User power consumption data calculation method and system based on power consumption demand

Abstract

The invention relates to the technical field of charging efficiency optimization, in particular to a user power consumption data calculation method and system based on power consumption demands. Identifying electric vehicle charging stations on the expressway to obtain charging station parameters; dividing the expressway according to the position of the charging station to obtain a road subset, and obtaining electric vehicle parameters on the road subset; identifying the road environment data, the road congestion data and the electric vehicle parameters of the road subsets to obtain the residual electric quantity when the electric vehicle passes through the terminal point charging pile; identifying the navigation route, the residual electric quantity and the road congestion data of the electric vehicle to obtain a charging demand index of the electric vehicle; determining a charging optimization parameter of the charging station according to the charging demand index; calculating a working coefficient according to the charging optimization parameter, the charging demand index and the charging station congestion data; and determining an optimal scheme of the emergency charging station according to the working coefficient. According to the invention, efficiency optimization of the charging station is realized through the charging demand index and the working coefficient.

Description

Technical Field

[0001] The present invention relates to the technical field of charging efficiency optimization, and in particular to a method and system for calculating user electricity consumption data based on electricity consumption demand. Background Art

[0002] The rapid development of the new energy vehicle industry has posed a major challenge to the operational efficiency of the charging service network. There are two core problems in the operation of the existing charging system: first, the static operation mode based on fixed service parameters is difficult to adapt to differentiated charging needs, resulting in insufficient daily effective utilization of charging piles; second, the peak-to-valley difference in power grid load caused by centralized charging behavior exceeds the regional distribution network regulation capacity, resulting in increased operating costs. Especially during the peak travel period during holidays, the problem of regional resource mismatch is particularly prominent, seriously affecting service quality and operator revenue.

[0003] Existing technologies mostly focus on improvements at the power system level, and have three main defects: the data dimension is single, and predictions are made only based on historical vehicle flow time series data, without integrating real-time heterogeneous data such as vehicle SOC, navigation paths, and meteorological environment; the decision-making mechanism is lagging, and clustering algorithms are used for long-term site selection planning, lacking dynamic scheduling capabilities; resource matching is inaccurate, and the traditional allocation model based on a fixed service radius leads to a temporal and spatial misalignment between charging demand and supply.

[0004] To this end, a method and system for calculating user electricity consumption data based on electricity demand are proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for calculating user electricity consumption data based on electricity demand, identifying electric vehicle charging stations on highways to obtain charging station parameters; dividing highways according to the locations of charging stations to obtain road subsets, and obtaining electric vehicle parameters on road subsets; identifying road environment data, road congestion data and electric vehicle parameters of road subsets to obtain the remaining power of electric vehicles when passing through terminal charging piles; identifying electric vehicle navigation routes, remaining power and road congestion data to obtain the charging demand index of electric vehicles; determining charging optimization parameters of charging stations according to the charging demand index; calculating and obtaining working coefficients according to charging optimization parameters, charging demand index and charging station congestion data; and determining the optimal solution for emergency charging stations according to the working coefficient. The present invention optimizes the efficiency of charging stations through charging demand indexes and working coefficients.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for calculating user power consumption data based on power consumption demand, comprising: S10. Identify the electric vehicle charging station on the highway and obtain charging station parameters; the charging station parameters include the location of the charging station, the number of charging piles, the charging power and the congestion data of the charging station; the electric vehicle is a new energy electric vehicle.

[0007] S20. Divide the highway according to the location of the charging station to obtain a road subset; obtain electric vehicle parameters on the road subset, including electric vehicle model, electric vehicle license plate, electric vehicle navigation route, vehicle power data and personalized power consumption parameters; S30. Construct a remaining power prediction model, identify the road environment data, road congestion data and electric vehicle parameters of the road subset, and obtain the remaining power of the electric vehicle when it passes the terminal charging pile; S40. Construct a charging demand prediction model, identify the electric vehicle navigation route, remaining power and road congestion data, and obtain the charging demand index of the electric vehicle; determine the charging optimization parameters of the charging station according to the charging demand index; S50. Calculate the working coefficient based on the charging optimization parameters, the charging demand index and the charging station congestion data; S60. When the working coefficient exceeds the threshold, determine to set up an emergency charging station; obtain a preset plan for the emergency charging station, and determine the optimal plan based on the working coefficients before and after the emergency charging station is set up.

[0008] The remaining power prediction model includes a vehicle route screening layer, a road congestion prediction layer, an electric vehicle speed prediction layer, and an electric vehicle power prediction layer; The vehicle route screening layer identifies the electric vehicle navigation route and determines the electric vehicle passing through the charging station; The road congestion prediction layer identifies road congestion data, including vehicle entry data, vehicle exit data, vehicle quantity, vehicle location and vehicle speed data; and then combines the road environment data of the road subset to predict congestion prediction data; the congestion prediction data includes the predicted vehicle quantity and predicted vehicle speed; The electric vehicle speed prediction layer predicts the speed of the electric vehicle on the road according to the congestion prediction data, the road environment data and the electric vehicle parameters to obtain the electric vehicle speed prediction data; the electric vehicle speed prediction data is time series data; The electric vehicle power prediction layer obtains the remaining power of the electric vehicle passing through the charging station at the end of the road subset based on the electric vehicle speed prediction data, vehicle power data, road environment data and personalized power usage parameter identification.

[0009] The charging demand prediction model includes a charging probability prediction layer, a charging parameter prediction layer and a charging demand calculation layer; The charging probability prediction layer predicts the charging probability of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; the charging station congestion data includes the number of electric vehicles at the charging station; The charging parameter prediction layer predicts the charging time of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; The charging demand calculation layer corrects the charging time according to the charging power to obtain a corrected charging time, and calculates the charging demand index according to the corrected charging time and the charging probability of the electric vehicle.

[0010] The process of determining the charging optimization parameters is as follows: obtaining the standard power and upper limit power of the charging pile; obtaining the charging demand index of electric vehicles passing through the charging station during the period; obtaining the road congestion coefficient based on the road congestion data of the road subset; obtaining the charging station congestion coefficient based on the charging station congestion data; and calculating the charging optimization parameters through the standard power and upper limit power of the charging pile, the charging demand index, the road congestion coefficient and the charging station congestion coefficient.

[0011] The process of identifying the road congestion coefficient is as follows: obtaining data such as vehicle type, vehicle quantity, vehicle speed and vehicle spacing on a road subset, and identifying the data through a neural network to obtain the road congestion coefficient; the process of identifying the charging station congestion coefficient is as follows: obtaining the coefficient based on the ratio of the number of electric vehicles in the charging station to the number of charging piles.

[0012] The process of obtaining the working coefficient is as follows: setting a cycle, identifying the charging optimization parameters within the charging station cycle, and obtaining the charging parameters of the historical cycle and the charging parameters of the current cycle; then predicting the charging parameters of the future cycle to obtain the predicted cycle charging parameters; assigning weights to the charging parameters of the historical cycle, the current cycle, and the predicted cycle, respectively, and calculating the working coefficient of the current cycle.

[0013] The historical cycle charging parameters, current cycle charging parameters and predicted cycle charging parameters are the charging powers of the charging station in the historical cycle, current cycle and predicted cycle respectively; the process of assigning weights to the historical cycle charging parameters, current cycle charging parameters and predicted cycle charging parameters is: the default initial weight is one-third, which is used to measure the impact of the working conditions of the charging station in the historical cycle, current cycle and predicted cycle; it can be adjusted according to the continuous working performance of the charging pile.

[0014] The method for determining the optimal solution is as follows: obtaining the working coefficient of the initial charging station of the road subset before the emergency power station is set up as the initial working coefficient; obtaining the working coefficient of the charging station at the end of the road subset as the end working coefficient; Obtain a preset plan for constructing emergency charging stations within a subset of roads and determine the locations of the emergency charging stations; Predict the data after the emergency charging station is set up to obtain the first working coefficient of the initial charging station of the road subset, the second working coefficient of the emergency charging station, and the third working coefficient of the terminal charging station of the road subset; The effect coefficient of the preset scheme is calculated based on the initial working coefficient, the terminal working coefficient, the first working coefficient, the second working coefficient and the third working coefficient; and the optimal scheme is determined based on the effect coefficient.

[0015] A user power consumption data calculation system based on power consumption demand, comprising: A charging station data acquisition module identifies electric vehicle charging stations on highways and obtains charging station parameters; the charging station parameters include charging station location, number of charging piles, charging power and charging station congestion data; The electric vehicle parameter acquisition module divides the highway according to the location of the charging station to obtain a road subset; obtains the electric vehicle parameters on the road subset, including the electric vehicle model, electric vehicle license plate, electric vehicle navigation route, vehicle power data and personalized power consumption parameters; The remaining power prediction module builds a remaining power prediction model, identifies the road environment data, road congestion data and electric vehicle parameters of the road subset, and obtains the remaining power of the electric vehicle when it passes the terminal charging pile; The charging demand optimization module builds a charging demand prediction model, identifies the electric vehicle's navigation route, remaining power, and road congestion data, and obtains the electric vehicle's charging demand index; and determines the charging optimization parameters of the charging station based on the charging demand index; The working state identification module calculates the working coefficient based on the charging optimization parameters, charging demand index and charging station congestion coefficient; The emergency plan identification module determines to set up an emergency charging station when the working coefficient exceeds the threshold; obtains the preset plan of the emergency charging station, and determines the optimal plan through the working coefficients before and after the emergency charging station is set up.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention divides the expressway according to the location of the charging station to obtain road subsets; constructs a remaining power prediction model, identifies the environmental data, congestion data and electric vehicle parameters of the road subset, and obtains electric vehicle speed prediction data based on the congestion situation of the road subset combined with the environmental data and electric vehicle parameter prediction; and then accurately identifies the remaining power of the electric vehicle based on the electric vehicle speed prediction data, vehicle power data, road environment data and personalized power consumption parameters.

[0017] 2. The present invention constructs a charging demand prediction model, identifies electric vehicle parameters, remaining power, road congestion data, road environment data and charging station parameters, and predicts the probability of electric vehicle charging and the charging time of the electric vehicle; corrects the charging time according to the charging power to obtain the corrected charging time, and obtains the charging demand index according to the charging time and the charging probability, so as to accurately identify the charging demand of the electric vehicle passing through the charging station.

[0018] 3. The present invention obtains the road congestion coefficient based on the congestion data of the road subset; obtains the charging station congestion coefficient based on the congestion data of the charging station; obtains the charging optimization parameters by calculating the standard power and upper limit power of the charging pile, the charging demand index, the road congestion coefficient and the charging station congestion coefficient; thereby accurately identifying the charging power of the charging station.

[0019] 4. The invention obtains the initial working coefficient and the terminal working coefficient of the road subset before the emergency power station is set up; predicts the data after the emergency charging station is set up to obtain the first working coefficient, the second working coefficient and the third working coefficient of the road subset; calculates the effect coefficient of the preset solution based on the initial working coefficient, the terminal working coefficient, the first working coefficient, the second working coefficient and the third working coefficient; based on the effect coefficient, the optimal solution can be accurately determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a flow chart of a method for calculating user power consumption data based on power consumption demand according to the present invention; Figure 2 It is a structural schematic diagram of the remaining power prediction model of the present invention; Figure 3 It is a structural schematic diagram of the charging demand prediction model of the present invention; Figure 4 The present invention is a schematic diagram of the structure of a user power consumption data calculation system based on power consumption demand. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Embodiment 1 The present invention proposes a method for calculating user electricity consumption data based on electricity demand, the process of which is as follows: Figure 1 As shown, including: S10. Identify electric vehicle charging stations on the highway and obtain charging station parameters; the charging station parameters include charging station location, number of charging piles, charging power and charging station congestion data.

[0023] S20. Divide the highway according to the location of the charging station to obtain a road subset; obtain electric vehicle parameters on the road subset, including electric vehicle model, electric vehicle license plate, electric vehicle navigation route, vehicle power data and personalized power usage parameters.

[0024] S30. Construct a remaining power prediction model, identify the road environment data, road congestion data and electric vehicle parameters of the road subset, and obtain the remaining power of the electric vehicle when it passes the terminal charging pile. The road environment data includes temperature data, wind data and humidity data in the road subset.

[0025] The remaining power prediction model is constructed based on a deep neural network, and its structure is as follows: Figure 2 As shown, it includes a vehicle route screening layer, a road congestion prediction layer, an electric vehicle speed prediction layer, and an electric vehicle power prediction layer; The vehicle route screening layer identifies the electric vehicle navigation route and determines the electric vehicle passing through the charging station; The road congestion prediction layer identifies road congestion data, including vehicle entry data, vehicle exit data, vehicle quantity, vehicle location and vehicle speed data; and then combines the road environment data of the road subset to predict congestion prediction data; the congestion prediction data includes the predicted vehicle quantity and predicted vehicle speed; The electric vehicle speed prediction layer predicts the speed of the electric vehicle on the road according to the congestion prediction data, the road environment data and the electric vehicle parameters to obtain the electric vehicle speed prediction data; The electric vehicle power prediction layer obtains the remaining power of the electric vehicle passing through the charging station at the end of the road subset based on the electric vehicle speed prediction data, vehicle power data, road environment data and personalized power usage parameter identification.

[0026] The present invention divides highways according to the locations of charging stations to obtain road subsets; constructs a remaining power prediction model, identifies environmental data, congestion data and electric vehicle parameters of the road subsets, and obtains electric vehicle speed prediction data based on the congestion situation of the road subsets in combination with environmental data and electric vehicle parameter predictions; and then accurately identifies the remaining power of the electric vehicle based on the electric vehicle speed prediction data, vehicle power data, road environment data and personalized power usage parameters.

[0027] S40. Construct a charging demand prediction model, identify the electric vehicle's navigation route, remaining power and road congestion data, and obtain the electric vehicle's charging demand index; determine the charging optimization parameters of the charging station based on the charging demand index.

[0028] The charging demand prediction model is constructed based on a deep neural network, and its structure is as follows: Figure 3 As shown; including charging probability prediction layer, charging parameter prediction layer and charging demand estimation layer; The charging probability prediction layer predicts the charging probability of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; the charging station congestion data includes the number of electric vehicles at the charging station; The charging parameter prediction layer predicts the charging time of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; The charging demand calculation layer corrects the charging time according to the charging power to obtain a corrected charging time, and calculates the charging demand index according to the corrected charging time and the charging probability of the electric vehicle.

[0029] The process of acquiring the charging demand index is as follows: according to the corrected charging time of the electric vehicle and the charging probability of the electric vehicle, the expected charging time is calculated and the expected charging time is used as the charging demand index.

[0030] ; in, represents the charging demand index; Indicates electric vehicle Corrected charging time; Indicates electric vehicle The probability of charging an electric vehicle; Indicates the number of electric vehicles.

[0031] The present invention constructs a charging demand prediction model, identifies electric vehicle parameters, remaining power, road congestion data, road environment data and charging station parameters, and predicts the charging probability and charging time of the electric vehicle; the charging time is corrected according to the charging power to obtain the corrected charging time, and a charging demand index is obtained according to the charging time and the charging probability, so as to accurately identify the charging demand of the electric vehicle passing through the charging station.

[0032] The process of determining the charging optimization parameters is as follows: obtaining the standard power and upper limit power of the charging pile; obtaining the charging demand index of electric vehicles passing through the charging station during the period; obtaining the road congestion coefficient based on the road congestion data of the road subset; obtaining the charging station congestion coefficient based on the charging station congestion data; and calculating the charging optimization parameters through the standard power and upper limit power of the charging pile, the charging demand index, the road congestion coefficient and the charging station congestion coefficient.

[0033] The calculation formula of the charging optimization parameter is: ; in, Indicates charging optimization parameters; Indicates the standard power of the charging pile; Indicates the upper limit power of the charging pile; Indicates the charging demand threshold, which is determined based on the number of charging piles and the average area occupied by the charging piles; represents the road congestion weight; represents the road congestion coefficient; represents the congestion weight of the charging station; represents the congestion coefficient of the charging station; Indicates electric vehicle Charging demand index; Indicates the number of electric vehicles; Represents an exponential function with a natural constant as its base.

[0034] The present invention obtains a road congestion coefficient based on congestion data of a road subset; obtains a charging station congestion coefficient based on congestion data of a charging station; obtains charging optimization parameters by calculating the standard power and upper limit power of a charging pile, a charging demand index, a road congestion coefficient, and a charging station congestion coefficient; thereby accurately identifying the charging power of the charging station.

[0035] S50. Calculate the working coefficient based on the charging optimization parameters, the charging demand index and the charging station congestion data.

[0036] The process of obtaining the working coefficient is as follows: set a cycle, identify the charging optimization parameters within the charging station cycle, obtain the historical cycle charging parameters and the current cycle charging parameters; then predict the charging parameters of the future cycle to obtain the predicted cycle charging parameters; assign weights to the historical cycle charging parameters, the current cycle charging parameters and the predicted cycle charging parameters respectively, and calculate the working coefficient of the current cycle. The calculation formula of the working coefficient is: ; in, represents the working coefficient; Indicates historical cycle charging parameters; represents the first parameter weight; Indicates the current cycle charging parameters; represents the second parameter weight; represents the predicted cycle charging parameters; represents the third parameter weight; Indicates the charging parameter threshold.

[0037] The charging parameter threshold is the standard charging power, which is determined according to the performance of the charging pile.

[0038] The present invention identifies the charging optimization parameters within the cycle of the charging station to obtain the charging parameters of the historical cycle and the charging parameters of the current cycle; then predicts the charging parameters of the future cycle to obtain the predicted cycle charging parameters; weights are respectively assigned to the charging parameters of the historical cycle, the charging parameters of the current cycle and the charging parameters of the predicted cycle to obtain the working coefficient of the current cycle; thus, the working state of the charging station can be accurately identified according to the spatiotemporal characteristics of the charging parameters of the charging station.

[0039] S60. When the working coefficient exceeds the threshold, determine to set up an emergency charging station; obtain a preset plan for the emergency charging station, and determine the optimal plan based on the working coefficients before and after the emergency charging station is set up.

[0040] The method for determining the optimal solution is as follows: obtaining the working coefficient of the initial charging station of the road subset before the emergency power station is set up as the initial working coefficient; obtaining the working coefficient of the charging station at the end of the road subset as the end working coefficient; Obtain a preset plan for constructing emergency charging stations within a subset of roads and determine the locations of the emergency charging stations; Predict the data after the emergency charging station is set up to obtain the first working coefficient of the initial charging station of the road subset, the second working coefficient of the emergency charging station, and the third working coefficient of the terminal charging station of the road subset; The effect coefficient of the preset scheme is calculated based on the initial working coefficient, the terminal working coefficient, the first working coefficient, the second working coefficient and the third working coefficient; and the optimal scheme is determined based on the effect coefficient.

[0041] The calculation formula of the effect coefficient is: ; in, represents the effect coefficient; represents the variance function; represents the initial working coefficient; represents the end point working coefficient; represents the first working coefficient; represents the second duty factor; represents the third duty factor; represents the averaging function; Indicates the duty factor threshold.

[0042] The operating coefficient threshold is determined by an average of the operating coefficients of all charging stations on the highway.

[0043] The present invention obtains the initial working coefficient and the terminal working coefficient of the road subset before the emergency power station is set up; predicts the data after the emergency charging station is set up to obtain the first working coefficient, the second working coefficient and the third working coefficient of the road subset; calculates the effect coefficient of the preset solution according to the initial working coefficient, the terminal working coefficient, the first working coefficient, the second working coefficient and the third working coefficient; and according to the effect coefficient, the optimal solution can be accurately determined.

[0044] The present invention also proposes a user power consumption data calculation system based on power consumption demand, the structure of which is as follows: Figure 4 As shown, including: A charging station data acquisition module identifies electric vehicle charging stations on highways and obtains charging station parameters; the charging station parameters include charging station location, number of charging piles, charging power and charging station congestion data; The electric vehicle parameter acquisition module divides the highway according to the location of the charging station to obtain a road subset; obtains the electric vehicle parameters on the road subset, including the electric vehicle model, electric vehicle license plate, electric vehicle navigation route, vehicle power data and personalized power consumption parameters; The remaining power prediction module builds a remaining power prediction model, identifies the road environment data, road congestion data and electric vehicle parameters of the road subset, and obtains the remaining power of the electric vehicle when it passes the terminal charging pile; The charging demand optimization module builds a charging demand prediction model, identifies the electric vehicle's navigation route, remaining power, and road congestion data, and obtains the electric vehicle's charging demand index; and determines the charging optimization parameters of the charging station based on the charging demand index; The working state identification module calculates the working coefficient based on the charging optimization parameters, charging demand index and charging station congestion coefficient; The emergency plan identification module determines to set up an emergency charging station when the working coefficient exceeds the threshold; obtains the preset plan of the emergency charging station, and determines the optimal plan through the working coefficients before and after the emergency charging station is set up.

[0045] The present invention identifies the electric vehicle charging station on the highway to obtain the charging station parameters; divides the highway according to the location of the charging station to obtain a road subset, and obtains the electric vehicle parameters on the road subset; identifies the road environment data, road congestion data and electric vehicle parameters of the road subset to obtain the remaining power of the electric vehicle when passing the terminal charging pile; identifies the navigation route, remaining power and road congestion data of the electric vehicle to obtain the charging demand index of the electric vehicle; determines the charging optimization parameters of the charging station according to the charging demand index; calculates the working coefficient according to the charging optimization parameters, the charging demand index and the charging station congestion data; and determines the optimal solution of the emergency charging station according to the working coefficient. The present invention realizes the efficiency optimization of the charging station through the charging demand index and the working coefficient.

[0046] Embodiment 2 The present invention proposes a method for calculating user electricity consumption data based on electricity demand, the process of which is as follows: Figure 1 As shown, including: S10. Identify electric vehicle charging stations on the highway and obtain charging station parameters; the charging station parameters include charging station location, number of charging piles, charging power and charging station congestion data.

[0047] S20. Divide the highway according to the location of the charging station to obtain a road subset; obtain electric vehicle parameters on the road subset, including electric vehicle model, electric vehicle license plate, electric vehicle navigation route, vehicle power data and personalized power usage parameters.

[0048] S30. Construct a remaining power prediction model, identify the road environment data, road congestion data and electric vehicle parameters of the road subset, and obtain the remaining power of the electric vehicle when it passes the terminal charging pile.

[0049] The remaining power prediction model includes a vehicle route screening layer, a road congestion prediction layer, an electric vehicle speed prediction layer, and an electric vehicle power prediction layer; The vehicle route screening layer identifies the electric vehicle navigation route and determines the electric vehicle passing through the charging station; The road congestion prediction layer identifies road congestion data, including vehicle entry data, vehicle exit data, vehicle quantity, vehicle location and vehicle speed data; and then combines the road environment data of the road subset to predict congestion prediction data; the congestion prediction data includes the predicted vehicle quantity and predicted vehicle speed; The electric vehicle speed prediction layer predicts the speed of the electric vehicle on the road according to the congestion prediction data, the road environment data and the electric vehicle parameters to obtain the electric vehicle speed prediction data; the electric vehicle speed prediction data is time series data; The electric vehicle power prediction layer obtains the remaining power of the electric vehicle passing through the charging station at the end of the road subset based on the electric vehicle speed prediction data, vehicle power data, road environment data and personalized power usage parameter identification.

[0050] During the driving of electric vehicles, the power consumption is closely related to the speed data of electric vehicles; the parameters of electric vehicles in smooth and congested road conditions are tested to obtain data table 1. Among them, the proportion of personalized power consumption is the proportion of personalized power consumption parameters, including air conditioners, audio equipment, etc.

[0051] Table 1 Electric vehicle power consumption test data table

[0052] It can be seen from Table 1 that compared with smooth road conditions, under congested road conditions, the average speed of electric vehicles decreases and the power consumption per 100 kilometers increases; the braking recovery of electric vehicles decreases; and the proportion of personalized electricity consumption increases.

[0053] The present invention divides highways according to the locations of charging stations to obtain road subsets; constructs a remaining power prediction model, identifies environmental data, congestion data and electric vehicle parameters of the road subsets, and obtains electric vehicle speed prediction data based on the congestion situation of the road subsets in combination with environmental data and electric vehicle parameter predictions; and then accurately identifies the remaining power of the electric vehicle based on the electric vehicle speed prediction data, vehicle power data, road environment data and personalized power usage parameters.

[0054] S40. Construct a charging demand prediction model, identify the electric vehicle's navigation route, remaining power and road congestion data, and obtain the electric vehicle's charging demand index; determine the charging optimization parameters of the charging station based on the charging demand index.

[0055] The charging demand prediction model includes a charging probability prediction layer, a charging parameter prediction layer and a charging demand calculation layer; The charging probability prediction layer predicts the charging probability of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; the charging station congestion data includes the number of electric vehicles at the charging station; The charging parameter prediction layer predicts the charging time of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; The charging demand calculation layer corrects the charging time according to the charging power to obtain a corrected charging time, and calculates the charging demand index according to the corrected charging time and the charging probability of the electric vehicle.

[0056] The present invention constructs a charging demand prediction model, identifies electric vehicle parameters, remaining power, road congestion data, road environment data and charging station parameters, and predicts the charging probability and charging time of the electric vehicle; the charging time is corrected according to the charging power to obtain the corrected charging time, and a charging demand index is obtained according to the charging time and the charging probability, so as to accurately identify the charging demand of the electric vehicle passing through the charging station.

[0057] The process of determining the charging optimization parameters is as follows: obtaining the standard power and upper limit power of the charging pile; obtaining the charging demand index of electric vehicles passing through the charging station during the period; obtaining the road congestion coefficient based on the road congestion data of the road subset; obtaining the charging station congestion coefficient based on the charging station congestion data; and calculating the charging optimization parameters through the standard power and upper limit power of the charging pile, the charging demand index, the road congestion coefficient and the charging station congestion coefficient.

[0058] The calculation formula of the charging optimization parameter is: ; in, Indicates charging optimization parameters; Indicates the standard power of the charging pile; Indicates the upper limit power of the charging pile; Indicates the charging demand threshold, which is determined based on the number of charging piles and the average area occupied by the charging piles; represents the road congestion weight; represents the road congestion coefficient; represents the congestion weight of the charging station; represents the congestion coefficient of the charging station; Indicates electric vehicle Charging demand index; Indicates the number of electric vehicles; Represents an exponential function with a natural constant as its base.

[0059] In order to verify the actual effect of the charging optimization parameters of this application, a fixed charging power is adopted as a comparison scheme; data Table 2 is obtained through comparative testing.

[0060] Table 2 Charging optimization parameter effect verification data table

[0061] Among them, the queuing time is the average of the queuing time before the electric vehicle is charged; the peak-to-valley difference of the power grid is obtained according to the peak value and valley value of the power grid; the utilization rate of the charging pile is determined according to the charging time of the charging pile. It can be obtained from the data in Table 2 that by adopting the charging optimization parameters described in the present invention, the queuing time of electric vehicle charging can be effectively reduced, the peak-to-valley difference of the power grid can be reduced, and the utilization rate of the charging pile can be improved at the same time.

[0062] The present invention obtains a road congestion coefficient based on congestion data of a road subset; obtains a charging station congestion coefficient based on congestion data of a charging station; obtains charging optimization parameters by calculating the standard power and upper limit power of a charging pile, a charging demand index, a road congestion coefficient, and a charging station congestion coefficient; thereby accurately identifying the charging power of the charging station.

[0063] S50. Calculate the working coefficient based on the charging optimization parameters, the charging demand index and the charging station congestion data.

[0064] The process of obtaining the working coefficient is as follows: setting a cycle, identifying the charging optimization parameters within the charging station cycle, and obtaining the charging parameters of the historical cycle and the charging parameters of the current cycle; then predicting the charging parameters of the future cycle to obtain the predicted cycle charging parameters; assigning weights to the charging parameters of the historical cycle, the current cycle, and the predicted cycle, respectively, and calculating the working coefficient of the current cycle.

[0065] The calculation formula of the working coefficient is: ; in, represents the working coefficient; Indicates historical cycle charging parameters; represents the first parameter weight; Indicates the current cycle charging parameters; represents the second parameter weight; represents the predicted cycle charging parameters; represents the third parameter weight; Indicates the charging parameter threshold.

[0066] The present invention identifies the charging optimization parameters within the cycle of the charging station to obtain the charging parameters of the historical cycle and the charging parameters of the current cycle; then predicts the charging parameters of the future cycle to obtain the predicted cycle charging parameters; weights are respectively assigned to the charging parameters of the historical cycle, the charging parameters of the current cycle and the charging parameters of the predicted cycle to obtain the working coefficient of the current cycle; thus, the working state of the charging station can be accurately identified according to the spatiotemporal characteristics of the charging parameters of the charging station.

[0067] S60. When the working coefficient exceeds the threshold, determine to set up an emergency charging station; obtain a preset plan for the emergency charging station, and determine the optimal plan based on the working coefficients before and after the emergency charging station is set up.

[0068] The method for determining the optimal solution is as follows: obtaining the working coefficient of the initial charging station of the road subset before the emergency power station is set up as the initial working coefficient; obtaining the working coefficient of the charging station at the end of the road subset as the end working coefficient; Obtain a preset plan for constructing emergency charging stations within a subset of roads and determine the locations of the emergency charging stations; Predict the data after the emergency charging station is set up to obtain the first working coefficient of the initial charging station of the road subset, the second working coefficient of the emergency charging station, and the third working coefficient of the terminal charging station of the road subset; The effect coefficient of the preset scheme is calculated based on the initial working coefficient, the terminal working coefficient, the first working coefficient, the second working coefficient and the third working coefficient; and the optimal scheme is determined based on the effect coefficient.

[0069] The present invention obtains the initial working coefficient and the terminal working coefficient of the road subset before the emergency power station is set up; predicts the data after the emergency charging station is set up to obtain the first working coefficient, the second working coefficient and the third working coefficient of the road subset; calculates the effect coefficient of the preset solution according to the initial working coefficient, the terminal working coefficient, the first working coefficient, the second working coefficient and the third working coefficient; and according to the effect coefficient, the optimal solution can be accurately determined.

[0070] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for calculating user electricity consumption data based on electricity demand, characterized in that: include: S10. Identify the electric vehicle charging station on the highway and obtain the charging station parameters; the charging station parameters include the location of the charging station, the number of charging piles, the charging power and the charging station congestion data; S20. Divide the highway according to the location of the charging station to obtain a road subset; obtain electric vehicle parameters on the road subset, including electric vehicle model, electric vehicle license plate, electric vehicle navigation route, vehicle power data and personalized power consumption parameters; S30. Construct a remaining power prediction model, identify the road environment data, road congestion data and electric vehicle parameters of the road subset, and obtain the remaining power of the electric vehicle when it passes the terminal charging pile; S40. Construct a charging demand prediction model, identify the electric vehicle navigation route, remaining power and road congestion data, and obtain the charging demand index of the electric vehicle; determine the charging optimization parameters of the charging station according to the charging demand index; S50. Calculate the working coefficient based on the charging optimization parameters, the charging demand index and the charging station congestion data; S60. When the working coefficient exceeds the threshold, determine to set up an emergency charging station; obtain a preset plan for the emergency charging station, and determine the optimal plan based on the working coefficients before and after the emergency charging station is set up.

2. A method for calculating user power consumption data based on power demand according to claim 1, characterized in that: The remaining power prediction model includes a vehicle route screening layer, a road congestion prediction layer, an electric vehicle speed prediction layer, and an electric vehicle power prediction layer; The vehicle route screening layer identifies the electric vehicle navigation route and determines the electric vehicle passing through the charging station; The road congestion prediction layer identifies road congestion data, including vehicle entry data, vehicle exit data, vehicle quantity, vehicle location and vehicle speed data; and then combines the road environment data of the road subset to predict congestion prediction data; the congestion prediction data includes the predicted vehicle quantity and predicted vehicle speed; The electric vehicle speed prediction layer predicts the speed of the electric vehicle on the road according to the congestion prediction data, the road environment data and the electric vehicle parameters to obtain the electric vehicle speed prediction data; the electric vehicle speed prediction data is time series data; The electric vehicle power prediction layer obtains the remaining power of the electric vehicle passing through the charging station at the end of the road subset based on the electric vehicle speed prediction data, vehicle power data, road environment data and personalized power usage parameter identification.

3. A method for calculating user power consumption data based on power demand according to claim 1, characterized in that: The charging demand prediction model includes a charging probability prediction layer, a charging parameter prediction layer and a charging demand calculation layer; The charging probability prediction layer predicts the charging probability of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; the charging station congestion data includes the number of electric vehicles at the charging station; The charging parameter prediction layer predicts the charging time of the electric vehicle based on the electric vehicle parameters, the remaining power, the road congestion data, the road environment data and the charging station parameters; The charging demand calculation layer corrects the charging time according to the charging power to obtain a corrected charging time, and calculates the charging demand index according to the corrected charging time and the charging probability of the electric vehicle.

4. The method for calculating user power consumption data based on power demand according to claim 1, characterized in that: The process of determining the charging optimization parameters is as follows: obtaining the standard power and upper limit power of the charging pile; obtaining the charging demand index of electric vehicles passing through the charging station during the period; obtaining the road congestion coefficient based on the road congestion data of the road subset; obtaining the charging station congestion coefficient based on the charging station congestion data; and calculating the charging optimization parameters through the standard power and upper limit power of the charging pile, the charging demand index, the road congestion coefficient and the charging station congestion coefficient.

5. The method for calculating user power consumption data based on power demand according to claim 1, characterized in that: The process of obtaining the working coefficient is as follows: identifying the charging optimization parameters within the charging station cycle to obtain the historical cycle charging parameters and the current cycle charging parameters; then predicting the charging parameters of the future cycle to obtain the predicted cycle charging parameters; Weights are assigned to the charging parameters of the historical cycle, the current cycle and the predicted cycle respectively, and the working coefficient of the current cycle is calculated.

6. A method for calculating user power consumption data based on power demand according to claim 1, characterized in that: The method for determining the optimal solution is as follows: obtaining the working coefficient of the initial charging station of the road subset before the emergency power station is set up as the initial working coefficient; obtaining the working coefficient of the charging station at the end of the road subset as the end working coefficient; Obtain a preset plan for constructing emergency charging stations within a subset of roads and determine the locations of the emergency charging stations; Predict the data after the emergency charging station is set up to obtain the first working coefficient of the initial charging station of the road subset, the second working coefficient of the emergency charging station, and the third working coefficient of the terminal charging station of the road subset; The effect coefficient of the preset scheme is calculated based on the initial working coefficient, the terminal working coefficient, the first working coefficient, the second working coefficient and the third working coefficient; and the optimal scheme is determined based on the effect coefficient.

7. A user electricity consumption data calculation system based on electricity demand, characterized in that: include: A charging station data acquisition module identifies electric vehicle charging stations on highways and obtains charging station parameters; the charging station parameters include charging station location, number of charging piles, charging power and charging station congestion data; The electric vehicle parameter acquisition module divides the highway according to the location of the charging station to obtain a road subset; obtains the electric vehicle parameters on the road subset, including the electric vehicle model, electric vehicle license plate, electric vehicle navigation route, vehicle power data and personalized power consumption parameters; The remaining power prediction module builds a remaining power prediction model, identifies the road environment data, road congestion data and electric vehicle parameters of the road subset, and obtains the remaining power of the electric vehicle when it passes the terminal charging pile; The charging demand optimization module builds a charging demand prediction model, identifies the electric vehicle's navigation route, remaining power, and road congestion data, and obtains the electric vehicle's charging demand index; and determines the charging optimization parameters of the charging station based on the charging demand index; The working state identification module calculates the working coefficient based on the charging optimization parameters, charging demand index and charging station congestion coefficient; The emergency plan identification module determines to set up an emergency charging station when the working coefficient exceeds the threshold; obtains the preset plan of the emergency charging station, and determines the optimal plan through the working coefficients before and after the emergency charging station is set up.

Images