. A charging transaction indicates a charging process in which energy is received by the battery of the electric vehicle. In particular, the charging transaction of the electric vehicle occurs at a charging station of a charging infrastructure. A charging station comprises a device configured to provide electric energy to a rechargeable battery and may further comprise a cable configured to connect said device to the electric vehicle. A charging station may also be referred to as "electric vehicle supply equipment". A charging infrastructure comprises one or more charging stations, in particular a plurality of charging stations. Exemplarily, the charging infrastructure may comprise charging stations within a delimited area. The charging stations of a charging infrastructure may be controlled collectively e.g. by a control module. Alternatively, the charging infrastructure may be distributed and may comprise a plurality of geographically distributed charging stations collectively controlled, e.g., by a control module. The start of a charging transaction, namely the activation of the charging process, is the moment in which energy starts being supplied to the