CN105868942A - Ordered charging scheduling method for electric vehicle - Google Patents

Abstract

The invention provides an ordered charging scheduling method for an electric vehicle. The method comprises the steps of calculating out energy consumption of the electric vehicle in a current work condition according to a pre-established driving range predicting model of the electric vehicle; calculating out a driving range of the electric vehicle according to the energy consumption of the electric vehicle in the current work condition and a current SOC; calculating out a charging quantity of the electric vehicle according to a pre-established electric vehicle power battery service life model when a proportion between the driving range of the electric vehicle and a predicted driving range of the electric vehicle before next charging is smaller than a set threshold value; scheduling a charging process of the electric vehicle according to the charging quantity and departure time of the electric vehicle and a current load condition of a power distribution network by taking the minimum difference between peak and valley of the local-area power distribution network as an optimizing target. According to the ordered charging scheduling method, meeting a driving behavior characteristic of a driver is used as a base, the service life of a power battery of the electric vehicle is prolonged by reasonably guiding the electric vehicle to charge and discharge, the difference between peak and valley of a network load is reduced, and stable operation of a power network is guaranteed.

Description

Orderly charging scheduling method for electric vehicles

technical field

The invention relates to the technical field of electric vehicle charging, in particular to an orderly charging scheduling method for electric vehicles.

Background technique

Guaranteeing the sustainable supply of energy is a link that cannot be ignored in the national energy security strategy. It is imperative to formulate an energy security strategy that is in line with my country's sustainable development. On the one hand, improving the energy environment and reducing carbon emissions is an important consensus for sustainable energy development. On the other hand, as an important form of global energy, fossil energy is vulnerable to political, economic, terrorist attacks and other aspects. Energy conservation, emission reduction and sustainable development have made traditional motor vehicles powered by internal combustion engines face the fate of being eliminated, while electric vehicles using clean energy will inevitably become a new direction for the future development of the motor vehicle industry. As a new type of electric load, electric vehicles are charged with randomness and intermittent characteristics. Large-scale electric vehicle charging will change the current load status of the power grid and increase the difference between the maximum load and the minimum load of the power grid in a day (peak-valley Poor), affecting the stable operation of the distribution network. Therefore, how to solve the large peak-to-valley difference caused by the electric vehicle charging to the power grid is the main aspect of the present invention.

In order to reduce the impact of large-scale access of electric vehicles on the distribution network and improve the reliability and economy of grid operation, it is necessary to minimize the random charging of electric vehicles (disorderly charging) and guide the charging of electric vehicles, that is, orderly charging . Since electric vehicles are still in the initial stage of development and the penetration rate of electric vehicles is not high, there are not many studies on the orderly charging of electric vehicles, and most of them focus on improving the load status of the distribution network or reducing the network loss of the distribution network. The target, but ignores the user's willingness to charge, making it difficult for these studies to be applied in practice.

In order to improve the response rate of electric vehicle users, in addition to the goal of safe operation of the power grid, it is also necessary to pay attention to the fundamental needs and interests of users. According to the research and survey results of the automobile industry, it is shown that in the process of purchasing and using electric vehicles, in addition to the cost performance of the vehicle, users are most concerned about the convenience of driving (single battery mileage, driving comfort, etc.), power battery life , The convenience of charging. If the user's driving behavior and user needs can be reasonably guided to charge and discharge to prolong the battery life of the vehicle, and at the same time reduce the peak-to-valley difference of the power grid, the user charging response rate of electric vehicles will have a qualitative leap. However, in the current prior art, few studies have considered the importance of battery life, user driving behavior characteristics and charging willingness to charging scheduling strategies.

Contents of the invention

Embodiments of the present invention provide a method for orderly charging scheduling of electric vehicles, so as to implement an orderly charging scheduling strategy for electric vehicles considering user driving behavior characteristics.

In order to achieve the above object, the present invention adopts the following technical solutions.

A method for orderly charging scheduling of electric vehicles, comprising:

Calculate the energy consumption of the current working condition of the electric vehicle according to the pre-established electric vehicle mileage prediction model, and calculate the continuation mileage of the electric vehicle according to the energy consumption of the current working condition of the electric vehicle and the current state of charge SOC ;

When the ratio between the mileage of the electric vehicle and the estimated mileage before the next charging of the electric vehicle is less than the set threshold, according to the charging amount of the electric vehicle, departure time and the current load status of the distribution network , using a pre-established electric vehicle power battery life model to calculate the charging capacity of the electric vehicle, and taking the minimum peak-to-valley difference of the local distribution network as the optimization goal, to schedule the charging process of the electric vehicle.

Further, the calculation of the energy consumption of the current working condition of the electric vehicle according to the pre-established electric vehicle mileage prediction model includes:

A prediction model for the mileage of an electric vehicle is established in advance, and the mileage prediction model of an electric vehicle includes: defining each set distance traveled by an electric vehicle as a segment, and setting parameter information for each segment, the parameter information includes average speed, maximum speed , the sum of squares of speed, acceleration ratio, deceleration ratio, constant speed ratio, idle speed ratio, outdoor temperature and air-conditioning power, select a set number of segments and the parameter information of each segment, and use principal component analysis and fuzzy clustering algorithm to analyze all The set number of fragments is calculated to obtain multiple cluster centers, each cluster center corresponds to a working condition, and the parameter information of each cluster center includes: average speed, acceleration ratio, deceleration ratio, uniform speed ratio, air conditioner Power, ambient temperature and energy consumption parameters;

According to the parameter information of the current segment of the electric vehicle and the parameter information of each cluster center except the energy consumption parameter, the distance values between the current segment of the electric vehicle and each cluster center are respectively calculated, and the Comparing each distance value, taking the working condition corresponding to the cluster center with the shortest distance value as the current working condition of the electric vehicle, and taking the energy consumption parameter of the cluster center with the shortest distance value as the current working condition of the electric vehicle energy consumption.

Further, the distance values between the current segment of the electric vehicle and each cluster center are respectively calculated, including:

Assuming that the number of cluster centers is _c , the calculation formula of the distance value di between the current segment of the electric vehicle and each cluster center is:

d _i =||xc _i ||, i=1,2,3,...,c

In the formula: x is the parameter of the current segment of the electric vehicle, ci is the cluster center parameter of the cluster center _i , _ci = ( _ci1 , _ci2 ,..., _ci6 ).

Further, the calculation of the driving range L1 of the electric vehicle according to the energy consumption of the current working condition of the electric vehicle and the current SOC of the electric vehicle includes:

The current state of charge SOC of the electric vehicle is read, the battery capacity of the electric vehicle is Q, and the number of cluster centers is c. According to the long-term driving behavior characteristics of the driver of the electric vehicle, the proportion of each working condition class is determined, and the proportion of each working condition category is x ₁ :x ₂ :...:x _i :...:x _c-1 :x _c , ( 1≤i≤c)), the energy consumption of each working condition is p ₁ ,p ₂ ,…,p _i ,…,p _c-1 ,p _c , (1≤i≤c)), according to the current vehicle SOC, to calculate the driving range L1, the calculation formula is:

$\mathrm{<span\; class="notranslate">\; L</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; c</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; .</span>$

Further, the ratio between the mileage of the electric vehicle and the expected mileage before the next charge of the electric vehicle is less than a set threshold includes:

Assuming that the estimated mileage before the next charging of the electric vehicle is L, the mileage of the electric vehicle calculated by the electric vehicle mileage prediction model is L1, if

L1<(1+10%)L

Then it is determined that the ratio between the driving range of the electric vehicle and the expected driving range before the next charging of the electric vehicle is less than a set threshold.

Further, the method also includes:

According to the ambient temperature, charging current, discharge current, discharge depth and cycle times that affect the life of the electric vehicle power battery, the electric vehicle power battery life model is established. The electric vehicle power battery life model includes: under low discharge depth and high discharge depth , the relationship between the capacity decline of the electric vehicle power battery and the number of cycles, the electric vehicle power battery life model shows that using the electric vehicle power battery under the low discharge depth can prolong the service life of the electric vehicle power battery.

Further, according to the charging amount of the electric vehicle, the departure time and the current load status of the distribution network, the charging amount of the electric vehicle is calculated by using the pre-established power battery life model of the electric vehicle, and the local distribution The minimum peak-to-valley difference of the power grid is the optimization goal, and the charging process of the electric vehicle is scheduled, including:

According to the historical load data of the distribution network, the daily load curve of the distribution network is obtained, and the day is divided into N periods. The original load of the distribution network in the i-th period is P _i (i=1,2,3,..., N), assuming that the charging capacity of the electric vehicle for travel is S _E , the charging process of the electric vehicle is constant power charging, the charging power is ΔP, the battery capacity of the electric vehicle is Q, and the initial SOC of the electric vehicle charging is S _S , The time to arrive at the charging location is T _S , the time to leave is t, and the initial charging time is T _c , then the calculation method of the charging power S _SOC required for the charging of the electric vehicle is as follows:

${\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; C</span>}}<span\; class="notranslate">\; =</span>\left\{\begin{array}{c}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; <</span>\mathrm{<span\; class="notranslate">\; Q</span>}\\ \mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; \&Greater\; Equal;</span>\mathrm{<span\; class="notranslate">\; Q</span>}\end{array}\right.$

The residence time T _stay of electric vehicles is

T _stay =t T _S

Assuming that the electric vehicle load being charged in the i-th time period is p _i , and there are n electric vehicles charging, then

${\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; \&Delta;</span>}\mathrm{<span\; class="notranslate">\; P</span>}$

The total load P _sumi of the distribution network in the i-th period is the superposition of the electric vehicle charging load p _i and the original load P _i :

P _sumi = p _i + P _i

During the parking time (T _S , t) of the electric vehicle, the charging start time _Tc of the electric vehicle is the earliest and the peak-to-valley difference of the distribution network is the smallest as the objective function of charging control. The objective function is:

$\left\{\begin{array}{c}\mathrm{<span\; class="notranslate">\; min</span>}\mathrm{<span\; class="notranslate">\; var</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; u</span>}\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span>\\ \mathrm{<span\; class="notranslate">\; min</span>}{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}\end{array}\right.$

Wherein, var(P _sumi ) is the variance function of P _sumi . P _max is the maximum load of the local distribution network, then P _sumi should meet the constraints:

P _{sumi ≤} P _max

In addition, the initial charging time _Tc of the electric vehicle should also meet the constraints:

T _S ≤ T _c ≤ t

(tT _c )ΔP≥S _SOC

The objective function and all constraint conditions are solved through a cyclic process to obtain the initial charging time T _c of the electric vehicle.

It can be seen from the technical solutions provided by the above-mentioned embodiments of the present invention that the present invention proposes an orderly charging scheduling method for electric vehicles based on satisfying the driver's driving behavior characteristics and charging willingness, and prolongs charging and discharging by reasonably guiding electric vehicles to charge and discharge. The service life of the electric vehicle power battery can reduce the peak-valley difference of the grid load, greatly improve the driver's enthusiasm for the charging scheduling method, and ensure the stable operation of the grid, which has very practical significance.

Additional aspects and advantages of the invention will be set forth in part in the description which follows, and will become apparent from the description, or may be learned by practice of the invention.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without any creative effort.

Fig. 1 is a processing flowchart of an orderly charging scheduling method for an electric vehicle that improves user response rate provided by an embodiment of the present invention;

Fig. 2 is a schematic diagram of the relationship between the amount of capacity decline and the number of cycles of the power battery of the electric vehicle;

Figure 3 is the effect diagram of the charging load of electric vehicles during disorderly charging and orderly charging within a day;

Figure 4 shows the effect diagram of the distribution network load when electric vehicles are charged in disorder and in order within a day.

detailed description

Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

Those skilled in the art will understand that unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the word "comprising" used in the description of the present invention refers to the presence of said features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Additionally, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in commonly used dictionaries should be understood to have a meaning consistent with the meaning in the context of the prior art, and unless defined as herein, are not to be interpreted in an idealized or overly formal sense Explanation.

In order to facilitate the understanding of the embodiments of the present invention, several specific embodiments will be taken as examples for further explanation below in conjunction with the accompanying drawings, and each embodiment does not constitute a limitation to the embodiments of the present invention.

Aiming at the negative impact of disorderly charging of electric vehicles on distribution network, the invention proposes an orderly charging dispatching method that satisfies driving behavior characteristics and charging willingness of electric vehicle drivers based on prolonging the service life of electric vehicle power batteries.

The present invention adopts the method of prolonging the service life of the electric vehicle power battery to improve the user's response rate to the orderly charging scheduling method. Information, input it into models A1 and A2, calculate the charging amount of this charge, and then use algorithm B (ie genetic algorithm) to calculate the orderly charging scheduling method of electric vehicles, to achieve the optimal distribution network and users.

The processing flowchart of the orderly charging scheduling method for electric vehicles proposed by the embodiment of the present invention to improve the user response rate is shown in FIG. 1 . The main steps are as follows:

Step 1: Establish electric vehicle driving range prediction model A1. Average speed, maximum speed, acceleration ratio, deceleration ratio, constant speed ratio, idling speed ratio, outdoor temperature, air-conditioning power, etc. will all affect the driving range of electric vehicles. The present invention adopts algorithm C (i.e. Combination of principal component analysis and fuzzy clustering algorithm) to identify the driving conditions of electric vehicles, study the energy consumption of electric vehicles, and predict the driving range of electric vehicles. Taking Toyota's PriusPHEV as an example, predict its driving range in pure electric mode. Define the driving process of the electric vehicle from the current charging to the next charging as a cycle, and in each cycle, define every 1km of the electric vehicle as a segment. In order to accurately describe each segment and ensure that there will be no loss and distortion of driving information, 9 parameters are selected and calculated to describe each segment. The 9 parameters are average speed, maximum speed, sum of squares of speed, and acceleration ratio , deceleration ratio, constant speed ratio, idle ratio, outdoor temperature and air conditioner power, the units of each parameter are km/h, km/h, (km/h) ² , 1, 1, 1, 1, ℃ and kW. Among them, each acceleration-related parameter (acceleration ratio, deceleration ratio, constant speed ratio and idle speed ratio) used in the parameters is obtained by calculating the first derivative of the speed. According to this method, 3368 segments were selected for subsequent principal component analysis.

Table 1 below shows the parameter values of the first 5 fragments.

Table 1: Each parameter value of the first 5 segments of electric vehicles

Principal component analysis is to use fewer comprehensive variables to replace the original more parameters, and these fewer comprehensive variables can reflect as much useful information as possible of the original parameters, and they are irrelevant to each other. The variables are called principal components. If the cumulative contribution rate of the first e (e=1, 2, . . . , 9) principal components reaches 80% or 85%, these e principal components can represent the original variables for analysis. The principal component analysis method is used in the present invention, and its function is realized by MATLAB. Because the digital processing capability of MATLAB is relatively strong, it is more suitable for the content of the present invention, so it is selected as the realization tool. Using MATLAB software to conduct principal component analysis on each parameter in 3368 fragments, 9 principal components were obtained. The eigenvalues and contribution ratios of each principal component are shown in Table 2 below.

Table 2 Eigenvalues and contribution rates of each principal component

main ingredient Eigenvalues Contribution rate/% Y1 2.3992 34.27 Y2 1.4624 20.89 Y3 1.0571 15.10 Y4 0.7321 10.46 Y5 0.4382 6.69 Y6 0.4148 6.35 Y7 0.2962 4.23 Y8 0.1568 1.54 Y9 0.0432 0.47

According to the principle of principal component analysis, the first four principal components are selected, and the correlation analysis between the characteristic parameters and the principal components is carried out, and the representative average vehicle speed, idle speed ratio, uniform speed ratio, deceleration ratio, and outdoor temperature are selected from the first four principal components. And six parameters of air conditioner power are used for cluster calculation.

The purpose of clustering is to divide the classified objects into several categories according to certain rules. The classification rules are determined according to the characteristics of the objects, and there are certain similarities between the objects in the same category. But in many cases, it is unreasonable to strictly divide each object to be classified into a certain category. Therefore, combining fuzzy set theory to deal with clustering problems can make the application of clustering more reasonable and reliable. The fuzzy C-means clustering algorithm is used in the present invention. Fuzzy C-means clustering is a clustering method based on the objective function, and each object belongs to each cluster center with a certain degree of membership. The research object of the present invention is data comprising 3368 segments and 6 parameters, and its observation matrix can be represented by the following matrix

In the matrix, each row is a fragment, and each column is the parameter of the fragment. Fuzzy clustering is to divide samples into c categories (2≤c≤3368). Define V={v ₁ ,v ₂ ,...,v _c } as the cluster center of class c, where v _i ={v _i1 ,v _i2 ,...,v _i6 }. Define u _ik to represent the membership degree of the k-th segment belonging to the i-th class, where 0≤u _ik ≤1, d _ik =||x _k -v _i ||, represents the distance from the kth variable to the ith center.

Define the objective function as:

$\mathrm{<span\; class="notranslate">\; J</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; V</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 3368</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; c</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}$

Where U=(U _ik )c×3368 is the membership degree matrix. J(U,V) represents the sum of the weighted square distances from the sample to the cluster center in each category, and the weight is the m power of the membership degree of the sample x _k belonging to the i-th category.

Fuzzy C-means clustering is to find U and V, so that J(U,V) takes the minimum value. Specific steps are as follows:

First, determine the number c of the class, the power index m>1 and the initial membership matrix In this paper, uniformly distributed random numbers on [0,1] are used to determine the initial membership degree matrix. l=1 means the first iteration.

Second, calculate the cluster center V ⁽⁰⁾ of step l:

${\mathrm{<span\; class="notranslate">\; v</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 3368</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; /</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 3368</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; m</span>}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; ...</span>\mathrm{<span\; class="notranslate">\; c</span>}<span\; class="notranslate">\; )</span>$

Again, modify the membership degree matrix U ^(l) and calculate the objective function J ^(l) of the first step

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; c</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; /</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; )</span>}^{\frac{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; ...</span><span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; c</span>}<span\; class="notranslate">\; ;</span>\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; ...</span><span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; 3368</span>}$

${\mathrm{<span\; class="notranslate">\; J</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; u</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; V</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 3368</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; c</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; m</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; d</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}^{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; l</span>}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

Finally, for a given membership degree termination tolerance ω _u >0, when , stop the iteration.

After the above steps, the final membership matrix and clustering center can be obtained, so that the value of the objective function J(U, V) can be minimized, and the membership of all samples can be determined according to the final membership matrix U.

According to the above process, the parameters of each segment of the electric vehicle are clustered and analyzed, and the number of clusters c is tried separately. Finally, it is found that when c=12, each cluster center can best reflect the driving conditions of the electric vehicle , each cluster center corresponds to a working condition.

The parameters of each cluster center are shown in Table 3 below. In addition to the above-mentioned six parameters of average vehicle speed, idling speed ratio, constant speed ratio, deceleration ratio, outdoor temperature and air-conditioning power, the table also includes energy consumption parameters under each working condition, and the unit is kWh.

Table 3 Parameters of each cluster center

The parameters in each column in the table represent the average speed, acceleration ratio, deceleration ratio, constant speed ratio, air-conditioning power, ambient temperature and cluster centers of energy consumption parameters. From the point of view of temperature, each cluster center basically has three distributions: low temperature, normal temperature, and high temperature, representing winter, spring and autumn, and summer respectively, indicating that the impact of temperature on the energy consumption of electric vehicles is more obvious. From the perspective of average speed, each cluster center can be basically divided into four categories: low speed, medium-low speed, medium speed, and high speed, which shows that the impact of speed on energy consumption is also obvious. The acceleration, deceleration, constant speed ratio and air conditioning power mainly reflect the driving behavior characteristics of electric vehicle drivers. According to each cluster center, the driving range prediction model A1 of electric vehicles is established by using the method of working condition identification. According to the principle of minimum distance, the category of each segment of the electric vehicle can be determined, and the driving segments can be divided into 12 categories according to the working conditions. Among them, the distance calculation formula is:

d _i =||xc _i ||, i=1,2,3,...,12

In the formula: x is the parameter of a segment, x=(x ₁ ,x ₂ ,…,x ₆ ); c _i is the cluster center parameter of class i, c _i =(c _i1 ,c _i2 ,…,c _i6 )

The working condition corresponding to the cluster center with the shortest distance value d _i is taken as the current working condition of the electric vehicle, and the energy consumption parameter of the cluster center with the shortest distance value is taken as the energy consumption of the current working condition of the electric vehicle.

Read the current SOC (State of Charge) of the vehicle, and the battery capacity of the electric vehicle is Q. According to the long-term driving behavior characteristics of the driver of the electric vehicle, the proportion of each working condition class is determined, and the proportion of each working condition class is x ₁ :x ₂ :...:x _i :...:x _c-1 :x _c (1 ≤i≤c),c=12), the energy consumption of each working condition is p ₁ ,p ₂ ,…,p _i ,…,p _c-1 ,p _c , (1≤i≤c), c =12), according to the SOC of the current vehicle, calculate the driving distance L1, the calculation formula is

$\mathrm{<span\; class="notranslate">\; L</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 12</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 12</span>}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}$

Step 2: Establish electric vehicle power battery life model A2.

When establishing the electric vehicle power battery life model A2, the ambient temperature, charging current, discharge current, discharge depth and cycle times are selected as the main factors affecting the life of the electric vehicle power battery. When the ambient temperature is selected, the simulation is carried out according to the temperature values of the mixed seasons, which are 10°C → 25°C → 40°C → 25°C → 10°C. The charging rate is usually relatively fixed for the power battery of an electric vehicle, and C/3 is selected (where C is the charging rate, and the calculation method is the charging current of the power battery of the electric vehicle divided by the rated capacity of the power battery of the electric vehicle). Under actual operating conditions, the discharge current of the electric vehicle power battery varies greatly, so the average discharge rate is selected, and its value is about C/2. Generally speaking, when the capacity of the electric vehicle power battery is 70%-80% of its nominal capacity, the electric vehicle power battery can no longer be used. It is said that the electric vehicle power battery is discharged from full charge to the corresponding SOC under the specified discharge depth, and the process of recharging is one cycle of the electric vehicle power battery. The relationship between the capacity decline of electric vehicle power batteries and the number of cycles was studied under low depth of discharge (50% depth of discharge) and high discharge depth (80% depth of discharge), and the results shown in Figure 2 were obtained. Among them, the relationship between the capacity decline of the electric vehicle power battery and the number of cycles under low discharge depth and high discharge depth is shown in Figure 2. It can be seen from Figure 2 that under the same number of cycles, the capacity decline of electric vehicle power batteries at low discharge depths is significantly lower than that at high discharge depths. The use of electric vehicle power batteries under low discharge depth can effectively prolong their service life. The relational expression is queried according to the current cycle number of the electric vehicle to obtain the current capacity decline of the power battery of the power vehicle. When determining the amount of charge, on the premise that the mileage of the electric vehicle meets the estimated mileage before the next charge of the electric vehicle, the power battery of the electric vehicle is kept in use at a low depth of discharge.

Step 3: Propose an orderly charging scheduling method for electric vehicles

In step 1 and step 2, the method of predicting the driving range of electric vehicles and the life prediction method of power battery are respectively proposed, and the prediction model A1 of driving range of electric vehicles and the life model A2 of power battery of electric vehicles are established. In step 3, combined with the driver's charging willingness and residence time, and according to the current load status of the distribution network, an orderly charging scheduling method for electric vehicles that meets the driver's charging willingness is proposed. This scheduling method uses a two-layer model, and the upper model is the user side. Before the charging starts, the driver of the electric vehicle inputs the current SOC of the electric vehicle, the departure time t, and the estimated mileage L before the next charging, and predicts the electric vehicle according to the model A1. The driving range L1 under the current SOC, if

L1≥(1+10%)L

Indicates that the current electric vehicle has sufficient power, and the driver of the electric vehicle decides whether to charge the electric vehicle; in the formula, 10% is the remaining power of the vehicle, if the current mileage does not meet the above formula or the driver still wants to charge, then At this time, it is still up to the driver to decide whether he is willing to accept charging scheduling. If he is not willing, the current electric vehicle will start charging and fully charged; if the driver is willing to accept scheduling, then enter the lower model, that is, the grid side. According to model A2 Calculate the charging amount S _E that satisfies the vehicle travel, and according to the departure time input by the driver and the current load status of the distribution network, take the minimum peak-valley difference of the local distribution network as the optimization goal, and propose a corresponding dispatching method.

The daily load curve of the distribution network is obtained from its historical load forecast. In the present invention, a day is divided into 96 time periods with a time interval of 15 minutes. Therefore, the original load of the distribution network in the i-th time period is P _i (i=1, 2, 3, . . . , 96). In addition, in the present invention, it is assumed that the charging process of the electric vehicle is constant power charging, and its charging power is ΔP. Assume that the battery capacity of the electric vehicle is Q, the initial SOC of electric vehicle charging is S _S , the time when the driver arrives at the charging location is T _S , the time of departure is t, and the initial charging time is T _c , then the charging time of the electric vehicle is The calculation method of the charging power S _SOC is as follows:

${\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; C</span>}}<span\; class="notranslate">\; =</span>\left\{\begin{array}{c}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; <</span>\mathrm{<span\; class="notranslate">\; Q</span>}\\ \mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; \&Greater\; Equal;</span>\mathrm{<span\; class="notranslate">\; Q</span>}\end{array}\right.$

The residence time T _stay of electric vehicles is

T _stay =t T _S

Assuming that the electric vehicle load being charged in the i-th time period is p _i , and there are n electric vehicles charging, then

${\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; \&Delta;</span>}\mathrm{<span\; class="notranslate">\; P</span>}$

The total load P _sumi of the distribution network in the i-th period is the superposition of the electric vehicle charging load p _i and the original load P _i :

P _sumi = p _i + P _i

During the time when the driver stops (T _S , t), the earliest charging start time of the user and the smallest peak-to-valley difference of the distribution network are used as the objective function of charging control, that is,

$\left\{\begin{array}{c}\mathrm{<span\; class="notranslate">\; min</span>}\mathrm{<span\; class="notranslate">\; var</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; u</span>}\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span>\\ \mathrm{<span\; class="notranslate">\; min</span>}{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}\end{array}\right.$

Wherein, var(P _sumi ) is the variance function of P _sumi .

P _max is the maximum load of the local distribution network, then P _sumi should meet the constraints:

P _{sumi ≤} P _max

In addition, the initial charging time T _c should also meet the constraints:

T _S ≤ T _c ≤ t

(tT _c )ΔP≥S _SOC

The above is the orderly charging scheduling problem, and algorithm B is used to solve the problem. Select the charging power of each period as the chromosome individual, perform binary coding, perform crossover and mutation operations, and calculate the objective function according to the constraints, retain and reinsert the excellent chromosomes, and solve the objective function and all constraints through a cyclic process condition to obtain the initial charging time T _c of the electric vehicle.

Step 4: There are 100 electric vehicles in the distribution network area. Taking one day as a stage, the charging load and distribution network load updated throughout the day are displayed in the effect diagram, and at the same time, the distribution network load under disorderly charging and the distribution network load under orderly charging are displayed in the effect diagram In order to verify the effectiveness of the ordered charging scheduling method. Accompanying drawing 3 is the effect diagram of charging load when electric vehicles are charged in disorder and in order in one day, and accompanying drawing 4 is the effect diagram of distribution network load in a day when electric vehicles are charged in disorder and in order respectively.

To sum up, the traditional orderly charging scheduling methods mostly aim at improving the load status of the distribution network or reducing the network loss of the distribution network, while ignoring the user's driving behavior characteristics and charging willingness, which leads to the fact that the orderly charging scheduling is ineffective in practice. are difficult to apply. In order to solve this problem, the embodiment of the present invention proposes an orderly charging scheduling method for electric vehicles based on the driver's driving behavior characteristics and charging willingness, and prolongs the service life of the power battery of the electric vehicle by reasonably guiding the charging and discharging of the electric vehicle. At the same time, it can reduce the peak-to-valley difference of the grid load, greatly improve the driver's enthusiasm for the charging scheduling method, and at the same time ensure the stable operation of the grid, which has very practical significance.

Those skilled in the art can understand that the accompanying drawing is only a schematic diagram of an embodiment, and the modules or processes in the accompanying drawing are not necessarily necessary for implementing the present invention.

It can be seen from the above description of the implementation manners that those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in storage media, such as ROM/RAM, disk , CD, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the present invention.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for relevant parts, refer to part of the description of the method embodiments. The device and system embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, It can be located in one place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without creative effort.

The above is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of changes or modifications within the technical scope disclosed in the present invention. Replacement should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims (7)

1. A method for orderly charging and dispatching of electric vehicles, characterized in that it comprises: Calculate the energy consumption of the current working condition of the electric vehicle according to the pre-established electric vehicle mileage prediction model, and calculate the continuation mileage of the electric vehicle according to the energy consumption of the current working condition of the electric vehicle and the current state of charge SOC ; When the ratio between the mileage of the electric vehicle and the estimated mileage before the next charging of the electric vehicle is less than the set threshold, according to the charging amount of the electric vehicle, departure time and the current load status of the distribution network , using a pre-established electric vehicle power battery life model to calculate the charging capacity of the electric vehicle, and taking the minimum peak-to-valley difference of the local distribution network as the optimization goal, to schedule the charging process of the electric vehicle. 2. The method according to claim 1, characterized in that, calculating the energy consumption of the current working condition of the electric vehicle according to the pre-established electric vehicle mileage prediction model includes: A prediction model for the mileage of an electric vehicle is established in advance, and the mileage prediction model of an electric vehicle includes: defining each set distance traveled by an electric vehicle as a segment, and setting parameter information for each segment, the parameter information includes average speed, maximum speed , the sum of squares of speed, acceleration ratio, deceleration ratio, constant speed ratio, idle speed ratio, outdoor temperature and air-conditioning power, select a set number of segments and the parameter information of each segment, and use principal component analysis and fuzzy clustering algorithm to analyze all The set number of fragments is calculated to obtain multiple cluster centers, each cluster center corresponds to a working condition, and the parameter information of each cluster center includes: average speed, acceleration ratio, deceleration ratio, uniform speed ratio, air conditioner Power, ambient temperature and energy consumption parameters; According to the parameter information of the current segment of the electric vehicle and the parameter information of each cluster center except the energy consumption parameter, the distance values between the current segment of the electric vehicle and each cluster center are respectively calculated, and the Comparing each distance value, taking the working condition corresponding to the cluster center with the shortest distance value as the current working condition of the electric vehicle, and taking the energy consumption parameter of the cluster center with the shortest distance value as the current working condition of the electric vehicle energy consumption. 3. The method according to claim 2, wherein said calculating the distance values between the current segment of said electric vehicle and each cluster center respectively comprises: Assuming that the number of cluster centers is _c , the calculation formula of the distance value di between the current segment of the electric vehicle and each cluster center is: d _i =||xc _i ||, i=1,2,3,...,c In the formula: x is the parameter of the current segment of the electric vehicle, ci is the cluster center parameter of the cluster center _i , _ci = ( _ci1 , _ci2 ,..., _ci6 ). 4. The method according to claim 1, wherein the calculating the mileage L1 of the electric vehicle according to the energy consumption of the current working condition of the electric vehicle and the current SOC of the electric vehicle comprises: The current state of charge SOC of the electric vehicle is read, the battery capacity of the electric vehicle is Q, and the number of cluster centers is c. According to the long-term driving behavior characteristics of the driver of the electric vehicle, the proportion of each working condition class is determined, and the proportion of each working condition class is x ₁ :x ₂ :...:x _i :...:x _c-1 :x _c (1 ≤i≤c), the energy consumption of each working condition is p ₁ , p ₂ ,…,pi ,…,p _c-1 ,p _c , ( _1≤i≤c ), according to the current vehicle SOC, To calculate the driving distance L1, the calculation formula is: $\mathrm{<span\; class="notranslate">\; L</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; c</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}<span\; class="notranslate">\; .</span>$ 5. The method according to any one of claims 1 to 4, characterized in that the ratio between the mileage of the electric vehicle and the expected mileage before the next charge of the electric vehicle is less than a set value set thresholds, including: Assuming that the estimated mileage before the next charging of the electric vehicle is L, the mileage of the electric vehicle calculated by the electric vehicle mileage prediction model is L1, if L1<(1+10%)L Then it is determined that the ratio between the driving range of the electric vehicle and the expected driving range before the next charging of the electric vehicle is less than a set threshold. 6. method according to claim 5, is characterized in that, described method also comprises: According to the ambient temperature, charging current, discharge current, discharge depth and cycle times that affect the life of the electric vehicle power battery, the electric vehicle power battery life model is established. The electric vehicle power battery life model includes: under low discharge depth and high discharge depth , the relationship between the capacity decline of the electric vehicle power battery and the number of cycles, the electric vehicle power battery life model shows that using the electric vehicle power battery under the low discharge depth can prolong the service life of the electric vehicle power battery. 7. The method according to claim 6, characterized in that, according to the charging amount of the electric vehicle, the departure time and the current load condition of the distribution network, the power battery life model of the electric vehicle established in advance is used to calculate The charging capacity of the electric vehicle is optimized with the minimum peak-to-valley difference in the local distribution network as the optimization goal, and the charging process of the electric vehicle is scheduled, including: According to the historical load data of the distribution network, the daily load curve of the distribution network is obtained, and the day is divided into N periods. The original load of the distribution network in the i-th period is P _i (i=1,2,3,..., N), assuming that the charging capacity of the electric vehicle for travel is S _E , the charging process of the electric vehicle is constant power charging, the charging power is ΔP, the battery capacity of the electric vehicle is Q, and the initial SOC of the electric vehicle charging is S _S , The time to arrive at the charging location is T _S , the time to leave is t, and the initial charging time is T _c , then the calculation method of the charging power S _SOC required for the charging of the electric vehicle is as follows: ${\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; C</span>}}<span\; class="notranslate">\; =</span>\left\{\begin{array}{c}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; <</span>\mathrm{<span\; class="notranslate">\; Q</span>}\\ \mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; S</span>}}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 10</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; E.</span>}}<span\; class="notranslate">\; \&Greater\; Equal;</span>\mathrm{<span\; class="notranslate">\; Q</span>}\end{array}\right.$ The residence time T _stay of electric vehicles is T _stay =t T _S Assuming that the electric vehicle load being charged in the i-th time period is p _i , and there are n electric vehicles charging, then ${\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; \&Delta;</span>}\mathrm{<span\; class="notranslate">\; P</span>}$ The total load P _sumi of the distribution network in the i-th period is the superposition of the electric vehicle charging load p _i and the original load P _i : P _sumi = p _i + P _i During the parking time (T _S , t) of the electric vehicle, the charging start time _Tc of the electric vehicle is the earliest and the peak-to-valley difference of the distribution network is the smallest as the objective function of charging control. The objective function is: $\left\{\begin{array}{c}\mathrm{<span\; class="notranslate">\; min</span>}\mathrm{<span\; class="notranslate">\; var</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; u</span>}\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span>\\ \mathrm{<span\; class="notranslate">\; min</span>}{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}\end{array}\right.$ Wherein, var(P _sumi ) is the variance function of P _sumi . P _max is the maximum load of the local distribution network, then P _sumi should meet the constraints: P _{sumi ≤} P _max In addition, the initial charging time _Tc of the electric vehicle should also meet the constraints: T _S ≤ T _c ≤ t (tT _c )ΔP≥S _SOC The objective function and all constraint conditions are solved through a cyclic process to obtain the initial charging time T _c of the electric vehicle.