A method and system for establishing an electricity price model based on electric vehicle data analysis

Abstract

The application discloses a kind of electric price model establishment method and system based on electric automobile data analysis, mainly related to the application technical field of electric price model in electric automobile data analysis. Including the following steps: collecting the charging time, frequency and charging quantity information of different car owners to electric automobile, and combining the collected information with traffic congestion situation, to build electric automobile charging demand model;Through the charging load obtained by electric automobile charging demand model, establish the traffic congestion degree electric price mechanism in the area and determine the traffic congestion degree coefficient;Using SS-AE to carry out threshold self-adaptive calculation of traffic congestion degree coefficient;Set up the feedback mechanism of car owner's personal charging intention, determine the charging / discharging intention index, and establish a dynamic electric price model.The beneficial effects of the present application are that it can relieve traffic congestion while optimizing power grid load distribution and improving overall system efficiency.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of application of an electricity price model in electric vehicle data analysis, and particularly relates to an electricity price model establishment method and system based on electric vehicle data analysis. BACKGROUND

[0002] With the continuous advancement of urbanization and the rapid increase of vehicle ownership, traffic congestion problems are becoming increasingly serious, and at the same time, the popularity rate of electric vehicles is increasing year by year. Although electric vehicles have significant advantages in reducing carbon emissions and reducing energy consumption, the charging demand of electric vehicles also brings new challenges to the power grid. Therefore, how to effectively manage the charging behavior of electric vehicles to alleviate traffic congestion and power grid pressure has become one of the current problems to be solved.

[0003] At present, a variety of technologies and methods have been used to solve the problems of electric vehicle charging and traffic congestion, such as time-of-use electricity price, smart grid charging / discharging load management and the like. Although the above technologies can alleviate the problems of electric vehicle charging and traffic congestion to a certain extent, there are still the following deficiencies:

[0004] Most of the existing electricity price models lack a dynamic adjustment mechanism and cannot respond to changes in charging demand of vehicle owners and traffic conditions in a timely manner. In addition, the existing solutions usually do not fully consider the individual charging willingness of electric vehicle owners, resulting in poor user experience and difficulty in achieving optimal scheduling effect. There is a lack of effective integration between traffic management and power management systems, making it difficult for them to work together and failing to fully realize the overall benefits.

[0005] Therefore, there is an urgent need for a dynamic charging / discharging electricity price model that comprehensively considers traffic congestion and individual charging willingness of electric vehicle owners to solve the above problems. SUMMARY

[0006] The application aims to provide an electricity price model establishment method and system based on electric vehicle data analysis, which can alleviate traffic congestion while optimizing power grid load distribution and improving overall system efficiency.

[0007] To achieve the above-mentioned purpose, the application realizes the following technical scheme:

[0008] On the one hand, the application provides an electricity price model establishment method based on electric vehicle data analysis, which includes the following steps:

[0009] S1: Collect charging time, frequency and charging amount information of electric vehicles of different vehicle owners, and combine the collected information with traffic congestion conditions to build an electric vehicle charging demand model;

[0010] S2: Obtain the charging load by the charging demand model of the electric vehicle in step S1, establish the traffic congestion degree price mechanism in the transformer area and determine the traffic congestion degree coefficient;

[0011] S3: Use SS-AE to perform threshold adaptive calculation of the traffic congestion degree coefficient;

[0012] S4: Set the personal charging intention feedback mechanism of the vehicle owner, determine the charging / discharging intention index, and establish a dynamic price model.

[0013] Preferably, in step S1, the electric vehicle charging demand model is constructed, including:

[0014] The probability distribution model of the initial charging time period and the probability model of the daily driving distance are used to describe the power consumption behavior of the electric vehicle:

[0015]

[0016] Wherein, t s represents the end charging time, μ s represents the average end charging time, σ s represents the standard deviation of the end charging time;

[0017] The driving distance is:

[0018]

[0019] Wherein, l represents the driving distance, σ l represents the standard deviation of the driving distance, μ l represents the average value of the driving distance;

[0020] The charging time calculation formula is:

[0021]

[0022] Wherein, T c represents the charging time, e represents the electric energy consumed by the electric vehicle per 100 kilometers of driving, P c represents the charging power of the electric vehicle, and ηc represents the charging efficiency of the electric vehicle;

[0023] The electric vehicle is sampled, and the daily basic charging load of the electric vehicle is calculated:

[0024] W c = P c T c

[0025] Wherein, W c is the charging load.

[0026] Preferably, in the step S2, the traffic congestion degree pricing mechanism in the station area is established and the traffic congestion degree coefficient is determined, comprising:

[0027] The traffic congestion degree in the station area is defined as:

[0028]

[0029] wherein, V i，t represents the average speed of the i-th station area at t time, V i，max represents the routine speed of the i-th station area, ρ i，t represents the traffic density of the i-th station area at t time, ρ i，max represents the maximum traffic density of the i-th station area;

[0030] The traffic congestion coefficient is denoted as: TPF,

[0031]

[0032] When TPF≥M, it indicates that the traffic in the station area is not congested, and when TPF

[0033] Preferably, the SS-AE includes two AEs, each of which includes an encoder and a decoder, and the encoder and the decoder are each composed of three dense layers, and the encoder part includes:

[0034] δ and δ' represent the historical traffic congestion coefficient and the real-time traffic congestion coefficient, respectively, r and r' represent the reconstruction of the historical traffic congestion coefficient and the real-time traffic congestion coefficient through the SS-AE, respectively, r and r' are the latent representations of δ and δ', respectively, r is represented as:

[0035] r = μ ε (δ) + σ ε (δ) ⊙ η

[0036]

[0037] The posterior probability q ε (r|δ,1) is:

[0038] q ε (r|δ,1) ~ N(r|μ ε (δ), σ 2 (δ))

[0039] The posterior probability of the low-confidence sample is represented as:

[0040]

[0041] The decoder part includes:

[0042] The decoder in the SS-AE is regarded as a conditional probability distribution model represents Based on the reconstruction of r to δ:

[0043]

[0044] The loss function of the conversion reconstruction is represented as:

[0045]

[0046] By maximizing Optimize the parameters of the decoder, D KL (q ε (r|δ,1)||p φ (r)) represents the KL divergence between q ε (r|δ,1) and p φ (r);

[0047] The reconstruction error between δ and δ' is ||δ-δ'| 2 , The reconstruction error between δ and δ' is ||δ-δ'|

[0048] Solve the threshold value M of the traffic congestion coefficient:

[0049]

[0050] Preferably, in the step S4, the charge / discharge willingness index, specifically the owner's response charge / discharge willingness index, is represented as:

[0051] W j，t = W j，or + SoC j，t

[0052] Wherein, W j，t represents the response charge / discharge willingness index of the jth electric vehicle, W j，or represents the charge / discharge willingness of the owner of the jth electric vehicle;

[0053] The dynamic electricity price model includes: establishing a charging price model and a discharging price model, establishing a charging price model, including:

[0054]

[0055] Wherein, is the charging price of the jth electric vehicle at time t, C t is the basic charging price in the transformer area at time t, a penalty price generated by charging congestion in the substation area for the t period, j，t SiC is the initial charging time t of the jth electric vehicle, a penalty price generated by whether the jth electric vehicle responds to scheduling,

[0056] establishing a discharge price model, comprising:

[0057]

[0058] wherein, D is the discharge price of the jth electric vehicle at time t, t D is the basic discharge price in the substation area at time t, a penalty price generated by charging congestion in the substation area for the t period, a penalty price generated by whether the jth electric vehicle responds to scheduling.

[0059] On the other hand, a system based on the above-mentioned electric vehicle data analysis-based price model establishment method is provided, comprising:

[0060] The data acquisition and electric vehicle charging demand model construction module is used to acquire the charging time, frequency and charging quantity information of different vehicle owners for electric vehicles, and combine the acquired information with traffic congestion conditions to construct an electric vehicle charging demand model.

[0061] The traffic congestion coefficient threshold calculation module is used to obtain the charging load quantity from the electric vehicle charging demand model, establish a traffic congestion price mechanism in the substation area and determine the traffic congestion coefficient; and the SS-AE is used for threshold adaptive calculation of the traffic congestion coefficient.

[0062] The dynamic price model construction module is used to set a vehicle owner personal charging willingness feedback mechanism, determine a charging / discharging willingness index, and establish a dynamic price model.

[0063] Compared with the prior art, the present application has the following advantages:

[0064] 1. Peak load shaving of the power grid is realized, and the pressure on the power grid is relieved: the dynamic price model adjusts the price to guide the vehicle owners to charge when the load of the power grid is low, thereby balancing the load of the power grid and avoiding the collapse of the power system;

[0065] 2. Traffic congestion conditions are optimized: the model considers traffic congestion conditions, and through dynamic price incentives, the vehicle owners are encouraged to charge during off-peak hours, reducing the traffic pressure during peak hours, for example, during the traffic peak period, the charging cost is higher, and the vehicle owners are more inclined to charge during off-peak hours, thereby reducing the travel volume during peak hours;

[0066] 3. Reduce charging costs for car owners: Through dynamic electricity pricing, car owners can choose to charge during periods of lower electricity prices, thereby reducing charging costs. In particular, for private car owners, the reduction in charging costs can significantly increase their enthusiasm for using electric vehicles and improve their economic benefits. It can even increase the market acceptance of electric vehicles, which is of great significance for promoting the popularization and development of electric vehicles. Attached Figure Description

[0067] Figure 1 This is the main view of the method flow of the present invention;

[0068] Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0069] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be understood that after reading the teachings of this invention, those skilled in the art can make various alterations or modifications to the invention, and these equivalent forms also fall within the scope defined in this application.

[0070] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.

[0071] In this invention, terms such as "fixed connection," "connected," and "linked" should be interpreted broadly, indicating a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can determine the specific meaning of these terms in this invention based on the specific circumstances, and they should not be construed as limitations on the invention.

[0072] Example:

[0073] like Figure 1 As shown, this embodiment provides a method for establishing an electricity price model based on electric vehicle data analysis, including the following steps:

[0074] S1: Collect information on the charging time, frequency, and amount of electric vehicles from different car owners, and combine the collected information with traffic congestion to build an electric vehicle charging demand model;

[0075] S2: Establish the traffic congestion degree price mechanism in the transformer area and determine the traffic congestion degree coefficient by the charging load obtained from the electric vehicle charging demand model in step S1;

[0076] S3: Threshold adaptive calculation of traffic congestion degree coefficient using SS-AE;

[0077] S4: Set up the personal charging willingness feedback mechanism of the car owner, determine the charging / discharging willingness index, and establish the dynamic price model.

[0078] In step S1, the electric vehicle charging demand model is constructed, including:

[0079] The charging load of the electric vehicle private car usually depends on the driving and charging habits of the car owner, and lacks obvious rules. Therefore, the probability distribution model of the initial charging time period and the probability model of the daily driving mileage are used to describe the electricity consumption behavior in this embodiment:

[0080]

[0081] Wherein, t s represents the end charging time, μ s represents the average end charging time, σ s represents the standard deviation of the end charging time,

[0082] The formal mileage is as follows:

[0083]

[0084] Wherein, l represents the driving mileage, σ l represents the standard deviation of the driving mileage, μ l represents the average value of the driving mileage, and the charging time of the private car is calculated as follows:

[0085]

[0086] Wherein, T c represents the charging time, e represents the electric energy consumed by the electric vehicle per 100 kilometers of driving, P c represents the charging power of the electric vehicle, η c represents the charging efficiency of the electric vehicle,

[0087] The Monte Carlo method is used to sample the private car to determine the starting charging time and charging duration, so as to calculate the daily basic charging load of the private car:

[0088] W c = P c T c

[0089] Wherein, W c is the charging load;

[0090] Since the operation time of taxi and bus is long and the driving mileage is large, the electricity consumption mode of these two types of electric vehicles is regular. Assuming that they need to be charged twice a day, the SoC and time of charging start are normally distributed, as shown in Table 1:

[0091] Table 1 Taxi and bus charging start time and SoC distribution

[0092]

[0093]

[0094] t1, t2, t3, t4 represent the expectation of the charging start and end time of taxis and buses respectively; σ t1 , σ t2 , σ t3 , σ t4 represent the variance of the charging start and end time of taxis and buses; SoC1, SoC2 represent the expectation of the SoC of the charging start and end time of taxis and buses respectively; represent the variance of the SoC of the charging start and end time of taxis and buses respectively,

[0095] The charging duration of taxis and buses is:

[0096]

[0097] where SoC e is the percentage of the remaining electric quantity of the two types of electric vehicles, C e is the battery capacity, η e is the charging efficiency of the two types of electric vehicles P e is the charging power of the two types of electric vehicles;

[0098] The charging load models of private cars, taxis and buses are established in order to analyze the dynamic electricity price in the future.

[0099] The charging demand of electric vehicles has a significant impact on the grid load, especially during peak hours. By developing a dynamic electricity price strategy, car owners can be guided to charge during periods of low grid load, thereby balancing the grid load and reducing the pressure on the grid. At the same time, a reasonable electricity price strategy can reduce the charging cost of car owners. According to the charging demand and the charging willingness of car owners, they can flexibly choose when and where to charge.

[0100] Since various types of electric vehicles are more mobile and do not have fixed charging / discharging areas, it is necessary to set a congestion price for each charging / discharging area. By monitoring the congestion degree of each charging pile in the area in real time, the charging / discharging price is dynamically adjusted to adapt to the free and dispersed charging behavior of users in different areas. When the traffic condition of a certain area becomes congested, the charging price will rise, and the discharging compensation price will decrease to encourage users to choose other areas for charging or discharging, thereby relieving the traffic congestion problem in the area. Through this congestion price mechanism, the charging / discharging resources can be optimized, and the charging / discharging efficiency of the distribution network can be improved. Therefore, steps S2-S3 include:

[0101] 1. Definition of traffic congestion degree in the area:

[0102]

[0103] where V i，t represents the average speed of the i-th area at time t, V i，max represents the routine speed of the i-th area, and p i，t represents the traffic density of the i-th area at time t, p i，max represents the maximum traffic density of the i-th area. In order to quantitatively analyze the traffic congestion condition of different areas, a traffic congestion coefficient (Traffic Performance Factor, TPF) is introduced to digitally analyze the traffic congestion condition:

[0104]

[0105] When TPF≥M, it indicates that the traffic in the area is not congested, and when TPF<M, it indicates that the traffic in the area is congested, where M is the threshold value of the traffic congestion coefficient;

[0106] 2. Adaptive solution of the threshold value M of the traffic congestion coefficient:

[0107] Between the demand for electric vehicle charging and the management of power grid load, optimizing charging resources and improving the efficiency of distribution network is the key. In order to achieve this goal, the embodiment proposes a method of threshold adaptive calculation using SS-AE. SS-AE determines the traffic congestion threshold value adaptively, dynamically adjusts the price strategy, and optimizes the charging / discharging behavior;

[0108] Specifically, SS-AE consists of two Autoencoders (AEs). Each AE contains an encoder and a decoder, and the encoder and the decoder are composed of three dense layers. The two encoders share weights and have the same structure, and the two decoders also have the same structure. The core of SS-AE lies in its ability to adaptively determine the threshold value.

[0109] In the application of electric vehicle charging substation management, SS-AE learns and identifies the charging behavior patterns in the substation by using real-time monitoring data. SS-AE will dynamically adjust the charging price and discharge compensation price of the substation according to the threshold value calculated by itself. In this way, when a certain substation becomes crowded, the charging price rises, and the discharge compensation price decreases, encouraging users to choose other substation for charging and discharging, thereby effectively alleviating traffic congestion problems.

[0110] where the encoder part is:

[0111] δ, δ' represent historical and real-time traffic congestion coefficients, respectively, r, r' represent the reconstruction of historical and real-time traffic congestion coefficients by SS-AE, respectively, r, r' are the latent representations of δ, δ', respectively, is represented as:

[0112] r = μ ε (δ) + σ ε (δ) ⊙ η

[0113]

[0114] Posterior probability q ε (r|δ,1):

[0115] q ε (r|δ,1) ~ N(r|μ ε (δ), σ 2 (δ))

[0116] The posterior probability of low confidence samples is represented as:

[0117]

[0118] Decoder part:

[0119] The decoder in SS-AE is considered as a conditional probability distribution model is represented as: Based on the reconstruction of r to δ:

[0120]

[0121] The loss function of the reconstruction is represented as:

[0122]

[0123] By maximizing the parameters of the decoder D KL (q ε (r|δ,1)||p φ (r)) represents qε (r|δ, 1) and p φ KL divergence between (r) and p

[0124] reconstruction error between δ and δ' is ||δ-δ'| 2 , reconstruction error between δ and δ' is ||δ-δ'|

[0125] Solve the threshold M of the traffic congestion coefficient:

[0126]

[0127] The embodiment uses the above formula to balance the historical traffic data and the real-time traffic data, and solves the threshold M of the traffic congestion coefficient based on the historical data and the real-time data.

[0128] Define the willingness index of the owner to respond to charging / discharging:

[0129] W j，t = W j，or + SoC j，t

[0130] wherein W j，t represents the response willingness index of the jth electric vehicle to charging / discharging, and W j，or represents the charging / discharging willingness of the owner of the jth electric vehicle;

[0131] The charging / discharging willingness of the owner is affected by multiple factors, mainly including the battery capacity, the remaining driving distance of the vehicle, and the road traffic condition. Specifically, when the road traffic is smooth, the owner will feel higher flexibility, and the movement of the vehicle in the region and between regions is not limited, so the charging willingness of the owner is relatively high, and the discharging willingness may also increase, especially when the system needs power, at this time, the electric vehicle as a mobilizable resource for adjusting energy demand can quickly respond and participate in the charging / discharging scheduling;

[0132] And in the case of road congestion, due to the decrease of vehicle speed and the increase of traffic density, the flexibility of the vehicle decreases, and the owner will tend to reserve the power to ensure that the vehicle can smoothly complete the travel task, so the charging / discharging willingness index will decrease accordingly, because the owner is worried that the vehicle cannot reach the charging station in time or affect the own travel due to insufficient power or road congestion during the driving process, therefore, the charging demand and the discharging willingness may be significantly weakened in traffic congestion, or even completely unwilling to participate in the charging / discharging scheduling;

[0133] From the above situation, it can be seen that the charging / discharging willingness index of the owner is not only affected by the vehicle power, but also affected by the traffic condition and the travel demand, and further affects the response ability of the electric vehicle as an energy adjustment resource;

[0134] When the road congestion is less, the vehicle flow density of each area of the city is low, the vehicle speed is faster, and the movement of the vehicle in the area and between areas is very smooth, which makes the electric vehicle as a mobilizable resource has high flexibility, and the vehicle owner is willing to charge / discharging in such a district; when the road congestion is serious, the vehicle flow density of each area increases, the vehicle speed decreases, and the movement and transfer of the vehicle are limited, which reduces the flexibility of the electric vehicle as a mobilizable resource and makes the scheduling difficult.

[0135] Therefore, the dynamic charging / discharging price model prepared in this embodiment is as described in step S4, which includes:

[0136] 1. Establish a charging price model:

[0137]

[0138] wherein, Cj(t) is the charging price of the jth electric vehicle at time t, t C(t) is the basic charging price in the district at time t, P(t) is the penalty price of the district at time t due to charging congestion, j，t SoCj(t) is the SoC of the jth electric vehicle at the initial charging time t, Pj is the penalty price of the jth electric vehicle due to whether it responds to the scheduling or not;

[0139] 2. Establish a discharging price model:

[0140]

[0141] wherein, Dj(t) is the discharging price of the jth electric vehicle at time t, t D(t) is the basic discharging price in the district at time t, P(t) is the penalty price of the district at time t due to charging congestion, Pj is the penalty price of the jth electric vehicle due to whether it responds to the scheduling or not;

[0142] As can be seen from the above model, when the electric vehicle owner has a higher willingness to respond to the scheduling, the charging price is lower; when the congestion of the district where the electric vehicle is located is lower, the charging price is lower. Similarly, when the electric vehicle owner has a higher willingness to respond to the scheduling, the owner has more benefits due to responding to the scheduling policy; when the charging congestion of the district where the electric vehicle is located is higher, the discharging price is higher, and the district needs more corresponding distributed power supply.

[0143] As shown in Figure 2 The embodiment also provides a system for establishing an electric price model based on electric vehicle data analysis, which is based on the above, and includes:

[0144] A data collection and electric vehicle charging demand model construction module is configured to collect charging time, frequency and charging quantity information of electric vehicles of different owners, and combine the collected information with traffic congestion conditions to construct an electric vehicle charging demand model;

[0145] A traffic congestion degree coefficient threshold value calculation module is configured to establish a traffic congestion degree pricing mechanism in a transformer area and determine a traffic congestion degree coefficient by using a charging load obtained from the electric vehicle charging demand model; and the threshold value of the traffic congestion degree coefficient is calculated adaptively using the SS-AE.

[0146] A dynamic pricing model construction module is configured to set a personal charging willingness feedback mechanism of the owner, determine a charging / discharging willingness index, and establish a dynamic pricing model.

[0147] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the described embodiments. Those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application. These equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method for establishing an electricity price model based on electric vehicle data analysis, characterized in that, Includes the following steps: S1: Collect information on the charging time, frequency, and amount of electric vehicles from different car owners, and combine the collected information with traffic congestion to build an electric vehicle charging demand model; S2: Using the charging load obtained from the electric vehicle charging demand model in step S1, establish a traffic congestion electricity pricing mechanism within the transformer area and determine the traffic congestion coefficient. S3: Use SS-AE to adaptively calculate the threshold of traffic congestion coefficient; S4: Set up a feedback mechanism for individual car owners' charging intentions, determine the charging / discharging intention index, and establish a dynamic electricity price model; The SS-AE comprises two AEs, each AE including an encoder and a decoder. Both the encoder and decoder consist of three dense layers. The encoder portion includes: , These represent the historical traffic congestion coefficient and the real-time traffic congestion coefficient, respectively. , These represent the historical traffic congestion coefficient and the real-time traffic congestion coefficient reconstructed by SS-AE, respectively. , They are respectively , Potential representations, , Represented as: Posterior probability : The posterior probability of a low-confidence sample is expressed as: ； The decoder portion includes: The decoder in SS-AE is considered as a conditional probability distribution model. ,express based on right Reconstruction: The loss function for transformation and reconstruction is expressed as: By maximizing Optimize the decoder parameters. express and Between Divergence; , The reconstruction error between them is , , The reconstruction error between them is ; The traffic congestion coefficient is denoted as: , when When, it indicates that traffic within the area is not congested. At that time, it indicates traffic congestion within the area, including The threshold for the traffic congestion coefficient; Threshold for traffic congestion coefficient Solution: ， ； In step S4, the charging / discharging willingness index is specifically the owner's response to the charging / discharging willingness index, expressed as: in, Representing the The willingness to charge / discharge of electric vehicles. Representing the The charging / discharging intentions of electric vehicle owners; The establishment of the dynamic electricity price model includes: establishing a charging price model and establishing a discharging price model. The establishment of the charging price model includes: in, For the first electric vehicles The electricity price for charging at any given moment. Within the Taiwan area Basic charging electricity price at all times for Penalty pricing for charging congestion within the designated time and area. For the first Initial charging moment of an electric vehicle of , For the first The penalty price incurred for whether an electric vehicle responds to dispatch; Establish a discharge pricing model, including: in, For the first electric vehicles The discharge price at any given time Within the Taiwan area The base discharge electricity price at any time for Penalty pricing for charging congestion within the designated time and area. For the first The penalty price incurred for whether an electric vehicle responds to a dispatch.

2. The method for establishing an electricity price model based on electric vehicle data analysis according to claim 1, characterized in that, In step S1, constructing an electric vehicle charging demand model includes: Its electricity consumption behavior is described using a probability distribution model of the initial charging period and a probability model of daily mileage: in, This indicates the end of charging time. This represents the average time to complete charging. This represents the standard deviation of the charging end time.

3. The method for establishing an electricity price model based on electric vehicle data analysis according to claim 2, characterized in that, Mileage: in, Represents mileage. Represents the standard deviation of mileage. This represents the average mileage.

4. The method for establishing an electricity price model based on electric vehicle data analysis according to claim 3, characterized in that, The formula for calculating charging time is: in, Represents charging time. This represents the amount of electricity consumed by an electric vehicle every 100 kilometers it travels. Represents the charging power of electric vehicles. This represents the charging efficiency of electric vehicles. A sample of electric vehicles was taken to calculate their daily basic charging load: in, This represents the charging load.

5. The method for establishing an electricity price model based on electric vehicle data analysis according to claim 4, characterized in that, In step S2, establishing a traffic congestion-based electricity pricing mechanism within the transformer substation and determining the traffic congestion coefficient includes: Traffic congestion within the district is defined as follows: in, Indicates the first Each district Average speed at any given time Indicates the first The routine vehicle speed in each area Indicates the first Each district Traffic density at any given time Indicates the first The maximum traffic density in each area.

6. A system based on the method for establishing an electricity price model based on electric vehicle data analysis as described in claim 1, characterized in that, include: The data collection and electric vehicle charging demand model building module is used to: collect information on the charging time, frequency and amount of electric vehicles from different car owners, and combine the collected information with traffic congestion to build an electric vehicle charging demand model; The threshold calculation module for traffic congestion coefficient is used to: establish a traffic congestion electricity pricing mechanism within the transformer substation and determine the traffic congestion coefficient based on the charging load obtained from the electric vehicle charging demand model; and perform adaptive threshold calculation of the traffic congestion coefficient using SS-AE. The dynamic electricity price model construction module is used to: set up a feedback mechanism for individual car owners' charging intentions, determine the charging / discharging intention index, and establish a dynamic electricity price model.

Images