Method and system for predicting the electrical consumption of an electric vehicle for completing a journey.

Abstract

The present invention relates to a method and a system for predicting the electrical consumption of an electric vehicle, referred to as the first vehicle in a set of electric vehicles, based on a global model for predicting the electrical consumption of an electric vehicle per trip and said data relating to the first trip obtained (34),said global model for predicting electric vehicle power consumption per trip being obtained (31) from actual power consumption of at least one electric vehicle from the set of electric vehicles following trips made by said at least one electric vehicle from the set of electric vehicles and from local models for predicting electric vehicle power consumption per trip trained from data relating to trips made by an electric vehicle from the set of electric vehicles following trips made by a device of said electric vehicle from the set of electric vehicles. Figure for the abstract: Figure 4,

Description

Title of the invention: Method and system for predicting the electrical consumption of an electric vehicle for completing a journey. technical field

[0001] The present invention relates to predicting the electrical consumption of an electric vehicle. In particular, the present invention relates to a method and a system for predicting the electrical consumption of an electric vehicle for completing a journey. Technological background

[0002] Current vehicles include navigation systems that allow a vehicle driver to enter a destination via a human-machine interface of such systems.

[0003] Once a user has entered a destination, the navigation systems provide a route to follow from the location of that vehicle to that destination, taking into account traffic conditions.

[0004] To reach the destination, the user must ensure that the vehicle's energy resources are sufficient. When the vehicle is powered by fossil fuels, the driver simply needs to ensure that the vehicle's fuel tank is sufficiently full.

[0005] However, for electric vehicle users, checking the battery charge level may not be sufficient. Indeed, even if the battery charge level appears sufficient for a trip, the user does not know the battery's condition, and the charge level could very well drop suddenly during the journey if the battery is in poor condition. Furthermore, battery discharge depends on the conditions in which it is located, i.e., the weather conditions along the route.

[0006] The problem solved by the present invention is to improve current navigation systems in order to reassure an electric vehicle driver that his vehicle's battery is sufficiently charged to complete a journey.

[0007] Summary of the present invention

[0008] One object of the present invention is to solve at least one of the problems of the technological background described above.

[0009] Another object of the present invention is to provide an estimate of the electrical consumption of an electric vehicle to complete a journey.

[0010] Another object of the present invention is to prevent battery failures in electric vehicles.

[0011] According to a first aspect, the present invention relates to a method for predicting the electrical consumption of an electric vehicle, referred to as the first vehicle of a set of electric vehicles, for completing a journey, referred to as the first journey, said method comprising the following steps: - obtaining, by a central device, a global model for predicting the electrical consumption of an electric vehicle per trip from local models for predicting the electrical consumption of an electric vehicle per trip and from actual electrical consumption of at least one electric vehicle from the set of electric vehicles following trips made by said at least one electric vehicle from the set of electric vehicles, each local model for predicting the electrical consumption of an electric vehicle per trip being trained from data relating to trips made by an electric vehicle from the set of electric vehicles and from actual electrical consumption of said electric vehicle from the set of electric vehicles to make said trips, the device of said electric vehicle from the set of electric vehicles being in communication with the central device; - emission, by the central device, of parameters of the global model for predicting electric vehicle electricity consumption per trip to the device of each electric vehicle in the set of electric vehicles; - obtaining, by the device of the first vehicle, a destination for the first journey to be made by the first electric vehicle; - obtaining, by the device of the first electric vehicle, data relating to the first journey according to said destination obtained; - obtaining, by the device of the first electric vehicle, an estimate of the electrical consumption of the first electric vehicle to carry out the first journey from the global model of prediction of electrical consumption of electric vehicle per journey and the said data relating to the first journey obtained.

[0012] The method is advantageous because it allows a user or an on-board navigation system of an electric vehicle to plan a route for said vehicle based on the estimated battery consumption of their electric vehicle provided by this method. The user can then be confident regarding the electrical resources available for their vehicle to complete a planned route.

[0013] The process makes it possible to preserve the anonymity of the data collected by an electric vehicle because it avoids the transmission of data relating to journeys made by an electric vehicle and of the actual electrical consumption of said electric vehicle to make said journeys via a communication network.

[0014] The method saves bandwidth on the communication network used because only parameters of electric vehicle power consumption prediction models per trip are transmitted between electric vehicles and a central device.

[0015] The method is advantageous because it uses the resources of each electric vehicle to train models for predicting electric vehicle electricity consumption per trip. The central device simply determines a global model for predicting electric vehicle electricity consumption per trip from said local models for predicting electric vehicle electricity consumption per trip.

[0016] The method is advantageous because it allows for the determination of an update of the global model for predicting electric vehicle electricity consumption per trip based on the local model(s) for predicting electric vehicle electricity consumption per trip trained by a new electric vehicle from the set of electric vehicles.

[0017] According to one variant, the process further comprises the following steps: - obtaining, by the device of the first vehicle, an actual electrical consumption of the first vehicle once the first electric vehicle has completed the first journey; - obtaining a predicted electrical consumption performance value of the first vehicle by calculating a difference between the estimated electrical consumption of the first vehicle to complete the first journey and the actual electrical consumption of the first vehicle once the first electric vehicle has completed the first journey.

[0018] This variant of the method is advantageous because it allows control of the degradation of electrical consumption prediction performance of an electric vehicle as soon as this vehicle is added to the set of electric vehicles.

[0019] According to one variant, the method further comprises a step of updating each local model of electric vehicle power consumption prediction per trip driven by the device of the first electric vehicle from the actual power consumption of the first vehicle once the first electric vehicle has completed the first trip.

[0020] This variant is advantageous because it allows for an update following each local model for predicting the electrical consumption of an electric vehicle per trip driven by an electric vehicle, from the set of electric vehicles following a trip taken by said electric vehicle, which can then launch a local learning phase in order to train said at least one local model for predicting the electrical consumption of an electric vehicle per trip, taking into account taking into account the data relating to said journey and the actual electrical consumption of said vehicle to carry out said journey.

[0021] According to one variant, obtaining the overall model for predicting electric vehicle electricity consumption per trip by the central device comprises the following steps: a) transmission, by the central device, of parameters of an initial local model for predicting the electrical consumption of an electric vehicle per trip to the device of each electric vehicle in the set of electric vehicles; b) learning at least one local model for predicting electric vehicle electricity consumption per trip by the device of at least one electric vehicle from the set of electric vehicles, each local model for predicting electric vehicle electricity consumption per trip is trained by an electric vehicle from the set of electric vehicles from data relating to trips made by said electric vehicle from the set of electric vehicles and from actual electricity consumption of said electric vehicle from the set of electric vehicles following a predetermined number of trips made by said electric vehicle from the set of electric vehicles; (c) emission of the parameters of said at least one local model for predicting electric vehicle power consumption per driven trip to the central device, the parameters of each local model for predicting electric vehicle power consumption per driven trip are emitted by the device of the electric vehicle of the set of electric vehicles which drove said local model for predicting electric vehicle power consumption per driven trip; d) determination by the central device, of the parameters of the global model for predicting electric vehicle electricity consumption per trip from the parameters of said at least one local model for predicting electric vehicle electricity consumption per trip received; e) emission, by the central device and to the device of each electric vehicle in the set of electric vehicles, of the parameters of the global model for predicting electric vehicle electricity consumption per trip obtained and steps b), c) d), and e) are iterated until a stopping condition is met.

[0022] According to one variant, the device of an electric vehicle in the set of vehicles drives a local model for predicting electric vehicle power consumption per trip per initial battery charge level of said electric vehicle in the set of electric vehicles and the central device obtains as many global models for predicting electric vehicle power consumption per trip as there are initial battery charge levels.

[0023] According to a second aspect, the present invention relates to a device comprising a memory associated with a processor configured for the implementation of at least one step of the process according to the first aspect of the present invention.

[0024] According to a third aspect, the present invention relates to an electric vehicle, for example of the automobile type, comprising a device as described above according to the second aspect of the present invention.

[0025] According to a fourth aspect, the present invention relates to a computer program which includes instructions adapted for carrying out the steps of the process according to the first aspect of the present invention, in particular when the computer program is executed by at least one processor.

[0026] Such a computer program may use any programming language, and be in the form of source code, object code, or an intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0027] According to a fifth aspect, the present invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the process according to the first aspect of the present invention.

[0028] On the one hand, the recording medium can be any entity or device capable of storing the program. For example, the medium can include a storage means, such as a ROM, a CD-ROM or a microelectronic circuit-type ROM, or a magnetic recording means or a hard disk drive.

[0029] On the other hand, this recording medium can also be a transmissible medium such as an electrical or optical signal, such a signal being able to be transmitted via an electrical or optical cable, by conventional or radio frequency, by self-directing laser beam, or by other means. The computer program according to the present invention can, in particular, be downloaded from an Internet-type network.

[0030] Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to execute or to be used in the execution of the process in question.

[0031] According to a sixth aspect, the present invention relates to a system for predicting the electrical consumption of an electric vehicle, said first vehicle of a set of electric vehicles comprising a central device in communication with electric vehicles of the set of electric vehicles, characterized in that said central device implements at least one step of the process according to the first aspect of the present invention and each electric vehicle of the set of electric vehicles is an electric vehicle according to the third aspect of the present invention. Brief description of the figures

[0032] Other features and advantages of the present invention will become apparent from the description of the particular and non-limiting embodiments of the present invention below, with reference to the attached Figures 1 to 4, in which:

[0033] [Fig-1] schematically illustrates a consumption prediction system electric of an electric vehicle of a set of electric vehicles, according to a particular and non-limiting embodiment of the present invention;

[0034] [Fig.2] schematically illustrates a device embedded in vehicles electrical [Fig.1], according to a particular and non-limiting embodiment of the present invention;

[0035] [Fig.3] schematically illustrates a central device, according to an example of particular and non-limiting embodiment of the present invention;

[0036] [Fig.4] illustrates a flowchart of the different stages of a prediction process electrical consumption of an electric vehicle, referred to as the first vehicle in a set of electric vehicles, according to a particular and non-limiting embodiment of the present invention.

[0037] Description of examples of implementation

[0038] A method and device for estimating and predicting the electrical consumption of an electric vehicle or a set of electric vehicles will now be described in what follows with joint reference to Figures 1 to 4. The same elements are identified with the same reference symbols throughout the following description.

[0039] [Fig.1] schematically illustrates a system 1 for predicting the electrical consumption of an electric vehicle 101, called the first vehicle, of a set 10 of electric vehicles 101, 102, ..., 101, according to a particular and non-limiting embodiment of the present invention.

[0040] The first vehicle 101 belongs to said set 10 of electric vehicles.

[0041] The set 10 of electric vehicles lOi includes electric vehicles of the same brand, same model and using the same batteries.

[0042] The set 10 of electric vehicles is dynamic, that is to say, new electric vehicles can be added to or removed from the set 10.

[0043] It is subsequently assumed that most of the batteries of the electric vehicles in set 10 function correctly and that if one of them is defective it is then considered as an aberration.

[0044] Each electric vehicle lOi includes a device 2 implementing part of the steps of the process for predicting the electrical consumption of the first electric vehicle 101.

[0045] System 1 also includes a central device 14.

[0046] The central device 14 is located at a distance from the device 2 installed in each vehicle electrical lOi. The central device 14 communicates with a device 2 by means of communication such as an interface element of a block 303 or a communication interface 304 of the central device 14 of [Fig.3] and an interface element of a block 203 or a communication interface 204 of the device 2 of [Fig.2],

[0047] Figure 1 illustrates the example of devices 2 communicating with the central device 14 via a relay antenna 12 of a communication network infrastructure 13. The various elements of the communication network infrastructure used to route a message between the antenna 12 and the central device 14 are illustrated here by a cloud. The communications between the central device 14 and a device 2 are bidirectional, meaning that devices 14 and 2, as well as the elements of the communication network infrastructure 13, are adapted so that the central device 14 can transmit information to a device 2 (downward communication) and receive information transmitted by a device 2 (upward communication).

[0048] [Fig.2] schematically illustrates a device 2 embedded in vehicles Figure 1 [Fig. 1] shows a particular, non-limiting embodiment of the present invention. Examples of such a device 2 include, but are not limited to, various electronic devices such as a smartphone, a tablet, a laptop computer, and electronic equipment embedded in an electric vehicle. The elements of the device 2, individually or in combination, can be integrated into a single integrated circuit, into several integrated circuits, and / or into discrete components. The device 2 can be implemented in the form of electronic circuits or software (or computer) modules, or a combination of electronic circuits and software modules. The device 2 includes one (or more) processor(s) 201 configured for executing the instructions of the software embedded in the device 2.The processor 201 may include integrated memory, an input / output interface, and various circuits known to those skilled in the art. The device 2 further includes at least one memory 202, by volatile and / or non-volatile memory and / or includes a memory storage device which may include volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

[0049] The computer code comprising the instructions to be loaded and executed by the processor is for example stored on the memory or the memory storage device 202.

[0050] According to a particular and non-limiting embodiment, the device 2 comprises a block 203 of interface elements for communicating with external devices, for example the remote device 14 or a relay antenna 12. The interface elements of the block 203 comprise one or more of the following interfaces: - RF radio frequency interface, for example of the Bluetooth® or Wi-Fi® type; - USB interface (from the English "Universal Serial Bus" or "Universal Bus") Series (in French); - HDMI interface (from the English "High Definition Multimedia Interface", or "High Definition Multimedia Interface" in French); - RFID interface (from the English Radio Frequency Identification).

[0051] According to another particular embodiment, the device 2 includes a communication interface 204 which enables communication with other devices. The communication interface 204 corresponds, for example, to a transmitter configured to transmit and receive information and / or data via a communication channel 205. The communication interface 204 includes, for example, a modem and / or a network card, and the communication channel can, for example, be implemented in a wired and / or wireless medium.

[0052] Data is exchanged, for example, with the central device 14 using a Wi-Fi® network such as IEEE 802.11 via an access point. Communication between a device 2 on board an electric vehicle and this access point can then be established according to a wireless communication protocol such as Wi-Fi® (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or Bluetooth (according to IEEE 802.15.1), in the 2.4 GHz frequency band. The wireless access point can also communicate with another access point via a wired connection (or "backbone"), for example of the MoCA type (from the English "Multimedia over Coax Alliance" or in French "Alliance multimédia sur coax"), Ethernet, PLC (from the English "Powerline Communication" or in French CPL "Courants Porteurs en Ligne"), POF (from the English "Plastic Optical Fiber" or in French "Fibre optique plastique") or even ITU G.hn (corresponding to the standard for next-generation home network technologies of the ITU, from the English "International Telecommunication Union" or in French "Union internationale des télécommunications"). .

[0053] Data can also be exchanged with the central device 14 using a cellular network such as a 4G (or LTE Advanced according to 3GPP release 10 - version 10) or 5G network via the relay antennas 107 and / or 110.

[0054] Data can also be exchanged with the central device 14 by reading a "radio tag" (from the English RFID tag) then affixed to an element of the electric vehicles lOi or to equipment on board these electric vehicles lOi.

[0055] The communication interface 204 can also behave as an interface of a wireless ad hoc network (also called a WANET or MANET), corresponding to a decentralized wireless network. Unlike a centralized network that relies on an existing infrastructure including, for example, routers or access points connected to each other by a wired or wireless infrastructure, the wireless ad hoc network consists of nodes that each participate in data routing by retransmitting data from one node to another, from sender to receiver, according to network connectivity and a routing algorithm. The wireless ad hoc network advantageously corresponds to a vehicular ad hoc network (or VANET) or an intelligent vehicular ad hoc network (or InVANET).In such a network, two or more electric vehicles, each equipped with a node (i.e., a 204 communication interface behaving like a WANET or MANET interface), can communicate with each other in the context of vehicle-to-vehicle (V2V) communication or vehicle-to-infrastructure (V2I) communication. Each electric vehicle can also communicate with one or more pedestrians equipped with mobile devices (e.g., a smartphone) in the context of vehicle-to-pedestrian (V2P) communication.

[0056] According to one embodiment, a node of the ad hoc wireless network is connected to the communication network infrastructure 13 via a wired and / or wireless connection. The node can thus act as a relay between this communication network infrastructure and an electric vehicle. A relay antenna 12 can also implement an interface of an ad hoc wireless network. Such an antenna therefore provides the link between the ad hoc network and the communication network infrastructure 13 of which it is a part.

[0057] Devices 2 embedded in electric vehicles can thus communicate with the central device 14 via at least one node of a wireless ad hoc network using communication technologies such as 1TTS G5 (from the English "Intelligent Transportation System G5" or in French "Système de transport intelligent G5") in Europe or DSRC (from the English "Dedicated Short Range Communications" or in French "Communications dédiés à courte portée") in the United States of America, both of which are based on the IEEE 802.1 Ip standard, or the cellular network-based technology called C-V2X (from the English "Cellular - Vehicle to Everything" or in French "Cellulaire - Véhicule électrique vers tout") which is based on 4G based on LTE (from the English "Long Term Evolution" or in French "Evolution à long terme") and soon 5G.

[0058] According to a further particular embodiment, the device 2 can provide output signals to one or more external devices, such as a display screen 206, one or more speakers 207 and / or other peripherals 208 via output interfaces 209, 210 and 211 respectively. According to a variant, one or more of the external devices is integrated into the device 2. The display screen 206 corresponds for example to a screen, touch or not.

[0059] [Fig. 3] schematically illustrates a central device 14, according to a particular and non-limiting embodiment of the present invention. Examples of such a central device 14 include, but are not limited to, various electronic devices such as one or more computers or servers, one or more calculators. The elements of the central device 14, individually or in combination, may be integrated into a single integrated circuit, into several integrated circuits, and / or into discrete components. The central device 14 may be implemented in the form of electronic circuits or software (or computer) modules, or a combination of electronic circuits and software modules. The central device 14 comprises one (or more) processor(s) 301 configured for executing the instructions of the software embedded in the central device 14.The processor 301 may include integrated memory, an input / output interface, and various circuits known to those skilled in the art. The central device 14 further includes at least one memory 302, by volatile and / or non-volatile memory and / or includes a memory storage device which may include volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

[0060] The computer code including the instructions to be loaded and executed by the processor is for example stored on memory or memory storage device 302.

[0061] According to a particular and non-limiting embodiment, the central device 14 includes a block 303 of interface elements for communicating with external devices, for example a remote device 2 or a relay antenna 12. The interface elements of the block 303 include one or more of the following interfaces: - RF radio frequency interface, for example of the Bluetooth® or Wi-Fi® type; - USB interface (from the English "Universal Serial Bus" or "Universal Bus") Series (in French); - HDMI interface (from the English "High Definition Multimedia Interface", or "High Definition Multimedia Interface" in French); - RFID interface (from the English Radio Frequency Identification).

[0062] According to another particular embodiment, the central device 14 includes a communication interface 304 which allows communication to be established with other devices. Communication interface 304 corresponds, for example, to a transmitter configured to transmit and receive information and / or data via a communication channel 305. Communication interface 304 includes, for example, a modem and / or a network card, and the communication channel can, for example, be implemented in a wired and / or wireless medium.

[0063] Data is exchanged, for example, with a device 2 embedded in an electric vehicle lOi or 1 Ij using a Wi-Fi® network such as that according to IEEE 802.11 via an access point. Communication between the central device 14 and an access point can then be established according to a wireless communication protocol such as Wi-Fi® (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or Bluetooth (according to IEEE 802.15.1), in the 2.4 GHz frequency band. A wireless access point can also communicate with another access point via a wired connection (or "backbone"), for example of the MoCA (Multimedia over Coax Alliance), Ethernet, PLC (Powerline Communication), POF (Plastic Optical Fiber) or ITU G type.hn (corresponding to the standard for next-generation home network technologies of the ITU, from the English "International Telecommunication Union" or in French "Union internationale des télécommunications"). .

[0064] Data is exchanged for example with a device 2 on board an electric vehicle lOi using a cellular network such as a 4G network (or LTE Advanced according to 3GPP release 10 - version 10) or 5G via relay antennas 107 and / or 110.

[0065] Data can also be exchanged with a device 2 on board an electric vehicle lOi by reading a "radio tag" (from the English RFID tag) then affixed to an element of the electric vehicles lOi or to equipment on board these electric vehicles lOi.

[0066] According to a further particular embodiment, the central device 14 can provide output signals to one or more external devices, such as a display screen 306, one or more speakers 307 and / or other peripherals 308 via output interfaces 309, 310 and 311 respectively. In a variant, one or more of the external devices is integrated into the central device 14. The display screen 306 corresponds, for example, to a screen, whether touch-sensitive or not.

[0067] [Fig.4] illustrates a flowchart of the different stages of a method for predicting the electrical consumption of an electric vehicle, referred to as the first vehicle in a set of electric vehicles, according to a particular and non-limiting embodiment of the present invention.

[0068] The method is, for example, partially implemented by the central device 14 and by the device 2 installed in each electric vehicle lOi. The electric vehicles lOi are in communication with the central device 14 as discussed previously.

[0069] In a first step 31, the central device 14 obtains a global model M for predicting the electrical consumption of an electric vehicle per trip from local models Mj for predicting the electrical consumption of an electric vehicle per trip and from actual electrical consumptions of at least one electric vehicle lOi following trips made by said at least one electric vehicle lOi.

[0070] Each local model Mj for predicting the electrical consumption of an electric vehicle per trip is trained using data relating to trips made by an electric vehicle from the set of electric vehicles and using the actual electrical consumption of said electric vehicle from the set of electric vehicles for making said trips. The device 2 of said electric vehicle from the set of electric vehicles is in communication with the central device 14.

[0071] In a second step 32, the central device 14 emits parameters of the global model M for predicting electric vehicle consumption per trip to the device 2 of each electric vehicle lOi.

[0072] In a third step 33, the device 2 of the first vehicle 101 obtains a destination of a journey, called the first journey, to be carried out by the first electric vehicle 101.

[0073] According to one variant, the destination of the first journey is obtained by an on-board navigation system of vehicle 101.

[0074] According to one variant, the destination of the first journey is entered by a user via a human-machine interface linked to the navigation system.

[0075] In a fourth step 34, the device 2 of the first electric vehicle 101 obtains data relating to the first journey according to said destination obtained.

[0076] According to one variant, the data collected by the first electric vehicle lOi are at least one of the following: - a distance to be covered to reach the destination of the first journey by the first vehicle 101; - a theoretical speed of the first vehicle to complete the first journey which may depend on the condition of the road surface and / or traffic conditions; - a representative data point for the activation of an on-board air conditioning system of the first vehicle 101 along the first journey; - a representative data point for headlight activation of the first electric vehicle 101 along the first journey; - an average outside temperature data point along the first journey by the first vehicle; - a load (weight) of the first vehicle 101 along the first journey.

[0077] The data collected by the first vehicle 101 are normalized by maximum values.

[0078] In a fifth step 35, the device 2 of the first electric vehicle 101 obtains an estimate of the electrical consumption of the first electric vehicle 101 for completing the first trip from the overall model M for predicting the electrical consumption of electric vehicles per trip and from said data relating to the first trip obtained. Said data are presented as input to the overall model M, which then provides as output said estimated electrical consumption of the first vehicle 101 for completing the first trip.

[0079] According to one variant, the process further comprises steps 36 and 37.

[0080] In step 36, the device 2 of the first vehicle 101 obtains an actual electrical consumption of the first vehicle 101 once the first electric vehicle 101 has completed the first journey.

[0081] In step 37, a predicted electrical consumption performance value of the first vehicle 101 is obtained by calculating a difference between the estimated electrical consumption of the first vehicle 101 to complete the first trip and the actual electrical consumption of the first vehicle 101 once the first electric vehicle 101 has completed the first trip.

[0082] According to one variant, if the calculated power consumption prediction performance value is greater than a threshold value, in a sixth step 38, an actuator of the first electric vehicle 101 is activated to indicate that a preventive maintenance phase of the first electric vehicle 101 is to be expected.

[0083] According to one variant, an indicator light or an area of ​​an on-board human-machine interface of the first electric vehicle 101 is activated.

[0084] According to one embodiment, in a step 39, each local model Mj predicting the electric vehicle's per-trip power consumption driven by device 2 of the first electric vehicle 101 is updated from the actual power consumption of the first vehicle 101 once the first electric vehicle 101 has completed the first trip. This update consists of launching step 31, i.e., the training of each local model Mj predicting the electric vehicle's per-trip power consumption driven by device 2 of the first electric vehicle 101.

[0085] The global model M for predicting electric vehicle electricity consumption per trip is obtained in a federated manner as defined by the article by Brendan McMahan et al. entitled “Communication-Efficient Learning of Deep Networks from Decentralized Data (In Aarti Singh and Jerry Zhu, editors, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, volume 54 of Proceedings of Machine Learning Research, pages 1273-1282. PMLR, 20-22 Apr 2017. pages 1, 2, 3).

[0086] According to a particular and non-limiting example of embodiment, obtaining (step 31), by the central device 14, the global model M for predicting electric vehicle consumption per trip comprises steps 310 to 314.

[0087] In step 310, the central device 14 transmits parameters of an initial local model MO predicting electric vehicle power consumption per trip to device 2 of each electric vehicle lOi.

[0088] In step 311, at least one local model Mj for predicting electric vehicle power consumption per trip is trained by device 2 of at least one electric vehicle lOi (learning said at least one local model Mj by device 2 of a vehicle lOi from the set of electric vehicles).

[0089] Each local model Mj for predicting electric vehicle power consumption per trip is trained by an electric vehicle lOi from data relating to trips made by said electric vehicle lOi and from actual power consumption of said electric vehicle lOi following a predetermined number of trips made by said electric vehicle lOi.

[0090] In step 312, the parameters of said at least one local model Mj for predicting electric vehicle power consumption per driven trip (311) are sent to the central device 14. The parameters of each local model Mj for predicting electric vehicle power consumption per driven trip are sent by the device 2 of the electric vehicle lOi which trained this local model Mj.

[0091] Thus, the parameters of each local model Mj driven by the device 2 of an electric vehicle 11 j are sent to the central device 14.

[0092] In step 313, the central device 14 determines parameters of the global model M for predicting electric vehicle power consumption per trip from the parameters of said at least one local model Mj received.

[0093] According to one variant, the parameters of the global model M are obtained from the parameters of said at least one local model Mj for predicting electric vehicle consumption per trip according to a method of averaging the parameters of said at least one local model Mj.

[0094] According to one variant, the method of averaging the parameters of the Mj models is similar to that described in section 2 of the aforementioned article by Brendan McMahan et al.

[0095] In step 314, the central device 14 sends to device 2 of each electric vehicle lOi, the parameters of the global model M obtained and steps 311, 312, 313 and 314 are iterated until a stopping condition is met.

[0096] According to one variant, a stopping condition is checked when a maximum number of iterations is reached.

[0097] According to one variant, a stopping condition is verified when a variation of the parameters of the global model M between two successive iterations is less than a threshold value.

[0098] According to one embodiment, the device 2 of an electric vehicle lOi drives a local model Mj,n predicting the electric vehicle's power consumption per trip for each initial battery charge level of said electric vehicle lOi, and the central device 14 obtains as many global models Mn predicting the electric vehicle's power consumption per trip as there are initial battery charge levels. The index n belongs to a set of integer values ​​from 1 to N, where N is the number of initial battery charge levels.

[0099] According to one variant, the parameters of a global model Mn for a given initial load level are obtained from the parameters of at least one local model Mj,n corresponding to said initial load level by means of an averaging process of said at least one local model Mj,n.

[0100] Several local models Mj,n for predicting the electrical consumption of an electric vehicle per trip can thus be trained by the device 2 of an electric vehicle lOi, each corresponding to an initial battery charge level of the electric vehicle lOi (step 311). The parameters of each of the models Mj,n are sent to the central device 14 (step 312), and the central device 14 determines N global models Mn for predicting the electrical consumption of an electric vehicle per trip from the received local models Mj,n (step 313). The parameters of the global models Mn are sent to each electric vehicle lOi (step 314), and steps 311, 312, 313, and 314 are iterated until a stopping condition is met.Following a journey (called the first journey) undertaken by the first electric vehicle 101, device 2 of the first electric vehicle 101 selects one of the global models Mn for predicting electric vehicle power consumption per journey based on the initial battery charge level at the start of the first journey. Device 2 of the first electric vehicle 101 obtains (step 33) a destination for the first journey to be undertaken by the first electric vehicle 101, obtains (34) data relating to the first journey based on the destination obtained, and obtains (35) an estimate of the power consumption of the first electric vehicle 101 for undertaking the first journey.

[0101] For example, 10 models Mj,n (n=l to 10) are trained: A first model Ml,j is trained for an initial battery charge percentage between 1 and 10%, a second model M2,j is trained for an initial battery charge percentage between 11 and 20%, etc.

[0102] According to one variant, a local model Mj or Mj,n for predicting the electric vehicle's electricity consumption per trip and a global model M or Mn for predicting the electric vehicle's electricity consumption per trip are implemented by a neural network, also called a deep regression network. The parameters of a local model Mj or Mj,n and the parameters of a global model M or Mn are the internal parameters of the neural network.

[0103] According to one variant, the neural network can, for example, comprise three layers of neurons. The first layer has as many neurons as there are input data points. The second layer is a hidden, fully connected layer with 64 neurons, and the third layer has a single neuron corresponding to one output data point. The neural layers use a Rectified Linear Unit (ReLU) activation function, which basically allows negative results to be replaced by zero.

[0104] Training a local model Mj or Mj,n consists of determining internal parameters of the neural network so as to minimize a cost function defined as a function of electric vehicle power consumption values ​​provided by the neural network when data collected by an electric vehicle lOi following journeys made by the electric vehicle lOi, and as a function of electric vehicle power consumption values ​​of the electric vehicle lOi as they were actually recorded following these journeys.

[0105] Of course, the present invention is not limited to the embodiments described above but extends to a method for predicting the electrical consumption of an electric vehicle, referred to as the first vehicle in a set of electric vehicles, which would include secondary steps without falling outside the scope of the present invention. The same would apply to a device configured for implementing such a method.

[0106] The present invention also relates to an electric vehicle, for example a motor vehicle or more generally an autonomous electric vehicle with a land motor, comprising device 2 of [Fig.2].

Claims

1. Demands Method for predicting the electrical consumption of an electric vehicle, referred to as the first vehicle in a set of electric vehicles, for completing a journey, referred to as the first journey, said method comprising the following steps: - obtaining (31), by a central device, a global model based on a neural network (M) for predicting the electrical consumption of an electric vehicle per trip from local models based on neural networks (Mj, Mj,n) for predicting the electrical consumption of an electric vehicle per trip and from actual electrical consumptions of at least one electric vehicle from the set of electric vehicles following trips made by said at least one electric vehicle from the set of electric vehicles, each local model based on a neural network (Mj, Mj,n) for predicting the electrical consumption of an electric vehicle per trip being trained from data relating to trips made by an electric vehicle from the set of electric vehicles and from actual electrical consumptions of said electric vehicle from the set of electric vehicles to make said trips,a device (2) of said electric vehicle of the set of electric vehicles being in communication with the central device; - emission (32), by the central device (14), of parameters of the global model based on a neural network (M) for predicting the electrical consumption of an electric vehicle per trip to the device (2) of each electric vehicle in the set of electric vehicles; - obtaining (33) by the device of the first vehicle, a destination of the first journey to be made by the first electric vehicle; - obtaining (34), by the device (2) of the first electric vehicle, data relating to the first journey according to said destination obtained; - obtaining (35), by the device (2) of the first electric vehicle, an estimate of the electric consumption of the first electric vehicle to carry out the first journey from the global model based on a neural network (M) for predicting consumption electric vehicle per trip and said data relating to the first trip obtained.

2. A method according to claim 1, which further comprises the following steps: - obtaining (36), by the device (2) of the first vehicle, an actual electrical consumption of the first vehicle once the first electric vehicle has completed the first trip; - obtaining (37) a predicted electrical consumption performance value of the first vehicle by calculating a difference between the estimated electrical consumption of the first vehicle to complete the first trip and the actual electrical consumption of the first vehicle once the first electric vehicle has completed the first trip.

3. A method according to claim 2, further comprising a step (39) of updating each local neural network-based (Mj, Mj,n) electric vehicle per trip prediction model driven by device (2) of the first electric vehicle from the actual electric consumption of the first vehicle once the first electric vehicle has completed the first trip.

4. A method according to any one of claims 1 to 3, wherein obtaining (31), by the central device (14), the global model based on a neural network (M) for predicting electric vehicle power consumption per trip comprises the following steps: a) transmission (310), by the central device (14), of parameters of an initial local model based on a neural network for predicting electric vehicle power consumption per trip to the device of each electric vehicle in the set of electric vehicles;b) learning (311) of at least one local model based on a neural network (Mj, Mj,n) for predicting electric vehicle power consumption per trip by the device (2) of at least one electric vehicle from the set of electric vehicles, each local model based on a neural network (Mj, Mj,n) for predicting electric vehicle power consumption per trip is trained by an electric vehicle from the set of electric vehicles from data relating to trips made by said electric vehicle from the set of electric vehicles; and based on the actual electrical consumption of said electric vehicle of the set of electric vehicles following a predetermined number of journeys made by said electric vehicle of the set of electric vehicles; (c) emission (312) of the parameters of said at least one local model based on a neural network (Mj, Mj,n) for predicting electric vehicle power consumption per trained trip to the central device (14), the parameters of each local model based on a neural network (Mj) for predicting electric vehicle power consumption per trained trip are emitted by the device (2) of the electric vehicle of the set of electric vehicles which trained said local model based on a neural network (Mj) for predicting electric vehicle power consumption per trained trip; d) determination (313) by the central device (14), of the parameters of the global model based on a neural network (M) for predicting electric vehicle electricity consumption per trip from the parameters of said at least one local model based on a neural network (Mj, Mj,n) for predicting electric vehicle electricity consumption per trip received; e) emission (314), by the central device (14) and to the device (2) of each electric vehicle in the set of electric vehicles, of the parameters of the global model based on a neural network (M) of prediction of electric vehicle electrical consumption per trip obtained and steps b), c) d), and e) are iterated until a stopping condition is met.

5. A method according to any one of claims 1 to 4, wherein the device (2) of an electric vehicle in the vehicle set drives a local model based on a neural network (Mj,n) for predicting electric vehicle power consumption per trip per initial battery charge level of said electric vehicle in the vehicle set and the central device (14) obtains as many global models based on neural networks (Mn) for predicting electric vehicle power consumption per trip as there are initial battery charge levels.

6. A computer program comprising instructions for carrying out the method according to any one of the claims

7.

8.

9.

10. previous ones, when these instructions are executed by a processor. Computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the process according to any one of claims 1 to 5. Device (2) comprising a memory (201) associated with at least one processor (200) configured to carry out at least one step of the process according to any one of claims 1 to 5. Electric vehicle (101, 111) comprising the device (2) according to claim 8. System (1) for predicting the electrical consumption of an electric vehicle, said first vehicle of a set of electric vehicles comprising a central device (14) being in communication with electric vehicles of the set of electric vehicles, characterized in that said central device (14) implements at least one step of the method according to one of claims 1 to 5 and each electric vehicle of the set of electric vehicles is an electric vehicle according to claim 9.

Images