Intelligent regulation and control system and method for electric vehicle

Abstract

The invention belongs to the technical field of power grids, and particularly relates to an intelligent regulation and control system and method for an electric vehicle. The system comprises a data acquisition, analysis and prediction unit, a power distribution network weak link intelligent identification unit, a power grid weakness monitoring and evaluation unit, an electric vehicle intelligent regulation and control unit and a user interaction unit. For weak links of the power grid, when the load scale of the power grid is increased and the electric vehicle is accessed to the power grid as energy storage, the power quality of the power grid is improved. Large-scale load access to the power grid is effectively guaranteed, fluctuation of power grid voltage is reduced, balance of voltage and power of the power grid is guaranteed, electric energy indexes of weak links of the power grid are improved, and stable operation of the power grid is maintained.

Description

Technical Field

[0001] The present invention belongs to the technical field of improving the power quality of a power grid after electric vehicles are connected to the power grid as energy storage, targeting weak links in a power grid. In particular, the present invention relates to an intelligent control system and method for electric vehicles, and more specifically, to an intelligent control system and method for electric vehicles for improving power supply in weak links in a power grid. Background Art

[0002] With the global trend of developing clean and new energy, my country is also vigorously promoting the development of new energy. Electric vehicles have become an important carrier for the development of new energy with their significant advantages such as clean, energy-saving, intelligent and efficient. Electric vehicles are not only a charging load, but can also be regarded as a distributed energy storage. During the operation of the power system, there will be overload nodes and overload branches. Therefore, there are weak links in the power grid, namely vulnerable nodes and lines. Usually, the weak links of the power grid will show the phenomenon of low power quality during operation.

[0003] At the same time, when the load peaks, the large-scale charging load connected to the grid will cause large fluctuations in the grid voltage. The power quality, voltage, harmonics, etc. of the weak links of the grid will be greatly affected. At this time, it is necessary to identify the weak links of the grid and monitor and feedback in real time, and to compensate for them by dispatching electric vehicles as energy storage, which becomes more important.

[0004] However, traditional solutions usually require a lot of manpower and material resources, and the system has poor shock resistance and low flexibility. Summary of the invention

[0005] In view of the shortcomings of the above-mentioned prior art, the present invention provides an intelligent control system and method for electric vehicles. Its purpose is to realize the identification of weak links in the power grid, intelligently monitor and feedback the power energy indicators of the weak links, and through the scheduling of the charging and discharging of electric vehicles, the electric vehicles discharge to the power grid, relieve the load pressure of the power grid, and then ensure the access of large-scale loads to the power grid, reduce the fluctuation of the power grid voltage, ensure that the voltage and power of the power grid are balanced, improve the power energy indicators of the weak links of the power grid, maintain the stable operation of the power grid, and fully reflect the invention purpose of the intelligent control system of electric vehicles to accurately identify weak links and quickly compensate for the performance of the power grid.

[0006] The technical solution adopted by the present invention to achieve the above-mentioned purpose is:

[0007] An electric vehicle intelligent control system comprises a data acquisition and analysis prediction unit, a distribution network weak link intelligent identification unit, a power grid weakness monitoring and evaluation unit, an electric vehicle intelligent control unit and a user interaction unit; wherein the input end of the data acquisition and analysis prediction unit is connected to the secondary side of the busbar of the power system busbar system, the input end of the distribution network weak link intelligent identification unit is connected in parallel with the output end of the data acquisition and analysis prediction unit, the input end of the power grid weakness monitoring and evaluation unit is connected to the output end of the power grid weak link intelligent identification unit, the input end of the electric vehicle intelligent control unit is connected to the output end of the power grid weakness monitoring and evaluation unit, and the output end of the user interaction unit is connected to the input end of the electric vehicle intelligent control unit;

[0008] The data collection and analysis prediction unit collects power grid weakness parameters and performs analysis and prediction;

[0009] The weak link intelligent identification unit is used to comprehensively evaluate the analyzed and predicted parameters;

[0010] The power grid weakness monitoring and evaluation unit is used to detect the comprehensive evaluation results;

[0011] The electric vehicle intelligent control unit is used to formulate an electric vehicle charging and discharging scheduling strategy according to the detection results;

[0012] The user interaction unit is used to indicate the user's willingness to discharge and to set the power and duration of charging and discharging of the electric vehicle.

[0013] Furthermore, the data acquisition and analysis prediction unit includes: a data acquisition module, a data analysis module and a data prediction module; wherein the input end of the data acquisition module is connected to the secondary side bus of the power grid, the output end of the data acquisition module is connected to the input end of the data analysis module, and the output end of the data analysis module is connected to the data prediction module; the data acquisition module acquires power grid weakness parameters, the data analysis module classifies and normalizes the acquired data, and the data prediction module analyzes the power quality parameters of the future time period by analyzing the collected data rules through an intelligent prediction algorithm;

[0014] The intelligent identification unit for weak links in the distribution network includes: a weak node identification module and a weak line identification module; wherein the input ends of the weak node identification module and the weak line identification module are connected in parallel with the output end of the data prediction module in the data acquisition and data acquisition and analysis prediction unit; the weak node identification module needs to formulate weak node indicators according to the weak parameters of the power grid collected by the data acquisition module in the data acquisition and analysis prediction unit, and comprehensively evaluate the weak nodes according to the weak node indicators; the weak line identification module formulates weak line indicators according to the electrical parameters collected by the data acquisition module in the data acquisition and analysis prediction unit, and comprehensively evaluates the weak lines according to the weak line indicators through intelligent algorithms;

[0015] The grid weakness monitoring and evaluation unit comprises: a grid weakness monitoring and evaluation module and a feedback regulation module; wherein the input end of the grid weakness monitoring and evaluation module is connected to the secondary side bus of the distribution network, detects the grid weakness index and evaluates whether the index is within the specified weakness allowable range, and if the electrical index exceeds the weakness allowable range, sends the weakness signal to the feedback regulation module; the output end of the grid weakness monitoring and evaluation module is connected to the input end of the feedback regulation module, and the feedback regulation module receives the weakness signal and transmits the control signal to the electric vehicle intelligent control unit; the output end of the feedback regulation module is connected to the input end of the electric vehicle intelligent control unit, and when the electric vehicle intelligent control unit receives the control signal, the electric vehicle is intelligently controlled;

[0016] The electric vehicle intelligent control unit comprises: an optimization algorithm module and an electric vehicle dispatching module; wherein the output end of the optimization algorithm module is connected to the input end of the electric vehicle dispatching module, and the output end of the electric vehicle dispatching module is connected to the electric vehicle charging station; the optimization algorithm module formulates an electric vehicle charging and discharging dispatching strategy based on the operation information of the power grid and the traffic network, and transmits the charging and discharging dispatching strategy to the electric vehicle dispatching module to complete the real-time dispatching of the electric vehicle;

[0017] The user interaction unit includes: a discharge excitation module and a parameter setting module; wherein the discharge excitation module and the parameter setting module are connected in parallel to the input end of the electric vehicle intelligent control unit, the discharge excitation module discharges the power and discharge time period of the electric vehicle to the power grid, so that the electric vehicle realizes the energy storage function to adjust the electrical indicators of the power grid, and the parameter setting module sets the power and time parameters for the user according to the charging demand, and adjusts the charging and discharging time period of the electric vehicle while meeting the user's needs, thereby completing the charging and discharging scheduling of the electric vehicle.

[0018] An intelligent control method for an electric vehicle, comprising:

[0019] Step 1. The data collection and analysis prediction unit collects grid weakness parameters, performs classification and normalization processing and analysis, and predicts power quality parameters for future time periods;

[0020] Step 2. Obtain data feature quantities based on the predicted power quality parameters and input them into the intelligent identification unit for weak links in the distribution network;

[0021] Step 3. Formulate weak node indicators and weak line indicators based on the power quality parameters predicted by the collected data rules, and comprehensively evaluate weak nodes and weak lines through intelligent algorithms based on the weak indicators;

[0022] Step 4. According to the weak nodes and weak lines, the grid weakness index is detected and evaluated whether the index is within the specified weakness allowable range. If the electrical index exceeds the weakness allowable range, the weakness signal is sent to the grid weakness monitoring and evaluation unit, and the grid weakness monitoring and evaluation unit transmits the control signal to the electric vehicle intelligent control unit;

[0023] Step 5. The electric vehicle intelligent control unit combines the operation information of the power grid and the traffic network with the information set by the user of the user interaction unit to formulate a charging and discharging scheduling strategy for the electric vehicle;

[0024] Step 6: Send the charging and discharging scheduling strategy to the electric vehicle scheduling unit to complete the real-time scheduling of electric vehicles.

[0025] Furthermore, the data collection and analysis prediction unit collects grid weakness parameters, performs classification and normalization processing and analysis, and predicts power quality parameters in future time periods. The prediction method includes:

[0026] Step 1. Normalize the collected voltage data;

[0027] Step 2. Build a gray wolf optimization model and initialize the gray wolf position;

[0028] Step 3. Input sample data, design fitness function, determine the positions of the first three layers of gray wolves, and optimize;

[0029] Step 4. Calculate and update the position and parameters of the last layer of gray wolves, and check whether the dimension is out of bounds;

[0030] Step 5. If the error is within the allowable range, return the optimal gray wolf and output the weight;

[0031] Step 6. Establish the initialization parameters of the neural network model, and use the weights and thresholds optimized by the gray wolf optimization model to optimize the neural network model;

[0032] Step 7. Input sample parameters and train the normalized voltage data;

[0033] Step 8. If the error is within the allowable range, output the prediction result.

[0034] Furthermore, the power quality parameters predicted according to the collected data rules are used to formulate weak node indicators and weak line indicators, and the weak nodes and weak lines are comprehensively evaluated through intelligent algorithms according to the weak indicators; wherein the evaluation method includes:

[0035] Perform data preprocessing on the node voltage by normalization and other methods;

[0036] Use empirical mode decomposition to reduce the noise of voltage signals;

[0037] Predict the load node voltage through intelligent prediction algorithm;

[0038] Analyze various types of electrical data and establish indicators for identifying weak nodes in the distribution network;

[0039] Establish a distribution network weak node identification model and output the results.

[0040] Furthermore, the evaluation method of the power grid weakness monitoring and evaluation unit includes:

[0041] Step 1. Input the collected and processed data, sort the indicators to be evaluated, and calculate the subjective weight coefficient ω zgi The values ​​are:

[0042]

[0043] In the above formula: ω zgn is the subjective weight coefficient, n is the number of summation factors in the formula, i is the index ranking in the formula parameter, k is the index number, r k is the index importance coefficient;

[0044] According to the importance of adjacent indicators, the weight of each indicator is calculated:

[0045] ω zgi =r i+1 ω zgi+1

[0046] In the above formula: ω zgi The subjective weight of each indicator;

[0047] Therefore, ω zg =(ω zg1 ,ω zg2 ,...,ω zgn ) constitutes the subjective weight vector of the evaluation index;

[0048] Step 2. According to the information entropy, use the improved entropy weight method to calculate the objective weight coefficient ω kg ;

[0049] The calculation formula of the improved entropy weight method is shown as follows:

[0050]

[0051] In the above formula, ω kgi is the objective weight coefficient of the ith indicator, and satisfies Σω=1; m is the number of indicators; h i is the entropy value of the indicator, and satisfies 0≤h i ≤1, n is the number of summation factors in the formula;

[0052] Take any two entropy weights ω kg1 and ω kg2 , the corresponding entropy values ​​are h1 and h2, given by |ω kg1 -ω kg2 |Available:

[0053]

[0054] When the entropy weight ω kg1 and entropy weight ω kg2 When the entropy value of is infinitely close, the difference is approximately 0, that is, The above formula is transformed into:

[0055]

[0056] In the above formula: ζ is the limit of the difference in the mathematical formula;

[0057] ξ approaches 0 and is a definite value, so |ω kg1 -ω kg2 The change of | is consistent with the change trend of ξ; when the entropy value approaches 0, the entropy weight does not change exponentially; when the gap between h1 and h2 is large, assuming that h1>>h2 and h1 and h2 satisfy 0≤h i ≤1, let |h2-h1|=ξ(ξ→1), the number of indicators m is a finite real number, and:

[0058] but

[0059] In the above formula: ξ is the limit of the difference in the mathematical formula, h i is the entropy value of each indicator;

[0060] The objective weight vector obtained by the improved entropy method is: ω kg =(ω kg1 ,ω kg2 ,...,ωkgn ), where ω kg is the objective weight vector, ω kgn is the objective weight coefficient;

[0061] Step 3. Combine the subjective weighting method and the objective weighting method to approach the actual subjective and objective weights, use the minimum discriminant information principle to combine the subjective and objective weights, and calculate the weight value of each indicator ω i ;

[0062] The objective function is set according to the minimum discriminant information principle:

[0063]

[0064] Construct the Lagrangian function to solve:

[0065]

[0066] In the above formula: L is the constructed Lagrangian function;

[0067] make We can get:

[0068]

[0069] In the above formula: λ is the coefficient in the mathematical formula;

[0070] The weight values ​​of each indicator are:

[0071]

[0072] Step 4: Substitute the various indicators of weak nodes and weak lines to obtain the comprehensive evaluation results of weak links in the distribution network. The indicators are:

[0073] R VUL =ω i R i

[0074] In the above formula: R VUL is the comprehensive assessment result of the weak links in the distribution network, R i are the values ​​of each indicator, and R i ∈{R BO ,R Volt ,R UB ,R Lbi ,R χij ,R VS};ω i is the weight value of each indicator; the comprehensive evaluation result of the weak links of the distribution network R VUL The larger the value is, the higher the weakness of this link caused by power supply quality is.

[0075] Furthermore, the control method of the electric vehicle intelligent control unit includes:

[0076] Step 1. Obtaining a feedback regulation signal from a feedback regulation module in a grid weakness monitoring and evaluation unit, requiring the electric vehicle to provide electric energy to the grid;

[0077] Step 2. The optimization algorithm of the electric vehicle intelligent control unit is to transform the dispatching method into an optimization problem, with user cost, grid operation loss and weakness index as the objective function:

[0078]

[0079] In the above formula, P t loss are the user's cost and the network loss of the power grid operation, respectively. X is the minimum optimization function, J1 is the user's cost, J2 is the power grid loss cost, T is the total duration, t is different time periods, and k2 is the loss coefficient;

[0080] Step 3. Optimize the objective function through the optimization algorithm to obtain the optimal objective solution, that is, minimize the objective;

[0081] Step 4. Check whether the optimal solution of the objective function meets the error and the number of iterations. If so, output the optimal result.

[0082] Step 5. The obtained optimal control strategy is executed by the electric vehicle control module to control the electric vehicles that are connected to the power grid;

[0083] Step 6. Complete the real-time height of the electric vehicle and intelligently control the electric vehicle to discharge the electric vehicle.

[0084] An intelligent control device for an electric vehicle, comprising:

[0085] The data collection and analysis module is used to collect the power grid weakness parameters, analyze and classify them, and predict the power quality parameters in the future time period.

[0086] An input module is used to obtain data feature quantities according to the predicted power quality parameters and input them into the intelligent identification unit of weak links in the distribution network;

[0087] Comprehensive evaluation module, used to formulate weak node indicators and weak line indicators according to the power quality parameters predicted by the collected data rules, and comprehensively evaluate weak nodes and weak lines through intelligent algorithms according to the weak indicators;

[0088] The detection and evaluation module is used to detect the power grid weakness index according to the weak nodes and weak lines and evaluate whether the index is within the specified weakness allowable range. If the electrical index exceeds the weakness allowable range, the weakness signal is sent to the power grid weakness monitoring and evaluation unit, and the power grid weakness monitoring and evaluation unit transmits the control signal to the electric vehicle intelligent control unit;

[0089] An electric vehicle charging and discharging scheduling strategy formulation module is used for the electric vehicle intelligent control unit to combine the operation information of the power grid and the traffic network with the information set by the user of the user interaction unit to formulate the electric vehicle charging and discharging scheduling strategy;

[0090] A transmission module is used to transmit the electric vehicle charging and discharging scheduling strategy to the electric vehicle scheduling unit to complete the real-time scheduling of electric vehicles;

[0091] The user interaction module is used to express the user's willingness to discharge and set the power and duration of charging and discharging of the electric vehicle;

[0092] The electric vehicle intelligent control device is used to implement the steps of any one of the electric vehicle intelligent control methods.

[0093] A computer device comprises a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the computer program, the steps of any one of the methods for intelligent control of an electric vehicle are implemented.

[0094] A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods for intelligently controlling an electric vehicle.

[0095] The present invention has the following beneficial effects and advantages:

[0096] The system of the present invention includes a data collection and analysis prediction unit, a distribution network weak link intelligent identification unit, a power grid weakness monitoring and evaluation unit, an electric vehicle intelligent control unit, and a user interaction unit, which are used to identify the weak links of the distribution network and improve the power energy indicators of the weak links of the power grid by regulating electric vehicles.

[0097] There are weak links in the operation of the power grid, but when large-scale loads are connected to the power grid, that is, when the load is at peak, the power grid, especially the power grid's weak links, are reduced. The present invention uses a data acquisition and analysis prediction unit to collect power grid weakness parameters such as voltage, current, frequency, and harmonics, and performs classification and normalization processing and analysis on the collected data. The data prediction module predicts the power index parameters of the future time period by analyzing the collected data rules through an intelligent prediction algorithm; the weak links in the power grid are identified by the intelligent identification unit of the weak links of the distribution network, including weak lines and weak nodes; the power grid weakness monitoring and evaluation unit monitors and evaluates the weak line indicators of the power grid, and transmits the feedback signal to the electric vehicle intelligent control unit; the electric vehicle intelligent control unit combines the operation information of the power grid and the traffic network to formulate an electric vehicle charging and discharging scheduling strategy, and then completes the real-time scheduling of the electric vehicle according to the charging and discharging scheduling strategy, ensuring that large-scale loads are connected to the power grid, reducing the fluctuation of the power grid voltage, ensuring that the voltage and power of the power grid are balanced, improving the power index of the weak links of the power grid, and maintaining the stable operation of the power grid.

[0098] The present invention adds an intelligent identification unit for weak links in the distribution network, and further adds a step for intelligently identifying weak links in the distribution network, so that the relatively weak lines and nodes in the distribution network, i.e., those with poor power quality, large load fluctuations, and prone to abnormalities, can be identified; the present invention adds a power grid weakness monitoring and evaluation unit, and further adds a step for evaluating the weakness of weak nodes and lines in the power grid, so that the weakness of weak links in the power grid can be monitored and the improvement of the weakness of weak links in the power grid by regulating the charging and discharging of electric vehicles can be evaluated; the present invention adds an intelligent control unit for electric vehicles, so as to improve the weakness of weak links in the power grid by regulating the charging and discharging behavior of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0100] Figure 1 It is a schematic diagram of the structure of the intelligent control system of an electric vehicle of the present invention;

[0101] Figure 2 It is a structural block diagram of the data acquisition and analysis prediction unit of the present invention;

[0102] Figure 3 This is a structural block diagram of the intelligent identification unit for weak links in the distribution network of the present invention;

[0103] Figure 4 It is a structural block diagram of the power grid weakness monitoring and evaluation unit of the present invention;

[0104] Figure 5 This is a structural block diagram of the electric vehicle intelligent control unit of the present invention;

[0105] Figure 6 It is a structural block diagram of the user interaction unit of the present invention;

[0106] Figure 7 This is a flow chart of the intelligent control method of an electric vehicle of the present invention;

[0107] Figure 8 It is a flow chart of a method for predicting collected electrical parameter data using an intelligent prediction algorithm in the present invention;

[0108] Fig. 9 It is a flow chart of a method for identifying and evaluating weak nodes by a weak node identification module in the present invention;

[0109] Fig.10 It is a flow chart of a method for evaluating weak line identification by a weak line identification module in the present invention;

[0110] Fig.11 It is a flow chart of the comprehensive evaluation method of the power grid weakness monitoring and evaluation module in the present invention;

[0111] Fig.12 It is a flow chart of the operation method of intelligently controlling an electric vehicle in the present invention. DETAILED DESCRIPTION

[0112] In order to more clearly understand the above-mentioned objectives, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0113] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0114] Refer to the following Figure 1-Figure 12 The technical solutions of some embodiments of the present invention are described.

[0115] Example 1

[0116] The present invention provides an embodiment, which is an intelligent control system for electric vehicles. Figure 1 As shown, Figure 1 The present invention is a schematic diagram of the structure of the electric vehicle intelligent control system, specifically a structural block diagram of the electric vehicle intelligent control system for improving the power supply quality of weak links in the power grid.

[0117] The system of the present invention includes the following five units: a data acquisition and analysis prediction unit, a power distribution network weak link intelligent identification unit, a power grid weakness monitoring and evaluation unit, an electric vehicle intelligent control unit and a user interaction unit. Among them, the input end of the data acquisition and analysis prediction unit is connected to the secondary side of the power system bus, the input end of the power distribution network weak link intelligent identification unit is connected in parallel with the output end of the data acquisition and analysis prediction unit, the input end of the power grid weakness monitoring and evaluation unit is connected to the output end of the power grid weak link intelligent identification unit, the input end of the electric vehicle intelligent control unit is connected to the output end of the power grid weakness monitoring and evaluation unit, and the output end of the user interaction unit is connected to the input end of the electric vehicle intelligent control unit.

[0118] like Figure 2 As shown, Figure 2 The data acquisition and analysis prediction unit of the present invention comprises a data acquisition module, a data analysis module and a data prediction module.

[0119] The input end of the data acquisition module is connected to the secondary bus of the power grid, the output end of the data acquisition module is connected to the input end of the data analysis module, and the output end of the data analysis module is connected to the data prediction module. The data acquisition module collects power grid weakness parameters such as voltage, current, frequency, and harmonics, the data analysis module performs classification and normalization processing and analysis on the collected data, and the data prediction module analyzes the power quality parameters of the future time period by analyzing the collected data rules through an intelligent prediction algorithm.

[0120] like Figure 3 As shown, Figure 3 It is a structural block diagram of a weak link intelligent identification unit of a distribution network of the present invention, wherein the weak link intelligent identification unit of the distribution network comprises: a weak node identification module and a weak line identification module.

[0121] Among them, the input ends of the weak node identification module and the weak line identification module are connected in parallel with the output end of the data prediction module in the data acquisition and data acquisition and analysis prediction unit. The weak node identification module needs to formulate weak node indicators based on the voltage, current, frequency, harmonics and other power grid weakness parameters collected by the data acquisition module in the data acquisition and analysis prediction unit, and comprehensively evaluate the weak nodes based on the weak node indicators. The weak line identification module needs to formulate weak line indicators based on the voltage, current, frequency, harmonics and other electrical parameters collected by the data acquisition module in the data acquisition and analysis prediction unit, and comprehensively evaluate the weak lines through intelligent algorithms based on the weak line indicators.

[0122] like Figure 4 As shown, Figure 4It is a structural block diagram of a power grid weakness monitoring and evaluation unit of the present invention, wherein the power grid weakness monitoring and evaluation unit comprises: a power grid weakness monitoring and evaluation module and a feedback regulation module.

[0123] Among them, the input end of the power grid weakness monitoring and evaluation module is connected to the secondary side bus of the distribution network, and the power grid weakness indicators such as voltage, current, frequency, harmonics, etc. are detected and evaluated whether the indicators are within the specified weakness allowable range. If the electrical indicators exceed the weakness allowable range, the weakness signal is sent to the feedback regulation module; the output end of the power grid weakness monitoring and evaluation module is connected to the input end of the feedback regulation module, the feedback regulation module receives the weakness signal, and then transmits the control signal to the electric vehicle intelligent control unit; the output end of the feedback regulation module is connected to the input end of the electric vehicle intelligent control unit. When the electric vehicle intelligent control unit receives the control signal, it intelligently controls the electric vehicle, so that the electric vehicle discharges, adjusts the power supply quality of the power grid, and alleviates the weakness of the power grid.

[0124] like Figure 5 As shown, Figure 5 The electric vehicle intelligent control unit of the present invention is a structural block diagram, and the electric vehicle intelligent control unit includes: an optimization algorithm module and an electric vehicle scheduling module.

[0125] Among them, the output end of the optimization algorithm module is connected to the input end of the electric vehicle scheduling module, and the output end of the electric vehicle scheduling module is connected to the electric vehicle charging station; the optimization algorithm module combines the operation information of the power grid and the traffic network to formulate an electric vehicle charging and discharging scheduling strategy, and then transmits the charging and discharging scheduling strategy to the electric vehicle scheduling module to complete the real-time scheduling of electric vehicles.

[0126] like Figure 6 As shown, Figure 6 It is a structural block diagram of the user interaction unit of the present invention, and the user interaction unit includes: a discharge excitation module and a parameter setting module.

[0127] Among them, the discharge excitation module and the parameter setting module are connected in parallel to the input end of the electric vehicle intelligent control unit. The discharge excitation module controls the electric vehicle to discharge according to the set discharge power and discharge period, so that the electric vehicle can realize the energy storage function to adjust the electrical indicators of the power grid. The parameter setting module sets the power, time and other parameters for the user according to the charging needs. While meeting the user's needs, it adjusts the charging and discharging time period of the electric vehicle to complete the charging and discharging scheduling of the electric vehicle.

[0128] Example 2

[0129] The present invention further provides an embodiment, which is an intelligent control method for electric vehicles. Figure 7 As shown, Figure 7The flowchart of the electric vehicle intelligent control method of the present invention is implemented by using an electric vehicle intelligent control system as described in Example 1.

[0130] The present invention provides an intelligent control method for an electric vehicle, comprising the following steps:

[0131] Step 1. The data collection and analysis prediction unit collects grid weakness parameters such as voltage, current, frequency, harmonics, etc., and performs classification and normalization processing and analysis on the collected data. By analyzing the collected data rules, the power quality parameters of the future time period are predicted through the intelligent prediction algorithm;

[0132] Step 2. Obtain data feature quantities based on the power quality parameters predicted by the collected data rules and input them into the intelligent identification unit for weak links in the distribution network;

[0133] Step 3. The intelligent identification unit for weak links in the distribution network needs to formulate weak node indicators and weak line indicators based on the power quality parameters predicted by the collected data rules, and comprehensively evaluate weak nodes and weak lines through intelligent algorithms based on the weak indicators;

[0134] Step 4. According to the weak nodes and weak lines evaluated above, the grid weakness monitoring and evaluation module of the grid weakness monitoring and evaluation unit detects the grid weakness indicators such as voltage, current, frequency, harmonics, and evaluates whether the indicators are within the specified weakness allowable range. If the electrical indicators exceed the weakness allowable range, the weakness signal is sent to the feedback regulation module of the grid weakness monitoring and evaluation unit; after receiving the weakness signal, the feedback regulation module transmits the regulation signal to the electric vehicle intelligent regulation unit;

[0135] Step 5. When the electric vehicle intelligent control unit receives the control signal, the optimization algorithm module of the electric vehicle intelligent control unit combines the operation information of the power grid and the traffic network with the information set by the user of the user interaction unit to formulate the electric vehicle charging and discharging scheduling strategy;

[0136] Step 6. The electric vehicle charging and discharging scheduling strategy is transmitted to the electric vehicle scheduling unit to complete the real-time scheduling of electric vehicles. The electric vehicles are intelligently regulated to discharge the electric vehicles, adjust the power supply quality of the power grid, and alleviate the weakness of the power grid.

[0137] The user interaction unit is used to indicate that the user sets the charging and discharging time period and power according to the needs, that is, the user's discharge intention and the power and duration of charging and discharging of the electric vehicle.

[0138] Example 3

[0139] The present invention further provides an embodiment, which is an intelligent control method for electric vehicles, specifically an intelligent control method for electric vehicles for improving the power supply quality of weak links in the power grid, which is implemented using an intelligent control system for electric vehicles of the present invention as described in Example 1.

[0140] In the data acquisition and analysis prediction unit of the present invention, the data prediction module uses an intelligent prediction algorithm to predict the electrical parameter data collected by the data acquisition module, such as Figure 8 As shown, Figure 8 It is a flow chart of a method for predicting collected electrical parameter data using an intelligent prediction algorithm in the present invention.

[0141] The method for predicting the collected electrical parameter data using an intelligent prediction algorithm comprises the following steps:

[0142] Step 1. Normalize the collected voltage data;

[0143] Step 2. Build a gray wolf optimization model and initialize the gray wolf position;

[0144] Step 3. Input sample data, design fitness function, determine the positions of the first three layers of gray wolves and optimize them;

[0145] Step 4. Calculate and update the position and parameters of the last layer of gray wolves, and check whether the dimension is out of bounds;

[0146] Step 5. If the error is within the allowable range, return the optimal gray wolf α and output the weight;

[0147] Step 6. Establish the initialization parameters of the neural network model and use the weights optimized by the gray wolf optimization model to optimize the neural network model;

[0148] Step 7. Input sample parameters, i.e., the normalized voltage data obtained in step 1 for training;

[0149] Step 8. If the error is within the allowable range, output the prediction result. The error represents the allowable range of the difference between the data prediction and the actual value.

[0150] Example 4

[0151] The present invention further provides an embodiment, which is an intelligent control method for electric vehicles, specifically an intelligent control method for electric vehicles for improving the power supply quality of weak links in the power grid, which is implemented using an intelligent control system for electric vehicles as described in Example 1.

[0152] In the intelligent identification unit for weak links in the distribution network of the present invention, a weak node identification module is used to identify and evaluate weak nodes. Fig. 9 As shown, Fig. 9The flowchart of the weak node identification and evaluation method of the weak node identification module in the present invention includes the following steps:

[0153] Step 1. Perform data preprocessing on the node voltage by normalization or other methods;

[0154] Step 2. Use empirical mode decomposition to reduce the noise of the voltage signal;

[0155] Step 3. Predict the load node voltage using the intelligent prediction algorithm in Example 3;

[0156] Step 4. Analyze various types of electrical data and establish indicators for identifying weak nodes in the distribution network;

[0157] The various types of electrical data include: transformer overload degree, node status, meteorological risks, voltage over-limit and three-phase imbalance degree.

[0158] Step 5. Establish a distribution network weak node identification model and output the results.

[0159] Example 5

[0160] The present invention further provides an embodiment, which is an intelligent control method for electric vehicles, specifically an intelligent control method for electric vehicles for improving the power supply quality of weak links in the power grid, which is implemented using an intelligent control system for electric vehicles as described in Example 1.

[0161] In the intelligent identification unit for weak links in the distribution network of the present invention, the weak line identification module identifies and evaluates the weak line, and the method flow is as follows: Fig.10 As shown, Fig.10 The flowchart of the weak line identification module of the present invention is a weak line identification and evaluation method, which includes the following steps:

[0162] Step 1. Preprocess the node power distribution data by normalization and other methods;

[0163] Step 2. Identify the actual line topology and assign the collected data to the actual line;

[0164] Step 3. Construct a distribution network branch power supply matrix based on the preprocessed data in step 1 and the actual line in step 2;

[0165] Step 4. Analyze various types of electrical distribution data and establish weak line identification indicators of the distribution network; the various types of electrical distribution data include: improved node degree, improved branch degree, improved branch electrical transmission medium and line voltage stability.

[0166] Step 5. According to the weak line identification index of the distribution network in step 4, a weak line identification model of the distribution network is established, and a comprehensive evaluation result is output. The comprehensive evaluation result is a comprehensive evaluation result output by the calculation of the model according to the input index.

[0167] Example 6

[0168] The present invention further provides an embodiment, which is an intelligent control method for electric vehicles, specifically an intelligent control method for electric vehicles for improving the power supply quality of weak links in the power grid, which is implemented using an intelligent control system for electric vehicles as described in Example 1.

[0169] In the power grid weakness monitoring and evaluation unit of the present invention, the comprehensive evaluation method of the power grid weakness monitoring and evaluation module is as follows: Fig.11 As shown, Fig.11 The flowchart of the comprehensive evaluation method of the power grid weakness monitoring and evaluation module in the present invention is as follows. The method uses a comprehensive weighting method based on the minimum discriminant information principle to comprehensively evaluate the power grid weakness, and specifically includes the following steps:

[0170] Step 1. Input the collected and processed data, sort the indicators to be evaluated according to their relative importance, and calculate the subjective weight coefficient ω zgi The values ​​are:

[0171]

[0172] In the above formula: ω zgn is the subjective weight coefficient, n is the number of summation factors in the formula, i is the indicator ranking in the formula parameters, k is the indicator number, r k is the index importance coefficient.

[0173] According to the importance of adjacent indicators, the weight of each indicator can be calculated:

[0174] ω zgi =r i+1 ω zgi+1

[0175] In the above formula: ω zgi The subjective weight of each indicator.

[0176] Therefore, ω zg =(ω zg1 ,ω zg2 ,...,ω zgn ) constitutes the subjective weight vector of the evaluation index.

[0177] Step 2. According to the information entropy, use the improved entropy weight method to calculate the objective weight coefficient ω kg .

[0178] The calculation formula of the improved entropy weight method is shown as follows:

[0179]

[0180] In the above formula, ω kgi is the objective weight coefficient of the ith indicator, and satisfies Σω=1; m is the number of indicators; h i is the entropy value of the indicator, and satisfies 0≤h i ≤1, n is the number of summation factors in the formula.

[0181] Take any two entropy weights ω kg1 and ω kg2 , the corresponding entropy values ​​are h1 and h2, given by |ω kg1 -ω kg2 |Available:

[0182]

[0183] When the entropy weight ω kg1 and entropy weight ω kg2 When the entropy value of is infinitely close, the difference is approximately 0, that is, At this point, the above formula can be transformed into:

[0184]

[0185] In the above formula: ζ is the limit of the difference in the mathematical formula.

[0186] Since ξ approaches 0 and is a definite value, so |ω kg1 -ω kg2 The change of | is consistent with the change trend of ξ. Therefore, when the entropy value approaches 0, the entropy weight will not change exponentially. When the gap between h1 and h2 is large, assuming that h1>>h2 and h1 and h2 satisfy 0≤h i ≤1, then let |h2-h1|=ξ(ξ→1), and because the number of entropy values ​​is finite, the number of indicators m is a finite real number, and:

[0187] but

[0188] In the above formula: ξ is the limit of the difference in the mathematical formula, h i is the entropy value of each indicator.

[0189] In summary, the objective weight vector obtained by the improved entropy method is: ω kg =(ω kg1 ,ω kg2 ,…,ω kgn ), where ω kgis the objective weight vector, ω kgn is the objective weight coefficient.

[0190] Step 3. Combine the subjective weighting method and the objective weighting method to get as close to the actual subjective and objective weights as possible, use the minimum discriminant information principle to combine the subjective and objective weights, and calculate the weight value of each indicator ω i .

[0191] The objective function is set according to the minimum discriminant information principle:

[0192]

[0193] Secondly, in order to find the optimal solution to the above problem, a Lagrangian function is constructed to solve it:

[0194]

[0195] In the above formula: L is the constructed Lagrangian function.

[0196] make We can get:

[0197]

[0198] In the above formula: λ is the coefficient in the mathematical formula.

[0199] The weight values ​​of each indicator are:

[0200]

[0201] Step 4: Substituting various indicators of weak nodes and weak lines, the comprehensive evaluation results of weak links in the distribution network can be obtained, and the indicators are:

[0202] R VUL =ω i R i

[0203] In the above formula: R VUL is the comprehensive assessment result of the weak links in the distribution network, R i are the values ​​of each indicator, and R i ∈{R BO ,R Volt ,R UB ,R Lbi ,R χij ,R VS};ω i is the weight value of each indicator, and the comprehensive evaluation result of the weak links of the distribution network is R VUL The larger the value is, the higher the weakness of this link caused by power supply quality is.

[0204] Example 7

[0205] The present invention further provides an embodiment, which is an intelligent control method for electric vehicles, specifically an intelligent control method for electric vehicles for improving the power supply quality of weak links in the power grid, which is implemented using an intelligent control system for electric vehicles as described in Example 1.

[0206] The electric vehicle dispatching module in the electric vehicle intelligent control unit of the present invention has an operation method as follows: Fig.12 As shown, Fig.12 It is a flow chart of the method for intelligently controlling the operation of an electric vehicle in the present invention.

[0207] The method comprises the following steps:

[0208] Step 1. Obtaining a feedback regulation signal from a feedback regulation module in a grid weakness monitoring and evaluation unit, requiring the electric vehicle to provide electric energy to the grid;

[0209] Step 2. The optimization algorithm of the electric vehicle intelligent control unit is to transform the dispatching method into an optimization problem, with user cost, grid operation loss and weakness index as the objective function:

[0210]

[0211] In the above formula, P t loss They are the user's cost and the network loss of the power grid operation, X is the minimum optimization function, J1 is the user cost, J2 is the power grid loss cost, T is the total duration, t is different time periods, and k2 is the loss coefficient.

[0212] Step 3. Optimize the objective function through the optimization algorithm to obtain the optimal objective solution, that is, minimize the objective;

[0213] Step 4. Check whether the optimal solution of the objective function meets the error and the number of iterations. If so, output the optimal result.

[0214] Step 5. The optimal control strategy obtained is executed by the electric vehicle control module to control the electric vehicles that are connected to the power grid to complete the discharge task while ensuring their charging needs, thereby improving the power supply quality of weak links.

[0215] Step 6. Complete the real-time height of the electric vehicle and intelligently control the electric vehicle to discharge the electric vehicle.

[0216] Example 8

[0217] Based on the same inventive concept, an embodiment of the present invention further provides a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, the steps of any one of the electric vehicle intelligent control methods described in embodiments 2-7 are implemented.

[0218] Example 9

[0219] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the electric vehicle intelligent control methods described in embodiments 2-7 are implemented.

[0220] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0221] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0222] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0223] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0224] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An intelligent control system for electric vehicles, characterized by: It includes a data acquisition and analysis prediction unit, a distribution network weak link intelligent identification unit, a power grid weakness monitoring and evaluation unit, an electric vehicle intelligent control unit and a user interaction unit; wherein the input end of the data acquisition and analysis prediction unit is connected to the secondary side of the power system bus system bus, the input end of the distribution network weak link intelligent identification unit is connected in parallel with the output end of the data acquisition and analysis prediction unit, the input end of the power grid weakness monitoring and evaluation unit is connected to the output end of the power grid weak link intelligent identification unit, the input end of the electric vehicle intelligent control unit is connected to the output end of the power grid weakness monitoring and evaluation unit, and the output end of the user interaction unit is connected to the input end of the electric vehicle intelligent control unit; The data collection and analysis prediction unit collects power grid weakness parameters and performs analysis and prediction; The weak link intelligent identification unit is used to comprehensively evaluate the analyzed and predicted parameters; The power grid weakness monitoring and evaluation unit is used to detect the comprehensive evaluation results; The electric vehicle intelligent control unit is used to formulate an electric vehicle charging and discharging scheduling strategy according to the detection results; The user interaction unit is used to indicate the user's willingness to discharge and to set the power and duration of charging and discharging of the electric vehicle.

2. The electric vehicle intelligent control system according to claim 1 is characterized in that: The data acquisition and analysis prediction unit includes: a data acquisition module, a data analysis module and a data prediction module; wherein the input end of the data acquisition module is connected to the secondary side bus of the power grid, the output end of the data acquisition module is connected to the input end of the data analysis module, and the output end of the data analysis module is connected to the data prediction module; the data acquisition module collects power grid weakness parameters, the data analysis module classifies and normalizes the collected data, and the data prediction module analyzes the power quality parameters of the future time period by analyzing the collected data rules through the intelligent prediction algorithm; The intelligent identification unit for weak links in the distribution network includes: a weak node identification module and a weak line identification module; wherein the input ends of the weak node identification module and the weak line identification module are connected in parallel with the output end of the data prediction module in the data acquisition and data acquisition and analysis prediction unit; the weak node identification module needs to formulate weak node indicators according to the weak parameters of the power grid collected by the data acquisition module in the data acquisition and analysis prediction unit, and comprehensively evaluate the weak nodes according to the weak node indicators; the weak line identification module formulates weak line indicators according to the electrical parameters collected by the data acquisition module in the data acquisition and analysis prediction unit, and comprehensively evaluates the weak lines according to the weak line indicators through intelligent algorithms; The grid weakness monitoring and evaluation unit comprises: a grid weakness monitoring and evaluation module and a feedback regulation module; wherein the input end of the grid weakness monitoring and evaluation module is connected to the secondary side bus of the distribution network, detects the grid weakness index and evaluates whether the index is within the specified weakness allowable range, and if the electrical index exceeds the weakness allowable range, sends the weakness signal to the feedback regulation module; the output end of the grid weakness monitoring and evaluation module is connected to the input end of the feedback regulation module, and the feedback regulation module receives the weakness signal and transmits the control signal to the electric vehicle intelligent control unit; the output end of the feedback regulation module is connected to the input end of the electric vehicle intelligent control unit, and when the electric vehicle intelligent control unit receives the control signal, the electric vehicle is intelligently controlled; The electric vehicle intelligent control unit comprises: an optimization algorithm module and an electric vehicle dispatching module; wherein the output end of the optimization algorithm module is connected to the input end of the electric vehicle dispatching module, and the output end of the electric vehicle dispatching module is connected to the electric vehicle charging station; the optimization algorithm module formulates an electric vehicle charging and discharging dispatching strategy based on the operation information of the power grid and the traffic network, and transmits the charging and discharging dispatching strategy to the electric vehicle dispatching module to complete the real-time dispatching of the electric vehicle; The user interaction unit includes: a discharge excitation module and a parameter setting module; wherein the discharge excitation module and the parameter setting module are connected in parallel to the input end of the electric vehicle intelligent control unit, the discharge excitation module discharges the power and discharge time period of the electric vehicle to the power grid, so that the electric vehicle realizes the energy storage function to adjust the electrical indicators of the power grid, and the parameter setting module sets the power and time parameters for the user according to the charging demand, and adjusts the charging and discharging time period of the electric vehicle while meeting the user's needs, thereby completing the charging and discharging scheduling of the electric vehicle.

3. An intelligent control method for electric vehicles, characterized by: include: The data collection and analysis prediction unit collects grid weakness parameters, performs classification and normalization processing and analysis, and predicts power quality parameters for future time periods; The data feature quantity is obtained according to the predicted power quality parameters and input into the intelligent identification unit of the weak link of the distribution network; Formulate weak node indicators and weak line indicators based on the power quality parameters predicted by the collected data rules, and comprehensively evaluate weak nodes and weak lines through intelligent algorithms based on the weak indicators; According to the weak nodes and weak lines, the weak indicators of the power grid are detected and evaluated whether the indicators are within the specified weak range. If the electrical indicators exceed the weak range, the weak signal is sent to the power grid weakness monitoring and evaluation unit, and the power grid weakness monitoring and evaluation unit transmits the control signal to the electric vehicle intelligent control unit; The electric vehicle intelligent control unit combines the operation information of the power grid and the traffic network with the information set by the user of the user interaction unit to formulate the charging and discharging scheduling strategy of the electric vehicle; The charging and discharging scheduling strategy is transmitted to the electric vehicle scheduling unit to complete the real-time scheduling of electric vehicles.

4. The electric vehicle intelligent control method according to claim 3 is characterized by: The data collection and analysis prediction unit collects grid weakness parameters, performs classification and normalization processing and analysis, and predicts power quality parameters in future time periods. The prediction method includes: Step 1. Normalize the collected voltage data; Step 2. Build a gray wolf optimization model and initialize the gray wolf position; Step 3. Input sample data, design fitness function, determine the positions of the first three layers of gray wolves, and optimize; Step 4. Calculate and update the position and parameters of the last layer of gray wolves, and check whether the dimension is out of bounds; Step 5. If the error is within the allowable range, return the optimal gray wolf and output the weight; Step 6. Establish the initialization parameters of the neural network model, and use the weights and thresholds optimized by the gray wolf optimization model to optimize the neural network model; Step 7. Input sample parameters and train the normalized voltage data; Step 8. If the error is within the allowable range, output the prediction result.

5. The electric vehicle intelligent control method according to claim 3 is characterized by: The power quality parameters predicted according to the collected data rules are used to formulate weak node indicators and weak line indicators, and the weak nodes and weak lines are comprehensively evaluated through intelligent algorithms according to the weak indicators; wherein the evaluation method includes: Perform data preprocessing on the node voltage by normalization and other methods; Use empirical mode decomposition to reduce the noise of voltage signals; Predict the load node voltage through intelligent prediction algorithm; Analyze various types of electrical data and establish indicators for identifying weak nodes in the distribution network; Establish a distribution network weak node identification model and output the results.

6. The electric vehicle intelligent control method according to claim 3 is characterized by: The evaluation method of the power grid weakness monitoring and evaluation unit includes: Step 1. Input the collected and processed data, sort the indicators to be evaluated, and calculate the subjective weight coefficient ω zgi The values ​​are: In the above formula: ω zgn is the subjective weight coefficient, n is the number of summation factors in the formula, i is the index ranking in the formula parameter, k is the index number, r k is the index importance coefficient; According to the importance of adjacent indicators, the weight of each indicator is calculated: oh zgi =r i+1 oh zgi+1 In the above formula: ω zgi The subjective weight of each indicator; Therefore, ω zg =(ω zg1 ,ω zg2 ,...,ω zgn ) constitutes the subjective weight vector of the evaluation index; Step 2. According to the information entropy, use the improved entropy weight method to calculate the objective weight coefficient ω kg ; The calculation formula of the improved entropy weight method is shown as follows: In the above formula, ω kgi is the objective weight coefficient of the ith indicator, and satisfies Σω=1; m is the number of indicators; h i is the entropy value of the indicator, and satisfies 0≤h i ≤1, n is the number of summation factors in the formula; Take any two entropy weights ω kg1 and ω kg2 , the corresponding entropy values ​​are h1 and h2, given by |ω kg1 -ω kg2 |Available: When the entropy weight ω kg1 and entropy weight ω kg2 When the entropy value of is infinitely close, the difference is approximately 0, that is, The above formula is transformed into: In the above formula: ζ is the limit of the difference in the mathematical formula; ξ approaches 0 and is a definite value, so |ω kg1 -ω kg2 The change of | is consistent with the change trend of ξ; when the entropy value approaches 0, the entropy weight does not change exponentially; when the gap between h1 and h2 is large, assuming that h1>>h2 and h1 and h2 satisfy 0≤h i ≤1, let |h2-h1|=ξ(ξ→1), the number of indicators m is a finite real number, and: but In the above formula: ξ is the limit of the difference in the mathematical formula, h i is the entropy value of each indicator; The objective weight vector obtained by the improved entropy method is: ω kg =(ω kg1 ,ω kg2 ,...,ω kgn ), where ω kg is the objective weight vector, ω kgn is the objective weight coefficient; Step 3. Combine the subjective weighting method and the objective weighting method to approach the actual subjective and objective weights, use the minimum discriminant information principle to combine the subjective and objective weights, and calculate the weight value of each indicator ω i ; The objective function is set according to the minimum discriminant information principle: Construct the Lagrangian function to solve: In the above formula: L is the constructed Lagrangian function; make We can get: In the above formula: λ is the coefficient in the mathematical formula; The weight values ​​of each indicator are: Step 4: Substitute the various indicators of weak nodes and weak lines to obtain the comprehensive evaluation results of weak links in the distribution network. The indicators are: R VUL =ω i R i In the above formula: R VUL is the comprehensive assessment result of the weak links in the distribution network, R i are the values ​​of each indicator, and R i ∈{R BO ,R Volt ,R UB ,R Lbi ,R χij ,R VS };ω i is the weight value of each indicator; the comprehensive evaluation result of the weak links of the distribution network R VUL The larger the value is, the higher the weakness of this link caused by power supply quality is.

7. The electric vehicle intelligent control method according to claim 3 is characterized by: The electric vehicle intelligent control unit, the control method thereof comprises: Step 1. Obtaining a feedback regulation signal from a feedback regulation module in a grid weakness monitoring and evaluation unit, requiring the electric vehicle to provide electric energy to the grid; Step 2. The optimization algorithm of the electric vehicle intelligent control unit is to transform the dispatching method into an optimization problem, with user cost, grid operation loss and weakness index as the objective function: In the above formula, are the user's cost and the network loss of the power grid operation, respectively. X is the minimum optimization function, J1 is the user's cost, J2 is the power grid loss cost, T is the total duration, t is different time periods, and k2 is the loss coefficient; Step 3. Optimize the objective function through the optimization algorithm to obtain the optimal objective solution, that is, minimize the objective; Step 4. Check whether the optimal solution of the objective function meets the error and the number of iterations. If so, output the optimal result. Step 5. The obtained optimal control strategy is executed by the electric vehicle control module to control the electric vehicles that are connected to the power grid; Step 6. Complete the real-time height of the electric vehicle and intelligently control the electric vehicle to discharge the electric vehicle.

8. An intelligent control device for electric vehicles, characterized by: include: The data collection and analysis module is used to collect the power grid weakness parameters, analyze and classify them, and predict the power quality parameters in the future time period. An input module is used to obtain data feature quantities according to the predicted power quality parameters and input them into the intelligent identification unit of weak links in the distribution network; Comprehensive evaluation module, used to formulate weak node indicators and weak line indicators according to the power quality parameters predicted by the collected data rules, and comprehensively evaluate weak nodes and weak lines through intelligent algorithms according to the weak indicators; The detection and evaluation module is used to detect the power grid weakness index according to the weak nodes and weak lines and evaluate whether the index is within the specified weakness allowable range. If the electrical index exceeds the weakness allowable range, the weakness signal is sent to the power grid weakness monitoring and evaluation unit, and the power grid weakness monitoring and evaluation unit transmits the control signal to the electric vehicle intelligent control unit; An electric vehicle charging and discharging scheduling strategy formulation module is used for the electric vehicle intelligent control unit to combine the operation information of the power grid and the traffic network with the information set by the user of the user interaction unit to formulate the electric vehicle charging and discharging scheduling strategy; A transmission module is used to transmit the electric vehicle charging and discharging scheduling strategy to the electric vehicle scheduling unit to complete the real-time scheduling of electric vehicles; A user interaction module, used to indicate the user's willingness to discharge and to set the power and duration of charging and discharging of the electric vehicle; The electric vehicle intelligent control device is used to implement the steps of an electric vehicle intelligent control method as described in any one of claims 4-7.

9. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the steps of an electric vehicle intelligent control method as described in any one of claims 4 to 7 are implemented.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the electric vehicle intelligent control method described in any one of claims 4 to 7 are implemented.

Images