Shopping mall discharging system based on V2G technology

Abstract

The invention relates to a V2G technology-based market discharge system, and the system comprises a flow analysis module which is used for predicting the power load condition of a commercial district in a future time period T in real time according to the historical power data of the commercial district; the data acquisition module is used for calculating the mileage anxiety state of an electric vehicle user; the behavior analysis module is used for calculating the probability that the electric vehicle user is guided; the behavior guiding module responds to reply information of the electric vehicle user to the charging and discharging request, and guides the electric vehicle user to a corresponding commercial district load node when the electric vehicle user arrives at the commercial district; and the discharge adjusting module is used for calculating the discharge power and the discharge time of the electric vehicle user at the load node of the commercial area according to the electrical load condition of the commercial area in the future time period T, and prompting the electric vehicle user to discharge. Management difficulty and operation cost of the power grid can be reduced, and stable operation of the power grid is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system and electric vehicle, and in particular to a shopping mall discharge system based on V2G technology. Background Art

[0002] With the rapid growth of the number of electric vehicles (EVs), the power system is facing increasing load fluctuations and management pressures. The traditional power grid architecture is difficult to cope with the peak load problem caused by the simultaneous charging and discharging of large-scale electric vehicles, and the introduction of V2G (Vehicle-to-Grid) technology provides a new idea for solving this problem. V2G technology enables electric vehicles to feed back electric energy to the power grid when they are not in motion, thereby providing additional power support to the power grid during peak power demand and balancing power supply and demand. However, the current V2G technology still has the following problems and challenges in practical applications: Existing technologies are difficult to effectively predict and manage the charging and discharging behavior of electric vehicles, resulting in large fluctuations in the load of the power grid, which increases the difficulty of power grid management and operating costs. Summary of the invention

[0003] In order to solve the problems existing in the background technology, the present invention provides a shopping mall discharge system based on V2G technology, which monitors the charge state of electric vehicles and the power load of commercial areas in real time, utilizes user profiling technology and discharge control algorithm, realizes effective management and guidance of the discharge behavior of electric vehicles, and ensures the stable operation of the power grid.

[0004] In order to achieve the above technical objectives, the present invention provides a shopping mall discharge system based on V2G technology, comprising:

[0005] Load monitoring terminal, installed in the power distribution room of the commercial area, is used to collect power data of the commercial area in real time;

[0006] The flow analysis module is used to predict the power load of the commercial area in the future time period T in real time based on the historical power data of the commercial area;

[0007] A data acquisition module, used to obtain facial image data of electric vehicle users to calculate the range anxiety status of electric vehicle users;

[0008] A behavior analysis module, used to calculate the probability of an electric vehicle user being guided according to the electric vehicle user's range anxiety state;

[0009] The behavior guidance module sends a discharge request to the electric vehicle user according to the power load of the commercial area in the future time period T when the probability of the electric vehicle user being guided is greater than a set threshold a; and in response to the reply information of the electric vehicle user to the charge and discharge request, guides the electric vehicle user to the corresponding load node in the commercial area when the electric vehicle user arrives at the commercial area;

[0010] The discharge regulation module is used to calculate the discharge power and discharge time of electric vehicle users at the load nodes in the commercial area according to the power load conditions in the commercial area in the future period T.

[0011] The present invention has at least the following beneficial effects

[0012] The present invention collects power data of the commercial area in real time through the load monitoring terminal, providing a rich and accurate data basis for the flow analysis module. The flow analysis module uses historical power data to predict the power load of the commercial area in the future time period T in real time, significantly improving the accuracy and timeliness of load prediction; the data acquisition module calculates the user's mileage anxiety state by acquiring the facial image data of the electric vehicle user, which helps to understand the charging needs and psychological state of the electric vehicle user and provide an important reference for the subsequent guidance strategy; the behavior analysis module is used to calculate the probability of the electric vehicle user being guided to the commercial area for discharge; and in response to the reply information of the electric vehicle user to the charging and discharging request, the electric vehicle user is guided to the corresponding commercial area load node when the electric vehicle user arrives at the commercial area; the system intelligently guides the electric vehicle user to the commercial area load node for discharge; the discharge regulation module calculates the discharge power and discharge time of the electric vehicle user at the commercial area load node; the load monitoring terminal, the flow analysis module, the data acquisition module, the behavior analysis module, the behavior guidance module and the discharge regulation module together constitute a complete shopping mall discharge system based on V2G technology. The system can collect and analyze electricity data in real time, predict future electricity load conditions, and provide intelligent guidance based on the mileage anxiety status and behavioral characteristics of electric vehicle users. It achieves precise management of electricity loads in commercial areas and effective use of electric vehicle energy storage resources, reduces the management difficulty and operating costs of the power grid, and ensures the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the system framework of the present invention;

[0014] Figure 2 Schematic diagram of anxiety detection based on facial feature points;

[0015] Figure 3 It is a comparison of load curves before and after discharge and a peak reduction effect diagram of the present invention. DETAILED DESCRIPTION

[0016] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0017] See also Figure 1 The present invention provides a shopping mall discharge system based on V2G technology, comprising:

[0018] Load monitoring terminal, installed in the power distribution room of the commercial area, is used to collect power data of the commercial area in real time;

[0019] In this embodiment, the load monitoring terminal is mainly used to collect current data, voltage data and power data of the distribution network; it is mainly monitored through relevant power monitoring sensors, such as current sensors, voltage sensors, etc.

[0020] The flow analysis module is used to predict the power load of the commercial area in the future time period T in real time based on the historical power data of the commercial area;

[0021] A data acquisition module, used to obtain facial image data of electric vehicle users to calculate the range anxiety status of electric vehicle users;

[0022] A behavior analysis module, used to calculate the probability of an electric vehicle user being guided according to the electric vehicle user's range anxiety state;

[0023] The behavior guidance module sends a discharge request to the electric vehicle user according to the power load of the commercial area in the future time period T when the probability of the electric vehicle user being guided is greater than a set threshold a; and in response to the reply information of the electric vehicle user to the charge and discharge request, guides the electric vehicle user to the corresponding load node in the commercial area when the electric vehicle user arrives at the commercial area;

[0024] The discharge regulation module is used to calculate the discharge power and discharge time of electric vehicle users at the load nodes in the commercial area according to the power load conditions in the commercial area in the future period T, and prompt the electric vehicle users to discharge.

[0025] Preferably, the predicting of the power load situation of the commercial area in the future time period T includes:

[0026] X t =[P(tn),P(t-n+1),…,P(t-1),P(t)]

[0027] L(t)=[P(t+1),P(t+2),…,P(t+T)]=LSTM(X t )

[0028] Among them, t represents the current time, P(tn) represents the power data of the commercial area at time (tn); n represents the number of samples of historical power data; LSTM represents long short-term memory network; P(t+k) represents the power load of the commercial area at time t+k in the future, k = {1,2,..T}; L(t) represents the power load of the commercial area in the future time period T.

[0029] In this embodiment, the long short-term memory network (LSTM) is introduced as the core prediction algorithm to further improve the accuracy and reliability of load prediction. In addition, a mall discharge system based on V2G technology is constructed by combining modules such as behavior analysis, behavior guidance, and discharge regulation. This system not only improves the accuracy and reliability of power load prediction, but also realizes the optimal configuration and efficient utilization of electric vehicle energy storage resources, providing strong support for building a green, low-carbon, and intelligent urban energy system.

[0030] Preferably, the calculating of the range anxiety state of the electric vehicle user comprises:

[0031] When the distance between the electric vehicle user and the commercial area is less than the set threshold d, the facial image of the electric vehicle user is collected, and the range anxiety state of the electric vehicle user is calculated in real time;

[0032] The calculation of the range anxiety state of the electric vehicle user includes:

[0033] The facial feature vector of the electric car user is extracted using the facial feature point detection library Dlib based on the facial image of the electric car user;

[0034] See also Figure 2In this embodiment, the facial image of the electric car user is captured by the in-car camera, and the facial feature point detection library Dlib is used to automatically extract 5 feature points of each eyebrow, and the feature points of the left and right eyebrows are calibrated as 1, 2, 3, 4, 5, 6, 7, 8, 9, and 10 respectively; 6 feature points of each eye are collected, and the feature points of the left and right eyes are calibrated as 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, and 22; 7 feature points of the nose are collected and calibrated as 23, 24, 25, 26, 27, 28, and 29; 20 feature points of the mouth are collected and calibrated as 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, and 49. Construct the driver's facial coordinate system with the center of the nose as the origin, the line connecting the nose wings as the x-axis, and the line connecting the nose bridge as the y-axis, and obtain the geometric feature set h of the i-th facial image of the electric vehicle user i =(x1,y1,…,x 49 ,y 49 ), (x1, y1) represents the coordinates of the first feature point in the driver's facial coordinate system, and the same is true for the other feature points; then the facial feature vector corresponding to the electric vehicle user is H = (h1, h2, ..., h n1 ) T , n1 means collecting n1 facial images.

[0035] According to the facial feature vectors of electric vehicle users and combined with the FACS coding system, a range anxiety state determination model for electric vehicle users is constructed, and the range anxiety state of electric vehicle users is calculated based on the constructed range anxiety state determination model.

[0036] In this embodiment, after extracting the facial feature vector of the electric vehicle user, a range anxiety state determination model of the electric vehicle user based on eyebrows (u), eyes (v), and mouth (w) is constructed in combination with the FACS coding system; t1 and t2 are defined to represent the initial moment and the next moment of face image acquisition respectively, and x m ,y m Indicates the horizontal and vertical coordinates of the mth feature point at time t1; Represents the horizontal and vertical coordinates of the mth feature point at time t2. The expression of the user's anxious facial state is:

[0037]

[0038] Among them, u is the eyebrow feature, v is the eye feature, and w is the mouth feature.

[0039] The range anxiety state determination model of electric vehicle users is:

[0040] g=α n u+βn v+γ n w

[0041] Where g is the range anxiety state of electric vehicle users, which is a dimensionless unit with a value of 0-1; α n , β n , γ n is the adjustment factor.

[0042] Preferably, the probability that the electric vehicle user is guided includes:

[0043]

[0044] Where c represents the probability of an electric vehicle user being guided, exp() represents the natural exponential function; α and β are adjustment coefficients; a0∈(0,1) means that the average power consumption of an electric vehicle user per trip is not higher than a0 times the battery capacity; B cap represents the battery capacity; ε is the average energy consumption of electric vehicle users; d represents the travel distance from the current location of the electric vehicle user to the commercial area; S SOC Indicates the remaining power of the electric vehicle user; S th represents the minimum safe power of electric vehicle users; θ1 and θ2 represent adjustment coefficients, and g represents the mileage anxiety state of electric vehicle users.

[0045] In this embodiment, through the calculation of range anxiety, the system can evaluate the psychological state of electric vehicle users in real time, providing the system with accurate user emotional data, so that it can intelligently judge whether the user is willing to participate in discharge and optimize the discharge guidance strategy, improve user experience, reduce range anxiety, and ultimately help the power grid manage electric vehicle discharge behavior more efficiently, balance load demand, and improve the stability and efficiency of system operation.

[0046] In this embodiment, it is defined that the average power consumption per trip is no higher than 60% of the battery capacity.

[0047] Preferably, sending a discharge request to an electric vehicle user according to the power load situation of the commercial area in the future time period T includes:

[0048] Calculate the peak load index of the commercial area's electricity load according to the electricity load situation of the commercial area in the future time period T;

[0049]

[0050] Among them, PLI represents the peak load index of the commercial area power load, t0 represents the time point when the detection starts, t0∈[0,T]; P(t0+k) represents the power load at time t0+k; N is the total number of moments in the time period;

[0051] Calculate the time when the commercial area electricity load enters the peak period based on the peak load index of the commercial area electricity load;

[0052] t peak =t0(PLI>P th )

[0053] Among them, t peak is the time point when the load peak period begins; P th is the preset peak load threshold;

[0054] The time to send the discharge request is calculated based on the time when the commercial area's electricity load enters the peak period:

[0055]

[0056] Among them, t m The time to send a discharge request to the electric vehicle user; t a0 is a fixed value for the time to arrive at the commercial area in advance; d i represents the travel distance of electric vehicle user i from the commercial area, v i is the average driving speed of electric vehicle user i;

[0057] At the time t at which the discharge request is sent m Send a discharge request to the electric vehicle user.

[0058] Preferably, when the electric vehicle user arrives at the commercial area, guiding the electric vehicle user to the corresponding commercial area load node comprises:

[0059] S101: When the electric vehicle user arrives at the commercial area, the distance between the electric vehicle user and each load node in the commercial area and the discharge waiting time of the electric vehicle user at each load node in the commercial area are calculated;

[0060] S102: traverse each commercial area load node to check whether the commercial area load node is occupied by other electric vehicle users. If so, execute step S103; otherwise, execute step S105;

[0061] S103: Determine whether the discharge waiting time of the electric vehicle user at the load node in the commercial area is less than a set threshold τ, if so, execute step S104;

[0062] S104: Determine whether the distance from the electric vehicle user to the load node in the commercial area is less than a set threshold value θ. If so, execute step S105:

[0063] S105: Determine whether the difference between the dispatching potential of the electric vehicle user at the commercial area load node and the dispatching demand of the commercial area load node is less than a set threshold δ. If so, allocate the commercial area load node to the electric vehicle user and stop traversal.

[0064] In this embodiment, through steps S101 to S105, the system can intelligently guide electric vehicle users to select appropriate discharge nodes, ensuring that users select the best node for discharge according to distance and waiting time. This not only reduces the user's waiting time and improves the user experience, but also optimizes the distribution of power loads, avoids resource waste, balances the power demand of the shopping mall area, and improves the overall system scheduling efficiency and the stability of the power grid.

[0065] In this embodiment, the state of each commercial area load node is defined as S j It means that for each load node, the dispatch potential R of electric vehicle users at the load node in the commercial area is calculated. i,j ;

[0066]

[0067] R i,j =min(C j,dis ,η×SOC i ×P i )

[0068] Among them, R i,j represents the dispatch potential of electric vehicle users at load node j in the commercial area, C j,dis represents the maximum discharge capacity of load node j in the commercial area; η is the discharge efficiency; SOC i represents the remaining battery capacity of electric vehicle user i (expressed as a percentage); P i is the maximum discharge power of electric vehicle user i.

[0069] For each electric vehicle user i, calculate the driving distance from its current location to each commercial area load node j;

[0070] The discharge waiting time of each electric vehicle user i after arriving at the node is estimated. The discharge waiting time of electric vehicle user i at load node j in the commercial area is:

[0071]

[0072] In the formula, Q i represents the remaining discharge capacity of the i-th vehicle; P i represents the maximum discharge power of the i-th vehicle; K represents the number of vehicles currently in the queue; T wait,avg is the discharge waiting time of electric vehicle user i at load node j in the commercial area.

[0073] According to the electricity load curve of the commercial area, the scheduling demand of each node j is calculated as follows:

[0074]

[0075] C(t)=L u (t)-L tg

[0076] Among them, C j represents the dispatching demand of load node j in the commercial area, represents the maximum load capacity of load node j in the commercial area; m represents the total number of load nodes in the commercial area; C(t) represents the discharge demand of the commercial area power grid; ω j represents the adjustment coefficient of load node j in the commercial area; L u (t) represents the real-time power load in the commercial area; L tg It represents the target control power of the commercial area power grid.

[0077] The greedy algorithm is used to allocate the optimal commercial area load node j to electric vehicle user i. The specific steps are as follows:

[0078] S101: When electric vehicle user i (initial value is 1) arrives at the commercial area, the system starts to guide the user to select a load node (charging pile node) in the commercial area and prepares to allocate a suitable load node in the commercial area to the user for discharge service.

[0079] For each electric vehicle user i, initialize the remaining battery capacity SOC of electric vehicle user i i , Maximum discharge power P i and the average speed v i ;

[0080] S102: The system starts from the first commercial area load node j=1 and checks whether node j is currently occupied by other electric vehicle users. If the commercial area load node is occupied (i.e. S(j)=1), the next step S103 is executed; if the node is not occupied (S(j)=0), the system jumps to step S105;

[0081] S103: Determine whether the discharge waiting time of the electric vehicle user at the load node in the commercial area is less than a set threshold τ, if so, execute step S104;

[0082] S105: Determine whether the distance from the electric vehicle user to the load node in the commercial area is less than a set threshold value θ. If so, execute step S105:

[0083] S106: Based on whether the difference between the dispatching potential of the electric vehicle user at the commercial area load node and the dispatching demand of the commercial area load node is less than a set threshold δ, if so, the commercial area load node is allocated to the electric vehicle user and the traversal is stopped.

[0084] Preferably, the dispatching potential of the electric vehicle users at the load nodes in the commercial area includes:

[0085] R i,j =min(C j,dis ,η×SOC i ×P i )

[0086] Among them, R i,j represents the dispatch potential of electric vehicle users at load node j in the commercial area, C j,dis represents the maximum discharge capacity of load node j in the commercial area; η is the discharge efficiency; SOC i represents the remaining battery capacity of electric vehicle user i; P i is the maximum discharge power of electric vehicle user i.

[0087] Preferably, the dispatching requirements of the commercial area load nodes include:

[0088]

[0089] C(t)=L i (t)-L tg

[0090] Among them, C j represents the dispatching demand of load node j in the commercial area, represents the maximum load capacity of load node j in the commercial area; m represents the total number of load nodes in the commercial area; C(t) represents the discharge demand of the commercial area power grid; ω j represents the adjustment coefficient of load node j in the commercial area; L u (t) represents the real-time power load in the commercial area; L tg It represents the target control power of the commercial area power grid.

[0091] Preferably, the calculation of the discharge power and discharge time of the electric vehicle user at the load node in the commercial area includes:

[0092] Divide a day into 24 time periods by hour, and construct an objective function with the optimization goal of smoothing the fluctuation of the power load curve in the commercial area:

[0093]

[0094] Where f represents the objective function, m represents the total number of load nodes in the commercial area, n represents the number of electric vehicle users discharging in the commercial area, and P Lt It is expressed as the average power load of the commercial area during period t; P av It represents the average power load of the commercial area within 24 hours a day; P it represents the discharge power of electric vehicle user i in time period t;

[0095] The discharge power P of electric vehicle users itThe particle swarm optimization algorithm is used to solve the objective function as the decision variable to obtain the optimal discharge power and discharge time of the electric vehicle user. The discharge time of the electric vehicle user is calculated by statistically analyzing the discharge power P of the electric vehicle user. it The number of time periods >0 is calculated.

[0096] In this embodiment, by dividing a day into 24 time periods, the system uses the particle swarm optimization algorithm to optimize the discharge power and time of electric vehicle users, construct an objective function to stabilize the power load curve and reduce power fluctuations. The particle swarm algorithm can efficiently and accurately solve the optimal discharge strategy, while taking into account the constraints of power and battery capacity, ensuring the safety of user batteries and the reasonable distribution of grid loads. This method not only improves the computing efficiency of the system, but also improves the operational stability and energy efficiency of the grid.

[0097] In this embodiment, using the particle swarm optimization algorithm to solve the objective function includes:

[0098] The dimension of the particle is set to n*24, and the position of particle I is expressed as:

[0099] P1=[P 1,1 ,P 1,2 ,…,P 1,24 ,P 2,1 ,…,P 2,24 ,…,P i,j ,…,P n,24 ]

[0100] The position of particle i in the D-dimensional solution space can be expressed as a vector x i =[x i1 ,x i2 ,…,x iD ], with a velocity of v i =[v i1 ,v i2 ,v i3 ,..,v iD ], the particle updates its velocity and position according to the following formula.

[0101]

[0102] Where: k represents the number of iterations; represents the velocity of the D-dimensional vector of particle i in the kth iteration; is the position vector corresponding to the current optimal position of particle i; is the position vector of the optimal position in the entire group. ω is the inertia weight, which is the factor affecting the particle's previous flight speed on this flight speed; c1 and c2 are learning factors; rand1 and rand2 are random numbers between [0,1]. The inertia weight coefficient search process is:

[0103] ω=ω max -k(ω max -ω min ) / k max

[0104] The velocity of each dimension of the particle is controlled within [-V Dmax ,V Dmax ]between.

[0105] Maximum number of iterations k max : It terminates the algorithm and is set to 1000.

[0106] PSO algorithm flow with constraints;

[0107] ① Initialize the particle swarm and determine the basic parameter values ​​of the particles;

[0108] The particle speed update is achieved by considering the current speed, individual optimal position and global optimal position. Specifically, the speed of each particle update is and location According to the above formula, ensure that each particle complies with the following constraints in terms of speed and position.

[0109] 2) Power Constraints

[0110] The maximum charging current is half of the rated current, and the maximum discharging current is twice the rated current. Next, considering the line power capacity constraint, the charging and discharging power does not exceed 20kW.

[0111] P itmax =min(15,V it ×2I iN )

[0112]

[0113] Where: P itmax is the maximum discharge power of electric vehicle user i at time t; P itmin represents the maximum discharge power of electric vehicle user i at time t; I iN is the rated current of the battery of the electric vehicle user i; V it It is the actual charging voltage value of the battery of the electric vehicle user i.

[0114] 3) Available capacity constraints

[0115] The minimum remaining battery capacity of electric vehicle users shall not be less than 20% of the total battery capacity.

[0116] SOC i ≥0.2

[0117] 4) User sets the minimum SOC when leaving

[0118] SOC i ≥0.3

[0119] Where: SOC i The remaining battery capacity for electric vehicle users.

[0120] ③ Calculate the fitness function value of the particle swarm and track the optimal position of individuals and the optimal position of the group in the particle swarm;

[0121] ④Update the velocity and position of particles;

[0122] ⑤ Check whether the particle speed and position exceed the limit value according to the constraint conditions. If they exceed the limit range, limit them to the limit value and repeat step 2;

[0123] ⑥ Calculate the fitness function value of the particle swarm, update and record the optimal position of the individual in the particle swarm as the optimal position of the group;

[0124] ⑦ Determine whether the maximum number of iterations has been reached. If so, stop the calculation; otherwise, return to step 4.

[0125] See also Figure 3 This figure shows the power load curve of the mall area under different load conditions through Python simulation, with special emphasis on the load changes during peak hours. The figure compares the mall's power load curve in the future period T, the load curve after the electric vehicle is discharged, and the ideal load target set by the system, and analyzes their changing trends within 24 hours.

[0126] The yellow curve represents the mall's electricity load curve in the future period T, reflecting the fluctuation of the mall's electricity demand when no electric vehicle discharge adjustment is performed; the purple curve represents the load curve after the electric vehicle discharge operation, showing the effectiveness of discharge in smoothing peak loads; the green dotted line represents the system's ideal load target, that is, the balanced load state achieved by dispatching resources such as electric vehicles; the red cross ("X" mark) represents the peak point of the load curve; the gray shaded area represents the peak period of power load, reflecting the system's load management needs during these critical time periods.

[0127] As can be seen from the figure, the power load of the shopping mall has a significant peak during peak hours. Through the discharge operation of electric vehicles, the load peak has been significantly reduced, making the actual load closer to the ideal load. This shows that electric vehicles based on V2G technology can provide effective load regulation support for the power grid, reduce peak load pressure, optimize power grid operation, thereby helping to balance power supply and demand and improve the stability of the power grid.

[0128] In summary, the present invention collects power data of the commercial area in real time through the load monitoring terminal, providing a rich and accurate data basis for the flow analysis module. The flow analysis module uses historical power data to predict the power load of the commercial area in the future time period T in real time, significantly improving the accuracy and timeliness of load prediction; the data acquisition module calculates the user's mileage anxiety state by obtaining the facial image data of the electric vehicle user, which helps to understand the charging needs and psychological state of the electric vehicle user and provide an important reference for the subsequent guidance strategy; the behavior analysis module is used to calculate the probability of the electric vehicle user being guided to the commercial area for discharge; and in response to the electric vehicle user's reply information to the charging and discharging request, the electric vehicle user is guided to the corresponding commercial area load node when the electric vehicle user arrives at the commercial area; the system intelligently guides the electric vehicle user to the commercial area load node for discharge; the discharge regulation module calculates the discharge power and discharge time of the electric vehicle user at the commercial area load node; the load monitoring terminal, the flow analysis module, the data acquisition module, the behavior analysis module, the behavior guidance module and the discharge regulation module together constitute a complete shopping mall discharge system based on V2G technology. The system can collect and analyze electricity data in real time, predict future electricity load conditions, and provide intelligent guidance based on the mileage anxiety status and behavioral characteristics of electric vehicle users. It achieves precise management of electricity loads in commercial areas and effective use of electric vehicle energy storage resources, reduces the management difficulty and operating costs of the power grid, and ensures the stable operation of the power grid.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A shopping mall discharge system based on V2G technology, characterized in that: include: Load monitoring terminal, installed in the power distribution room of the commercial area, is used to collect power data of the commercial area in real time; The flow analysis module is used to predict the power load of the commercial area in the future time period T in real time based on the historical power data of the commercial area; A data acquisition module, used to obtain facial image data of electric vehicle users to calculate the range anxiety status of electric vehicle users; A behavior analysis module, used to calculate the probability of an electric vehicle user being guided according to the electric vehicle user's range anxiety state; The behavior guidance module sends a discharge request to the electric vehicle user according to the power load of the commercial area in the future time period T when the probability of the electric vehicle user being guided is greater than a set threshold a; and in response to the reply information of the electric vehicle user to the charge and discharge request, guides the electric vehicle user to the corresponding load node in the commercial area when the electric vehicle user arrives at the commercial area; The discharge regulation module is used to calculate the discharge power and discharge time of electric vehicle users at the load nodes in the commercial area according to the power load conditions in the commercial area in the future period T.

2. The V2G technology-based shopping mall discharge system according to claim 1 is characterized in that: The predicted electricity load of the commercial area in the future time period T includes: X t =[P(t-n),P(t-n+1),…,P(t-1),P(t)] L(t)=[P(t+1),P(t+2),…,P(t+f)]=LSTM(X t ) Among them, t represents the current time, P(tn) represents the power data of the commercial area at time (tn); n represents the number of samples of historical power data; LSTM represents long short-term memory network; P(t+k) represents the power load of the commercial area at time t+k in the future, k = {1, 2, ..T}; L(t) represents the power load of the commercial area in the future time period T.

3. The V2G technology-based shopping mall discharge system according to claim 1 is characterized in that: The calculation of the range anxiety state of the electric vehicle user includes: When the distance between the electric vehicle user and the commercial area is less than the set threshold d, the facial image of the electric vehicle user is collected, and the range anxiety state of the electric vehicle user is calculated in real time; The calculation of the range anxiety state of the electric vehicle user includes: The facial feature vector of the electric car user is extracted using the facial feature point detection library Dlib based on the facial image of the electric car user; According to the facial feature vectors of electric vehicle users and combined with the FACS coding system, a range anxiety state determination model for electric vehicle users is constructed, and the range anxiety state of electric vehicle users is calculated based on the constructed range anxiety state determination model.

4. The V2G technology-based shopping mall discharge system according to claim 1 is characterized in that: The probability that the electric vehicle user is guided includes: AND ac =ε×d T ab =1-A anxiety Where c represents the probability of an electric vehicle user being guided, exp() represents the natural exponential function; α and β are adjustment coefficients; a0∈(0,1) means that the average power consumption of an electric vehicle user per trip is not higher than a0 times the battery capacity; B cap represents the battery capacity; ε is the average energy consumption of electric vehicle users; d represents the travel distance from the current location of the electric vehicle user to the commercial area; S SOC Indicates the remaining power of the electric vehicle user; S th represents the minimum safe power of electric vehicle users; θ1 and θ2 represent adjustment coefficients, and g represents the mileage anxiety state of electric vehicle users.

5. The V2G technology-based shopping mall discharge system according to claim 1 is characterized in that: The sending of a discharge request to an electric vehicle user according to the power load situation of the commercial area in the future time period T includes: Calculate the peak load index of the commercial area's electricity load according to the electricity load situation of the commercial area in the future time period T; Among them, PLI represents the peak load index of the commercial area power load, t0 represents the time point when the detection starts, t0∈[0,T]; P(t0+k) represents the power load at time t0+k; N is the total number of moments in the time period; Calculate the time when the commercial area electricity load enters the peak period based on the peak load index of the commercial area electricity load; t peak =t0(PLI>P th ) Among them, t peak is the time point when the load peak period begins; P th is the preset peak load threshold; The time to send the discharge request is calculated based on the time when the commercial area's electricity load enters the peak period: Among them, t m The time to send a discharge request to the electric vehicle user; t a0 is a fixed value for the time to arrive at the commercial area in advance; d i represents the travel distance of electric vehicle user i from the commercial area, v i is the average driving speed of electric vehicle user i; At the time t at which the discharge request is sent m Send a discharge request to the electric vehicle user.

6. The V2G technology-based shopping mall discharge system according to claim 1 is characterized in that: The step of guiding the electric vehicle user to the corresponding commercial area load node when the electric vehicle user arrives at the commercial area includes: S101: When the electric vehicle user arrives at the commercial area, the distance between the electric vehicle user and each load node in the commercial area and the discharge waiting time of the electric vehicle user at each load node in the commercial area are calculated; S102: traverse each commercial area load node to check whether the commercial area load node is occupied by other electric vehicle users. If so, execute step S103; otherwise, execute step S105; S103: Determine whether the discharge waiting time of the electric vehicle user at the load node in the commercial area is less than a set threshold τ, if so, execute step S104; S104: Determine whether the distance from the electric vehicle user to the load node in the commercial area is less than a set threshold value θ. If so, execute step S105: S105: Determine whether the difference between the dispatching potential of the electric vehicle user at the commercial area load node and the dispatching demand of the commercial area load node is less than a set threshold δ. If so, allocate the commercial area load node to the electric vehicle user and stop traversal.

7. The V2G technology-based shopping mall discharge system according to claim 6 is characterized in that: The dispatch potential of electric vehicle users at commercial area load nodes includes: R i，j =min(C j,dis ,η×SOC i ×P i ) Among them, R i，j represents the dispatch potential of electric vehicle users at load node j in the commercial area, C j，dis represents the maximum discharge capacity of load node j in the commercial area; η is the discharge efficiency; SOC i represents the remaining battery capacity of electric vehicle user i; P i is the maximum discharge power of electric vehicle user i.

8. The V2G technology-based shopping mall discharge system according to claim 6 is characterized in that: The dispatching requirements of the commercial area load nodes include: C(t)=L u (t)-L tg Where Cj represents the dispatching demand of load node j in the commercial area, represents the maximum load capacity of load node j in the commercial area; m represents the total number of load nodes in the commercial area; C(t) represents the discharge demand of the commercial area power grid; ω j represents the adjustment coefficient of load node j in the commercial area; L u (t) represents the real-time power load in the commercial area; L tg It represents the target control power of the commercial area power grid.

9. The V2G technology-based shopping mall discharge system according to claim 1, characterized in that: The calculation of the discharge power and discharge time of the electric vehicle user at the load node in the commercial area includes: Divide a day into 24 time periods by hour, and construct an objective function with the optimization goal of smoothing the fluctuation of the power load curve in the commercial area: Where f represents the objective function, m represents the total number of load nodes in the commercial area, n represents the number of electric vehicle users discharging in the commercial area, and P Lt It is expressed as the average power load of the commercial area during period t; P av It represents the average power load of the commercial area within 24 hours a day; P it represents the discharge power of electric vehicle user i in time period t; The discharge power P of electric vehicle users it The particle swarm optimization algorithm is used to solve the objective function as the decision variable to obtain the optimal discharge power and discharge time of the electric vehicle user. The discharge time of the electric vehicle user is calculated by statistically analyzing the discharge power P of the electric vehicle user. it The number of time periods >0 is calculated.

Images