Charging guiding method and system for new energy automobile

Abstract

The invention provides a charging guiding method and system for a new energy automobile, and relates to the field of new energy automobile charging. The method comprises the following steps: according to current weather information, historical weather information, current road condition information, historical road condition information, historical charging information of a new energy automobile, operation information of a plurality of charging stations in a plurality of historical periods and operation information of a plurality of historical time points in the current period, calculating the current weather information of the new energy automobile; predicting operation information of the plurality of charging stations at a plurality of future time points of the current period, determining an optimal charging station from the plurality of charging stations, and generating an out-station guiding path corresponding to the optimal charging station; determining an optimal charging pile from the optimal charging stations according to the current weather information, the historical charging information of the new energy vehicle, the operation information of the optimal charging stations in a plurality of historical periods and the operation information of the optimal charging stations at a plurality of historical time points in the current period, and generating an in-station guiding path corresponding to the optimal charging pile, the method has the advantage of improving the charging efficiency and charging convenience of the new energy vehicle.

Description

Technical Field

[0001] The present invention relates to the field of new energy vehicle charging, and in particular to a charging guidance method and system for new energy vehicles. Background Art

[0002] With the rapid development of new energy technologies, the proportion of new energy vehicles is increasing, and more and more parking lots are equipped with charging spaces and corresponding charging piles, so that vehicle personnel (such as drivers) with vehicle charging needs can charge their vehicles through the charging piles corresponding to the charging spaces.

[0003] In actual applications, the conditions (e.g., location, quantity, etc.) of charging spaces in different parking lots are not the same. When a person with a need to charge a vehicle drives a vehicle into an unfamiliar parking lot, the person is not familiar with the relevant conditions of the charging spaces in the parking lot (e.g., the number and location of the charging spaces and the working status of the corresponding charging piles, etc.), which will result in the person being unable to quickly find a charging space that meets his or her vehicle charging needs, and thus unable to charge the vehicle in time.

[0004] Therefore, it is necessary to provide a charging guidance method and system for new energy vehicles, so as to realize automatic guidance of charging of new energy vehicles and improve the charging efficiency and convenience of new energy vehicles. Summary of the invention

[0005] The present invention provides a charging guidance system for new energy vehicles, comprising: a request receiving module, for receiving a charging guidance request initiated by a new energy vehicle; a data acquisition module, for acquiring current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical periods and operation information at multiple historical time points in the current period; a data analysis module, for analyzing the current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical periods and operation information at multiple historical time points in the current period The charging guidance module is used to determine the optimal charging station from the multiple charging stations according to the current road condition information, the historical charging information of the new energy vehicle, and the operating information of the multiple charging stations at multiple future time points in the current cycle, and generate an off-station guidance path corresponding to the optimal charging station; the charging guidance module is also used to determine the optimal charging pile from the optimal charging station according to the current meteorological information, the historical charging information of the new energy vehicle, and the operating information of the optimal charging station at multiple historical time points in the current cycle, and generate an in-station guidance path corresponding to the optimal charging pile.

[0006] Further, the operation information at least includes the charging load of the charging station; the data analysis module predicts the operation information of multiple charging stations at multiple future time points in the current cycle based on current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical periods, and operation information at multiple historical time points in the current cycle, including: for each charging station, determining the key meteorological factors and key roads corresponding to the charging station according to the historical meteorological information, historical road condition information and the charging load of the charging station in multiple historical periods; grouping the multiple charging stations according to the key meteorological factors and key roads corresponding to each charging station to determine at least one charging station group; for each charging station group, generating multiple training samples according to the historical meteorological information, historical road condition information, and the charging load of the charging stations included in the charging station group in multiple historical periods, and establishing a load prediction model corresponding to the charging station group; based on the load prediction model corresponding to each charging station group, the current meteorological information, the current road condition information and the operation information of each charging station at multiple historical time points in the current cycle, predicting the charging load of multiple charging stations at multiple future time points in the current cycle.

[0007] Furthermore, the data analysis module determines the key meteorological factors and key roads corresponding to the charging station based on historical meteorological information, historical road condition information and the charging load of the charging station in multiple historical periods, including: for each meteorological factor, determining the correlation coefficient between the meteorological factor and the charging load based on the historical meteorological information and the charging load of the charging station in multiple historical periods; determining the key meteorological factors corresponding to the charging station based on the correlation coefficient between each meteorological factor and the charging load; for each road, determining the correlation coefficient between the road and the charging load based on the historical road condition information and the charging load of the charging station in multiple historical periods; determining the key road corresponding to the charging station based on the correlation coefficient between each road and the charging load.

[0008] Furthermore, the data analysis module predicts the operation information of multiple charging stations at multiple future time points in the current cycle based on the load prediction model corresponding to each charging station group, the current meteorological information, the current road condition information and the operation information of each charging station at multiple historical time points in the current cycle, including: for each charging station group, based on the key meteorological factors corresponding to each charging station included in the charging station group, determining the key meteorological factors corresponding to the charging station group, and determining the load correction parameters corresponding to multiple meteorological types for any two charging stations included in the charging group according to the key meteorological factors corresponding to the charging station group, the historical meteorological information and the historical charging information of each charging station included in the charging station group; for each charging station, The corresponding load prediction model predicts the initial charging load of the charging station at multiple future time points in the current cycle based on the current meteorological information, the current road condition information and the operation information of each charging station at multiple historical time points in the current cycle; for each charging station group, according to the load correction parameters corresponding to multiple meteorological types of any two charging stations included in the charging group, the load correction parameters corresponding to the current meteorological information of any two charging stations included in the charging group are determined, and according to the load correction parameters corresponding to the current meteorological information of any two charging stations included in the charging group, the initial charging load of each charging station included in the charging group at multiple future time points in the current cycle is corrected to generate the charging load of each charging station included in the charging group at multiple future time points in the current cycle.

[0009] Furthermore, the data analysis module determines the key meteorological factors corresponding to the charging station group based on the key meteorological factors corresponding to each charging station included in the charging station group, and determines the load correction parameters for multiple meteorological types corresponding to any two charging stations included in the charging group according to the key meteorological factors corresponding to the charging station group, historical meteorological information and historical charging information of each charging station included in the charging station group, including: determining the multiple meteorological types corresponding to the charging station group based on the key meteorological factors and historical meteorological information corresponding to each charging station included in the charging station group; grouping multiple historical periods according to the multiple meteorological types and historical meteorological information corresponding to the charging station group to determine multiple historical period groups, wherein one historical period group corresponds to one meteorological type; for each meteorological type, determining the load correction parameters for the meteorological type corresponding to any two charging stations included in the charging group according to the operating information of each charging station included in the charging station group in the historical period group.

[0010] Further, the charging guidance module determines the optimal charging station from the multiple charging stations according to the current road condition information, the historical charging information of the new energy vehicle, and the operation information of the multiple charging stations at multiple future time points in the current cycle, and generates an off-station guidance path corresponding to the optimal charging station, including: for each charging station, determining the optimal charging path corresponding to the charging station according to the real-time position of the new energy vehicle, the position of the charging station, the regional electronic map and the road condition information, and determining the score of the path index of the charging station according to the optimal charging path corresponding to the charging station; for each charging station, determining the score of the load index of the charging station according to the operation information of the charging station at multiple future time points in the current cycle; for each charging station, determining the score of the inertia index of the charging station according to the historical charging information of the new energy vehicle; determining the optimal charging station from the multiple charging stations according to the score of the path index, the score of the load index and the score of the inertia index of each charging station; and generating the off-station guidance path corresponding to the optimal charging station according to the optimal charging path corresponding to the optimal charging station.

[0011] Furthermore, the operation information also includes operation status information of each charging pile in the charging station; the charging guidance module determines the optimal charging pile from the optimal charging station according to the current meteorological information, the historical charging information of the new energy vehicle and the operation information of the optimal charging station at multiple historical time points in the current cycle, and generates an in-station guidance path corresponding to the optimal charging pile, including: determining the fault risk value of the charging pile in an idle state in the optimal charging station according to the operation status information of each charging pile in the optimal charging station; determining multiple candidate charging piles according to the fault risk value of the charging pile in an idle state in the optimal charging station; determining the optimal charging pile from the multiple candidate charging piles according to the current meteorological information and the historical charging information of the new energy vehicle; generating the in-station guidance path corresponding to the optimal charging pile according to the real-time position of the new energy vehicle, the position of the optimal charging pile and the in-station electronic map of the optimal charging station.

[0012] Furthermore, the charging guidance module determines the fault risk value of the charging piles in the optimal charging station that are in an idle state according to the operating status information of each charging pile in the optimal charging station, including: determining the initial fault risk value of each charging pile in the optimal charging station according to the operating status information of each charging pile in the optimal charging station; for any two charging piles in the optimal charging station, calculating the fault correlation coefficient of the two charging piles according to the historical status information of the two charging piles; for each charging pile in the optimal charging station, determining the fault-associated charging pile of the charging pile according to the fault correlation coefficient of any two charging piles in the optimal charging station; for each charging pile in the idle state in the optimal charging station, determining the fault risk value of the charging pile according to the initial fault risk value of the charging pile and the initial fault risk value of the fault-associated charging pile of the charging pile.

[0013] Furthermore, the charging guidance module determines the optimal charging pile from the multiple candidate charging piles based on the current meteorological information and the historical charging information of the new energy vehicle, including: for each candidate charging pile, calculating the state priority value corresponding to the candidate charging pile according to the state of the adjacent charging piles of the candidate charging pile; determining the inertial parking time of the new energy vehicle corresponding to the current meteorological information according to the historical charging information of the new energy vehicle; determining the optimal charging pile from the multiple candidate charging piles according to the inertial parking time of the new energy vehicle corresponding to the current meteorological information and the state priority value corresponding to each candidate charging pile.

[0014] The present invention provides a charging guidance method for new energy vehicles, which is applied to the above-mentioned charging guidance system for new energy vehicles, including: receiving a charging guidance request initiated by a new energy vehicle; obtaining current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of the new energy vehicle, operation information of multiple charging stations in multiple historical periods and operation information at multiple historical time points in the current period; predicting the operation information of multiple charging stations at multiple future time points in the current period according to the current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of the new energy vehicle, operation information of multiple charging stations in multiple historical periods and operation information at multiple historical time points in the current period; determining an optimal charging station from the multiple charging stations according to the current road condition information, historical charging information of the new energy vehicle, and operation information of multiple charging stations at multiple future time points in the current period, and generating an off-station guidance path corresponding to the optimal charging station; determining an optimal charging pile from the optimal charging station according to the current meteorological information, historical charging information of the new energy vehicle, and operation information of the optimal charging station in multiple historical periods and operation information at multiple historical time points in the current period, and generating an in-station guidance path corresponding to the optimal charging pile.

[0015] Compared with the prior art, the charging guidance method and system for new energy vehicles provided by the present invention have at least the following features:

[0016] Beneficial effects:

[0017] 1. By predicting the operation information of charging stations at future time points, the optimal charging station and the optimal charging pile can be quickly determined, avoiding the problem of long waiting time caused by improper selection of new energy vehicle users, and significantly improving the charging efficiency. Not only the choice of charging station is considered, but also the off-station guidance path from the user's current location to the optimal charging station, and the on-station guidance path from the charging station entrance to the optimal charging pile are generated. This all-round guidance service greatly improves the user's charging experience. By using big data analysis and prediction technology, taking into account multiple factors such as weather, road conditions, and historical charging information, intelligent charging decision support is provided for new energy vehicle users, making charging choices more scientific and reasonable. By introducing historical meteorological information, historical road conditions information, and historical charging information, the system can better adapt to charging needs at different times, in different weather and under different traffic conditions, improving the flexibility and adaptability of the system. By reasonably guiding the charging behavior of new energy vehicles, the system helps to balance the load of each charging station, avoid the situation where some charging stations are overcrowded while others are idle, thereby optimizing energy utilization and improving the operating efficiency of the overall charging network. When selecting the optimal charging station and charging pile, the system can take into account the historical operation and current status of the relevant facilities, which helps to avoid selecting charging facilities with safety hazards, thereby improving the safety of the charging process.

[0018] 2. By introducing multiple data sources, including weather and road condition information, the factors affecting the change of charging station load can be more comprehensively reflected, thereby improving the accuracy and reliability of load forecasting. The real-time load situation and future forecast information of the charging station can be obtained to select a more appropriate charging time and location, reduce waiting time, and improve the charging experience.

[0019] 3. According to the real-time location of new energy vehicles, the location of charging stations, road conditions and the load of charging stations, the optimal charging path and charging station are planned for users, reducing the user's driving time and waiting time, and improving the charging experience. By accurately predicting the load of charging stations, the system can guide users to choose charging stations with lower loads for charging, thereby balancing the load of each charging station and optimizing the configuration of charging resources. It can recommend charging piles with lower failure risks to users based on the operating status information of charging piles, reduce charging interruptions caused by charging pile failures, and improve charging efficiency. By comprehensively considering the failure risk value and failure correlation coefficient of charging piles, the reliability of charging piles can be more accurately evaluated, thereby providing users with more reliable charging services. It can provide users with personalized charging suggestions based on the historical charging information of new energy vehicles, such as recommending suitable charging piles and charging durations based on users' charging habits and current weather information. Through intelligent algorithms, it can quickly determine the optimal charging station and charging pile based on real-time data and historical information, and generate guidance paths to achieve intelligent guidance and scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0021] Figure 1 is a module schematic diagram of a charging guidance system for new energy vehicles according to some embodiments of this specification;

[0022] Figure 2 It is a flow chart of a charging guidance method for new energy vehicles according to some embodiments of this specification. DETAILED DESCRIPTION

[0023] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0024] Figure 1 is a schematic diagram of a module of a charging guidance system for a new energy vehicle according to some embodiments of this specification, such as Figure 1 As shown, the charging guidance system for new energy vehicles may include a request receiving module, a data acquisition module, a data analysis module and a charging guidance module.

[0025] The request receiving module can be used to receive a charging guidance request initiated by a new energy vehicle.

[0026] The data acquisition module can be used to obtain current weather information, historical weather information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical periods, and operation information at multiple historical time points in the current period.

[0027] Specifically, one cycle may be one day.

[0028] The operation information includes at least the charging load of the charging station. The operation information also includes the operation status information of each charging pile in the charging station, such as charging current, charging voltage, vibration information, temperature information, etc.

[0029] A status collection device may be provided at the charging pile to collect the operating status information of the charging pile.

[0030] The data analysis module can be used to predict the operating information of multiple charging stations at multiple future time points in the current cycle based on current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operating information of multiple charging stations in multiple historical cycles, and operating information at multiple historical time points in the current cycle.

[0031] Specifically include:

[0032] For each charging station, determine the key meteorological factors and key roads corresponding to the charging station based on historical meteorological information, historical road condition information, and the charging load of the charging station in multiple historical periods;

[0033] According to the key meteorological factors and key roads corresponding to each charging station, multiple charging stations are grouped to determine at least one charging station group;

[0034] For each charging station group, multiple training samples are generated based on historical meteorological information, historical road condition information, and charging loads of the charging stations included in the charging station group in multiple historical periods, and a load forecasting model corresponding to the charging station group is established, wherein the load forecasting model may be a long short-term memory network model;

[0035] Based on the load prediction model corresponding to each charging station group, current weather information, current road condition information and operation information of each charging station at multiple historical time points in the current cycle, the charging loads of multiple charging stations at multiple future time points in the current cycle are predicted.

[0036] In some embodiments, the data analysis module determines the key meteorological factors and key roads corresponding to the charging station based on historical meteorological information, historical road condition information, and the charging load of the charging station in multiple historical periods, including:

[0037] For each meteorological factor (e.g., weather temperature, weather humidity, weather humidity, light intensity, etc.), the correlation coefficient between the meteorological factor and the charging load is determined based on historical meteorological information and the charging load of the charging station in multiple historical periods;

[0038] Determine the key meteorological factor corresponding to the charging station according to the correlation coefficient between each meteorological factor and the charging load. For example, the meteorological factor having a correlation coefficient greater than a first correlation coefficient threshold may be used as the key meteorological factor corresponding to the charging station.

[0039] For each road, the correlation coefficient between the road and the charging load is determined based on the historical road condition information and the charging load of the charging station in multiple historical periods;

[0040] The key road corresponding to the charging station is determined according to the correlation coefficient between each road and the charging load. For example, the road with a correlation coefficient greater than a second correlation coefficient threshold may be used as the key road corresponding to the charging station.

[0041] Specifically, for each historical period, the characteristic value corresponding to the meteorological factor can be calculated. For example, on XX / XX / XX, the weather temperature is 20° C. to 26° C., and the middle value 23 can be taken as the characteristic value corresponding to the weather temperature.

[0042] The correlation coefficient between meteorological factors and charging load can be calculated according to the following formula:

[0043]

[0044] Among them, r i is the correlation coefficient between the ith meteorological factor and the charging load, F (i,n) is the characteristic value of the ith meteorological factor in the nth historical period, L n is the charging load of the nth historical cycle, and N is the total number of historical cycles.

[0045] The correlation coefficient between road and charging load can be calculated according to the following formula:

[0046]

[0047] Among them, r j is the correlation coefficient between road and charging load, F (i,n) is the characteristic value of the j-th road in the n-th historical period.

[0048] For any two charging stations, the similarity of the two charging stations can be calculated according to the key meteorological factors and key roads corresponding to the two charging stations. A hierarchical clustering algorithm is used to group multiple charging stations according to the similarity of the two charging stations to determine at least one charging station group.

[0049] For example, the charging station similarity of two charging stations can be calculated according to the following formula:

[0050]

[0051] Among them, S (e,f) is the similarity between the e-th charging station and the f-th charging station, C ((e,f),i,1) is the overlap value of the e-th charging station and the f-th charging station under the i-th meteorological factor. When the key meteorological factors of the e-th charging station and the f-th charging station both include the i-th meteorological factor, then C ((e,f),i,1) is 1, otherwise C ((e,f),i,1) is 0, C ((e,f),j,2) is the overlap value of the e-th charging station and the f-th charging station on the j-th road. When the key roads of the e-th charging station and the f-th charging station both include the j-th road, then C ((e,f),j,2) is 1, otherwise C ((e,f),j,2) is 0, I is the total number of meteorological factors, and J is the total number of roads.

[0052] In some embodiments, the data analysis module predicts the operation information of multiple charging stations at multiple future time points in the current cycle based on the load prediction model corresponding to each charging station group, current weather information, current road condition information, and the operation information of each charging station at multiple historical time points in the current cycle, including:

[0053] For each charging station group, based on the key meteorological factors corresponding to each charging station included in the charging station group, determine the key meteorological factors corresponding to the charging station group, and determine the load correction parameters corresponding to multiple meteorological types for any two charging stations included in the charging station group according to the key meteorological factors corresponding to the charging station group, historical meteorological information, and historical charging information of each charging station included in the charging station group;

[0054] For each charging station, the initial charging load of the charging station at multiple future time points in the current cycle is predicted by the load prediction model corresponding to the charging station group to which the charging station belongs based on the current meteorological information, the current road condition information and the operation information of each charging station at multiple historical time points in the current cycle;

[0055] For each charging station group, load correction parameters corresponding to multiple meteorological types of any two charging stations included in the charging group are determined, and the initial charging load of each charging station included in the charging group at multiple future time points in the current cycle is corrected according to the load correction parameters corresponding to the current meteorological information of any two charging stations included in the charging group, to generate the charging load of each charging station included in the charging group at multiple future time points in the current cycle.

[0056] Specifically, the union of the key meteorological factors corresponding to each charging station included in the charging station group can be calculated to determine the candidate key meteorological factors corresponding to the charging station group. For each candidate key meteorological factor, the proportion of charging stations in the charging station group that use the candidate key meteorological factor as a key meteorological factor can be determined, and the candidate key meteorological factors with a proportion greater than a proportion threshold are taken as the key meteorological factors corresponding to the charging station group.

[0057] In some embodiments, the data analysis module determines the key meteorological factors corresponding to the charging station group based on the key meteorological factors corresponding to each charging station included in the charging station group, and determines the load correction parameters corresponding to multiple meteorological types for any two charging stations included in the charging station group according to the key meteorological factors corresponding to the charging station group, historical meteorological information, and historical charging information of each charging station included in the charging station group, including:

[0058] Based on the key meteorological factors and historical meteorological information corresponding to each charging station included in the charging station group, multiple meteorological types corresponding to the charging station group are determined (for example, sunny high-irradiance meteorological type, cloudy low-irradiance meteorological type, high-temperature and high-humidity meteorological type, etc.);

[0059] According to the multiple meteorological types and historical meteorological information corresponding to the charging station group, multiple historical periods are grouped to determine multiple historical period groups, wherein one historical period group corresponds to one meteorological type;

[0060] For each meteorological type, load correction parameters corresponding to the meteorological type of any two charging stations included in the charging group are determined according to the operation information of each charging station included in the charging station group in the historical period group.

[0061] Specifically, different meteorological types correspond to different values ​​of at least one key meteorological factor.

[0062] The comprehensive correction model can be used to determine the load correction parameters of any two charging stations included in the charging group corresponding to the current meteorological information based on the load correction parameters of various meteorological types corresponding to any two charging stations included in the charging group. The initial charging load of each charging station included in the charging group at multiple future time points in the current cycle is corrected based on the load correction parameters of any two charging stations included in the charging group corresponding to the current meteorological information, and the charging load of each charging station included in the charging group at multiple future time points in the current cycle is generated. The comprehensive correction model can be multiple multivariate linear regression models.

[0063] The load correction parameters for the two charging stations corresponding to the meteorological types can be calculated according to the following formula:

[0064]

[0065] Among them, ψ ((i,j),k)is the load correction parameter of the i-th charging station and the i-th charging station corresponding to the k-th meteorological type, M k is the total number of historical cycles included in the historical cycle group corresponding to the kth meteorological type, L (i,m) is the charging load of the historical period included in the mth historical period group corresponding to the kth meteorological type at the i-th charging station, L (j,m) It is the charging load of the j-th charging station in the historical period included in the m-th historical period group corresponding to the k-th meteorological type.

[0066] The meteorological type corresponding to the current meteorological information can be determined, thereby determining the load correction parameters of any two charging stations included in the charging group corresponding to the current meteorological information.

[0067] The charging guidance module can be used to determine the optimal charging station from multiple charging stations based on current road condition information, historical charging information of new energy vehicles, and operating information of multiple charging stations at multiple future time points in the current cycle, and generate an off-station guidance path corresponding to the optimal charging station.

[0068] Specifically include:

[0069] For each charging station, the optimal charging path corresponding to the charging station is determined based on the real-time location of the new energy vehicle, the location of the charging station, the regional electronic map and the road condition information. Based on the optimal charging path corresponding to the charging station, the score of the charging station in the path indicator is determined;

[0070] For each charging station, a score of the charging station on the load index is determined based on the operation information of the charging station at multiple future time points in the current cycle;

[0071] For each charging station, the score of the charging station in the inertia index is determined based on the historical charging information of new energy vehicles;

[0072] Determine an optimal charging station from multiple charging stations according to a score of a path indicator, a score of a load indicator, and a score of an inertia indicator of each charging station;

[0073] According to the optimal charging path corresponding to the optimal charging station, an off-station guidance path corresponding to the optimal charging station is generated.

[0074] Specifically, the optimal charging path corresponding to the charging station can be determined by the path determination model according to the real-time location of the new energy vehicle, the location of the charging station, the regional electronic map and the road condition information, wherein the path determination model can be a convolutional neural network model, wherein the optimal charging path corresponding to the charging station can be the path that takes the shortest time for the new energy vehicle to travel from the current location to the charging station. The shorter the time required for the new energy vehicle to complete the optimal charging path corresponding to the charging station, the higher the score of the charging station in the load index.

[0075] The smaller the sum of the charging loads of the charging station at multiple future time points in the current cycle, the higher the score of the charging station in the load index.

[0076] The weight of each charging station can be determined based on the historical charging information of new energy vehicles, where the weight of a charging station is the ratio of the number of new energy vehicles charged at a certain charging station to the total number of new energy vehicles charged. The higher the weight of the charging station, the higher the score of the charging station in the inertia index.

[0077] The scores of the charging station in terms of path index, load index and inertia index may be weighted and summed to determine the comprehensive score of the charging station, and the charging station with the highest comprehensive score may be selected as the optimal charging station.

[0078] The charging guidance module is also used to determine the optimal charging pile from the optimal charging station based on current meteorological information, historical charging information of new energy vehicles and operating information of the optimal charging station at multiple historical time points in the current cycle, and generate an in-station guidance path corresponding to the optimal charging pile.

[0079] Specifically include:

[0080] Determine the fault risk value of the charging piles in the optimal charging station that are in an idle state according to the operating status information of each charging pile in the optimal charging station;

[0081] Determine multiple candidate charging piles according to the fault risk values ​​of the charging piles in an idle state in the optimal charging station. For example, the charging piles in an idle state in the optimal charging station whose fault risk values ​​are less than the fault risk value threshold can be used as candidate charging piles.

[0082] Determine the best charging pile from multiple candidate charging piles based on current weather information and historical charging information of new energy vehicles;

[0083] According to the real-time location of the new energy vehicle, the location of the optimal charging pile and the electronic map of the optimal charging station, the in-station guidance path corresponding to the optimal charging pile is generated.

[0084] In some embodiments, the charging guidance module determines the fault risk value of the idle charging pile in the optimal charging station according to the operation status information of each charging pile in the optimal charging station, including:

[0085] Determine the initial failure risk value of each charging pile in the optimal charging station according to the operating status information of each charging pile in the optimal charging station;

[0086] For any two charging piles in the optimal charging station, the fault correlation coefficients of the two charging piles are calculated according to the historical status information of the two charging piles;

[0087] For each charging pile in the optimal charging station, the fault correlation coefficient of any two charging piles in the optimal charging station is used to determine the fault-associated charging pile of the charging pile, and the charging pile with a fault correlation coefficient greater than a fault correlation coefficient threshold can be used as the fault-associated charging pile of the charging pile;

[0088] For each charging pile in an idle state in the optimal charging station, a failure risk value of the charging pile is determined according to an initial failure risk value of the charging pile and an initial failure risk value of a failure-associated charging pile of the charging pile.

[0089] Specifically, the initial fault risk value of the charging piles in the optimal charging station can be determined according to the operating status information of the charging piles in the optimal charging station through a fault prediction model, wherein the fault prediction model can be a long short-term memory network model.

[0090] Different charging pile states can be encoded, for example:

[0091] 000: Normal operation

[0092] 001: The charging station cannot be powered

[0093] 002: The power indicator light is off

[0094] 003: The power cord is broken or has poor contact

[0095] 004: Power socket is damaged

[0096] 010: Communication between the charging pile and the background system is interrupted

[0097] 011: Communication module failure

[0098] 012: The network signal is weak or unstable

[0099] 013: Communication protocol mismatch

[0100] 020: The charging gun cannot be inserted or removed

[0101] 021: Charging port is loose or damaged

[0102] 022: There is a foreign object in the charging port

[0103] 023: The charging port is poorly sealed, causing water leakage or dust ingress.

[0104] For any two charging piles in the optimal charging station, the fault correlation coefficient of the two charging piles can be calculated according to the following formula:

[0105]

[0106] Among them, r (i,j)is the fault correlation coefficient between the i-th charging pile and the j-th charging pile, E (i,n) is the coded value of the charging pile status of the i-th charging pile in the n-th historical period, E (j,n) is the encoding value of the charging pile status of the j-th charging pile in the n-th historical period.

[0107] The failure risk value of the charging pile can be determined by a failure risk correction model based on the initial failure risk value of the charging pile and the initial failure risk value of the charging pile associated with the failure of the charging pile, wherein the failure risk correction model can be a multivariate regression linear model.

[0108] In some embodiments, the charging guidance module determines the optimal charging pile from multiple candidate charging piles according to the current weather information and the historical charging information of the new energy vehicle, including:

[0109] For each candidate charging pile, calculate the state priority value corresponding to the candidate charging pile according to the states of the adjacent charging piles of the candidate charging pile;

[0110] According to the historical charging information of new energy vehicles, determine the inertia parking time of new energy vehicles corresponding to the current weather information;

[0111] According to the inertial parking time of the new energy vehicle corresponding to the current weather information and the state priority value corresponding to each candidate charging pile, the optimal charging pile is determined from multiple candidate charging piles.

[0112] Specifically, the inertia parking time of the new energy vehicle corresponding to the current weather information can be determined according to the following process:

[0113] Based on the historical charging information of new energy vehicles, determine the average charging parking time of new energy vehicles under different weather types;

[0114] Calculate the standard deviation of the average charging parking time of new energy vehicles under different weather types, and determine whether the standard deviation is less than the standard deviation threshold;

[0115] If the standard deviation is less than the standard deviation threshold, then the average of each parking charging time is calculated based on the historical charging information of the new energy vehicle to obtain the inertial parking time of the new energy vehicle corresponding to the current weather information;

[0116] If the standard deviation is greater than or equal to the standard deviation threshold, the average charging parking time of the new energy vehicle under the weather type corresponding to the current weather information is obtained as the inertia parking time of the new energy vehicle corresponding to the current weather information.

[0117] The adjacent relationship between the charging piles may be manually defined in advance, or may be determined based on the distance between the charging piles. For example, two charging piles whose distance is less than a distance threshold may be regarded as adjacent charging piles.

[0118] The adjacent charging piles in the idle state are marked as 1, and the adjacent charging piles in the charging state are marked as 0. The state marks of the adjacent charging piles of the candidate charging piles are averaged to obtain the state mark mean. The smaller the state mark mean, the greater the state priority value corresponding to the candidate charging pile.

[0119] The charging pile determination model can be used to determine the optimal charging pile from multiple candidate charging piles based on the inertial parking time of the new energy vehicle corresponding to the current meteorological information and the state priority value corresponding to each candidate charging pile, wherein the charging pile determination model can be a convolutional neural network model.

[0120] The path generation model can be used to generate a guide path within the station corresponding to the optimal charging pile according to the real-time location of the new energy vehicle, the location of the optimal charging pile and the electronic map within the optimal charging station, wherein the path generation model can be a convolutional neural network model.

[0121] Figure 2 is a flow chart of a charging guidance method for a new energy vehicle according to some embodiments of this specification, such as Figure 2 As shown, the charging guidance method for new energy vehicles may include the following steps.

[0122] Receive charging guidance requests initiated by new energy vehicles;

[0123] Obtain current weather information, historical weather information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical periods, and operation information at multiple historical time points in the current period;

[0124] Predicting the operation information of the plurality of charging stations at multiple future time points in the current cycle based on current weather information, historical weather information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of the plurality of charging stations in multiple historical cycles, and operation information at multiple historical time points in the current cycle;

[0125] According to the current road condition information, the historical charging information of new energy vehicles, and the operation information of multiple charging stations at multiple future time points in the current cycle, the optimal charging station is determined from multiple charging stations, and an off-station guidance path corresponding to the optimal charging station is generated;

[0126] Based on current meteorological information, historical charging information of new energy vehicles, and operating information of the optimal charging station in multiple historical periods and operating information at multiple historical time points in the current period, the optimal charging pile is determined from the optimal charging station, and an in-station guidance path corresponding to the optimal charging pile is generated.

[0127] The charging guidance method for new energy vehicles can be applied to the above-mentioned charging guidance system for new energy vehicles, which will not be described in detail here.

[0128] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A charging guidance system for new energy vehicles, characterized in that: include: A request receiving module, used to receive a charging guidance request initiated by a new energy vehicle; A data acquisition module is used to obtain current weather information, historical weather information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical periods, and operation information at multiple historical time points in the current period; A data analysis module, for predicting the operation information of multiple charging stations at multiple future time points in the current cycle based on current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical cycles, and operation information at multiple historical time points in the current cycle; A charging guidance module, configured to determine an optimal charging station from among the multiple charging stations based on current road condition information, historical charging information of new energy vehicles, and operation information of multiple charging stations at multiple future time points in the current cycle, and generate an off-station guidance path corresponding to the optimal charging station; The charging guidance module is also used to determine the optimal charging pile from the optimal charging station based on current meteorological information, historical charging information of new energy vehicles and operation information of the optimal charging station at multiple historical time points in the current cycle, and generate an in-station guidance path corresponding to the optimal charging pile.

2. The charging guidance system for new energy vehicles according to claim 1, characterized in that: The operation information includes at least the charging load of the charging station; The data analysis module predicts the operation information of multiple charging stations at multiple future time points in the current cycle based on current meteorological information, historical meteorological information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical cycles, and operation information at multiple historical time points in the current cycle, including: For each charging station, determining key meteorological factors and key roads corresponding to the charging station based on historical meteorological information, historical road condition information, and charging loads of the charging station in multiple historical periods; According to the key meteorological factors and key roads corresponding to each charging station, the plurality of charging stations are grouped to determine at least one charging station group; For each charging station group, multiple training samples are generated based on historical meteorological information, historical road condition information, and charging loads of the charging stations included in the charging station group in multiple historical periods, and a load prediction model corresponding to the charging station group is established; Based on the load prediction model corresponding to each charging station group, current weather information, current road condition information and operation information of each charging station at multiple historical time points in the current cycle, the charging loads of multiple charging stations at multiple future time points in the current cycle are predicted.

3. The charging guidance system for new energy vehicles according to claim 2, characterized in that: The data analysis module determines the key meteorological factors and key roads corresponding to the charging station according to the historical meteorological information, the historical road condition information and the charging load of the charging station in multiple historical periods, including: For each meteorological factor, determining a correlation coefficient between the meteorological factor and the charging load based on historical meteorological information and the charging load of the charging station in multiple historical periods; Determine the key meteorological factors corresponding to the charging station according to the correlation coefficient between each meteorological factor and the charging load; For each road, determining a correlation coefficient between the road and the charging load based on historical road condition information and the charging load of the charging station in multiple historical cycles; According to the correlation coefficient between each road and the charging load, the key road corresponding to the charging station is determined.

4. The charging guidance system for new energy vehicles according to claim 2, characterized in that: The data analysis module predicts the operation information of multiple charging stations at multiple future time points in the current cycle based on the load prediction model corresponding to each charging station group, current meteorological information, current road condition information, and the operation information of each charging station at multiple historical time points in the current cycle, including: For each charging station group, based on the key meteorological factors corresponding to each charging station included in the charging station group, determine the key meteorological factors corresponding to the charging station group, and determine the load correction parameters corresponding to multiple meteorological types for any two charging stations included in the charging station group according to the key meteorological factors corresponding to the charging station group, historical meteorological information and historical charging information of each charging station included in the charging station group; For each charging station, predicting the initial charging load of the charging station at multiple future time points in the current cycle through a load prediction model corresponding to the charging station group to which the charging station belongs based on current meteorological information, current road condition information, and operation information of each charging station at multiple historical time points in the current cycle; For each charging station group, the load correction parameters of any two charging stations included in the charging group corresponding to multiple meteorological types are determined, and the initial charging load of each charging station included in the charging group at multiple future time points in the current cycle is corrected according to the load correction parameters of any two charging stations included in the charging group corresponding to the current meteorological information, to generate the charging load of each charging station included in the charging group at multiple future time points in the current cycle.

5. The charging guidance system for new energy vehicles according to claim 4, characterized in that: The data analysis module determines the key meteorological factors corresponding to the charging station group based on the key meteorological factors corresponding to each charging station included in the charging station group, and determines the load correction parameters corresponding to multiple meteorological types for any two charging stations included in the charging group according to the key meteorological factors corresponding to the charging station group, historical meteorological information and historical charging information of each charging station included in the charging station group, including: Determining multiple meteorological types corresponding to the charging station group based on key meteorological factors and historical meteorological information corresponding to each charging station included in the charging station group; According to the multiple meteorological types and historical meteorological information corresponding to the charging station group, multiple historical periods are grouped to determine multiple historical period groups, wherein one historical period group corresponds to one meteorological type; For each meteorological type, load correction parameters corresponding to the meteorological type for any two charging stations included in the charging group are determined according to the operation information of each charging station included in the charging station group in the historical period group.

6. The charging guidance system for new energy vehicles according to any one of claims 1 to 5, characterized in that: The charging guidance module determines the optimal charging station from the multiple charging stations according to the current road condition information, the historical charging information of the new energy vehicle, and the operation information of the multiple charging stations at multiple future time points in the current cycle, and generates an off-station guidance path corresponding to the optimal charging station, including: For each charging station, determine the optimal charging path corresponding to the charging station based on the real-time location of the new energy vehicle, the location of the charging station, the regional electronic map and the road condition information, and determine the score of the charging station in the path indicator based on the optimal charging path corresponding to the charging station; For each charging station, determining a score of the charging station on the load index according to operation information of the charging station at multiple future time points in the current cycle; For each charging station, determining a score of the charging station in the inertia index according to the historical charging information of the new energy vehicle; Determining an optimal charging station from the plurality of charging stations according to a score of a path index, a score of a load index, and a score of an inertia index of each charging station; According to the optimal charging path corresponding to the optimal charging station, an off-station guidance path corresponding to the optimal charging station is generated.

7. The charging guidance system for new energy vehicles according to any one of claims 1 to 5, characterized in that: The operation information also includes the operation status information of each charging pile in the charging station; The charging guidance module determines the optimal charging pile from the optimal charging station according to the current meteorological information, the historical charging information of the new energy vehicle and the operation information of the optimal charging station at multiple historical time points in the current cycle, and generates an in-station guidance path corresponding to the optimal charging pile, including: Determining the fault risk value of the charging piles in the optimal charging station that are in an idle state according to the operating status information of each charging pile in the optimal charging station; Determining a plurality of candidate charging piles according to the failure risk values ​​of the charging piles in the idle state in the optimal charging station; Determine the optimal charging pile from the plurality of candidate charging piles according to current weather information and historical charging information of the new energy vehicle; According to the real-time position of the new energy vehicle, the position of the optimal charging pile and the electronic map of the optimal charging station, an in-station guidance path corresponding to the optimal charging pile is generated.

8. The charging guidance system for new energy vehicles according to claim 7, characterized in that: The charging guidance module determines the fault risk value of the charging pile in the idle state in the optimal charging station according to the operation status information of each charging pile in the optimal charging station, including: Determining an initial fault risk value of each charging pile in the optimal charging station according to the operating status information of each charging pile in the optimal charging station; For any two charging piles in the optimal charging station, calculating the fault correlation coefficients of the two charging piles according to the historical status information of the two charging piles; For each charging pile in the optimal charging station, the fault correlation coefficient of any two charging piles in the optimal charging station is used to determine the fault-associated charging pile of the charging pile; For each charging pile in the optimal charging station that is in an idle state, a failure risk value of the charging pile is determined according to an initial failure risk value of the charging pile and an initial failure risk value of a failure-associated charging pile of the charging pile.

9. The charging guidance system for new energy vehicles according to claim 7, characterized in that: The charging guidance module determines the optimal charging pile from the plurality of candidate charging piles according to the current meteorological information and the historical charging information of the new energy vehicle, including: For each candidate charging pile, calculate the state priority value corresponding to the candidate charging pile according to the states of the adjacent charging piles of the candidate charging pile; Determining the inertia parking time of the new energy vehicle corresponding to the current weather information according to the historical charging information of the new energy vehicle; According to the inertial parking time of the new energy vehicle corresponding to the current weather information and the state priority value corresponding to each candidate charging pile, the optimal charging pile is determined from the multiple candidate charging piles.

10. A charging guidance method for new energy vehicles, characterized in that: The charging guidance system for a new energy vehicle as claimed in any one of claims 1 to 9 comprises: Receive charging guidance requests initiated by new energy vehicles; Obtain current weather information, historical weather information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of multiple charging stations in multiple historical periods, and operation information at multiple historical time points in the current period; Predicting the operation information of the plurality of charging stations at multiple future time points in the current cycle based on current weather information, historical weather information, current road condition information, historical road condition information, historical charging information of new energy vehicles, operation information of the plurality of charging stations in multiple historical cycles, and operation information at multiple historical time points in the current cycle; Determine the optimal charging station from the multiple charging stations based on current road condition information, historical charging information of new energy vehicles, and operation information of multiple charging stations at multiple future time points in the current cycle, and generate an off-station guidance path corresponding to the optimal charging station; Based on current meteorological information, historical charging information of new energy vehicles, and operating information of the optimal charging station in multiple historical periods and operating information at multiple historical time points in the current period, the optimal charging pile is determined from the optimal charging station, and an in-station guidance path corresponding to the optimal charging pile is generated.

Images