Short-term forecasting method for electric vehicle charging load based on vehicle-grid interaction strategy optimization

Abstract

A short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization includes: using a data-driven method to obtain a short-term prediction result of the charging load; using a model-driven method to expand the dimension of the prediction result to obtain a short-term prediction result of a multi-dimensional charging load; using a first preset rule to optimize the short-term prediction result of the multi-dimensional charging load to obtain the final short-term prediction result of the electric vehicle charging load. The present invention further expands the dimensional information of the load prediction output, and can obtain information on the number of electric vehicles connected at each time point, the charging demand time, and the charging start time of each electric vehicle. This method is superior in terms of prediction accuracy and the dimensionality of the load prediction result output information.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging optimization, and in particular to a method for short-term prediction of electric vehicle charging load based on vehicle-grid interaction strategy optimization. Background Art

[0002] The charging load generated by electric vehicles has strong uncertainty in spatial and temporal distribution. In order to eliminate the problems of local overload and power quality deterioration caused by the randomness and volatility of the power supply and distribution network, power grid companies need to predict the load conditions of electric vehicle charging in the next few hours in order to formulate reasonable incentives for the demand response of electric vehicle charging load. The existing electric vehicle charging load mainly includes two types of data-driven prediction methods and model-driven prediction methods. Model-driven electric vehicle charging load prediction methods attempt to establish the connection between charging load and factors such as travel mode, road network traffic conditions and range anxiety, and make load forecasts based on this. These prediction methods provide a good reference for short-term prediction of charging load, but their output is a classic sequence of load forecast values, which provides limited information and cannot meet the needs of vehicle-grid interaction. Summary of the invention

[0003] In view of the above problems, the present invention is proposed to provide a short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization, which overcomes the above problems or at least partially solves the above problems.

[0004] In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention discloses a method for short-term prediction of electric vehicle charging load based on vehicle-grid interaction strategy optimization, comprising:

[0006] S100. Using a data-driven method to obtain a short-term prediction result of the charging load;

[0007] S200. Expand the prediction result dimension by using a model-driven method to obtain a short-term prediction result of multi-dimensional charging load;

[0008] S300. Optimize the short-term prediction result of the multi-dimensional charging load using a first preset rule to obtain a final short-term prediction result of the electric vehicle charging load.

[0009] Furthermore, in S100, a data-driven method is used to obtain a short-term prediction result of the charging load, and the specific method includes:

[0010] Use a data-driven forecasting method to obtain the initial short-term forecast sequence P da ,in, The first discrete moment, the tth discrete moment and the eth discrete moment in a day to be predicted respectively represent the electric vehicle charging load power corresponding to the first discrete moment, the tth discrete moment and the eth discrete moment in a day to be predicted, and then the autoregressive integrated moving average model is used to calculate the initial short-term prediction sequence P da To make a prediction, the autoregressive integrated moving average model is expressed as follows:

[0011]

[0012] where α 1 , α 2 , ....., αe represents the load forecast weighting coefficient, β 1 , β 2 ,....., β e Represents the load forecast error weighting coefficient.

[0013] Furthermore, in S200, a model-driven method is used to expand the dimension of the prediction result to obtain a short-term prediction result of multi-dimensional charging load; the specific method includes:

[0014] Get the maximum value max(P da ), the maximum value max(P da ) The charging load distribution according to low, medium and high time points is as follows: The time t corresponding to the value of the charging load at low, medium and high time points is recorded as the time of low, medium and high charging load; the time t corresponding to the value of the charging load at low, medium and high time points is expressed as:

[0015]

[0016] where t l ,t m and t h Indicates the charging times corresponding to low, medium, and high power charging loads.

[0017] Furthermore, after obtaining the time t corresponding to the value of the charging load, the driving distance of the electric vehicle is continuously obtained. The driving distance of the electric vehicle approximately obeys the log-normal distribution. The driving distance function of the electric vehicle f s (s) means as follows:

[0018]

[0019] The probability density of the driving distance of electric vehicles is represented by fs(s); the mathematical expectation and standard deviation are represented by σ d and μ dAccording to the car's driving distance data, σ is determined by the maximum likelihood estimation method. d and μ d The Monte Carlo simulation method is used to combine the electric vehicle driving distance function f s (s), generating EV mileages of different driving distances.

[0020] Furthermore, in S200, a model-driven method is used to expand the dimension of the prediction result to obtain a short-term prediction result of the multi-dimensional charging load; the specific method also includes: after obtaining the driving distance of the electric vehicle, the charging duration Tc(i) of each electric vehicle is calculated, and the charging duration Tc(i) is calculated as follows:

[0021]

[0022] Where T c (i) represents the charging duration of the i-th one; s (i) represents the driving distance of the i-th electric car generated in, w 1 Indicates the power consumption of electric vehicles per 100 kilometers; P c represents the charging power of electric vehicles; η represents the charging efficiency; according to the time t corresponding to the values ​​of low, medium and high charging loads, the number of electric vehicles connected to the area at each time k is determined 0 , the number of electric vehicles k 0 The expression is:

[0023]

[0024] where kl, km and kh represent the number of connected EVs at low, medium and high charging moments, and tl, tm and th represent the charging times corresponding to low, medium and high power charging loads.

[0025] Furthermore, if k 0 If an electric vehicle is connected to the area at time t, the charging load of the area can be expressed as:

[0026]

[0027] Where P m1 (t) represents the regional predicted charging load; a(i,t) represents the charging status of the i-th electric vehicle at time t, with a value of 1 representing the charging state and 0 representing the charging idle state; the expression of a(i,t) is:

[0028]

[0029] Where Tc,s(i) represents the charging start time of the i-th electric vehicle, Tc (i) represents the charging duration of the i-th one.

[0030] Further, when obtaining the regional predicted charging load P m1 (t), the mean absolute percentage error of the short-term forecast sequence Pda and the regional all-day charging load sequence Pm1 are calculated, and the values ​​of kl, km and kh are adjusted to minimize P da and P m1 (t), repeat step S200 to obtain Pm1 with the minimum mean absolute percentage error.

[0031] Further, in S300, the short-term prediction result of the multi-dimensional charging load is optimized by using the first preset rule, and the specific method includes: setting the number of electric vehicles connected to the area at each moment in S200 to the number of connected vehicles at each moment bt, correcting the predicted load in S200, and replacing unreasonable setting parameter values; based on the regional charging load Pm1 generated in, bt measures the number of electric vehicles connected to the area at time t to correct the load between Pda and the load Pm1 generated in S200, and obtain b t ; The correction area charging load prediction result Pm2(t) under electric vehicles, the expression of Pm2(t) is:

[0032]

[0033] Among them, P m2 (t) represents b t Correction of regional charging load forecast results under electric vehicles, adjusting b at each time t t value, so that at each moment t the load P m1 (t) and load P m2 The sum of (t) is approximately equal to P da .

[0034] Furthermore, according to the corrected load Pm2(t) of the generated all-day load sequence, the final short-term prediction result of the electric vehicle charging load Pm(t) is obtained. The formula of Pm(t) is:

[0035] p m (t) = P m1 (t)+p m2 (t)

[0036] Here, Pm(t) represents the final regional charging load at the corrected time t predicted based on the driving pattern.

[0037] In a second aspect, an embodiment of the present invention discloses an electronic device, including:

[0038] one or more processors;

[0039] A memory for storing one or more programs;

[0040] When the one or more programs are executed by the one or more processors, the one or more processors implement the electric vehicle charging load short-term prediction method.

[0041] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0042] The present invention discloses a short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization, including: S100. Using a data-driven method to obtain a short-term prediction result of the charging load; S200. Using a model-driven method to expand the dimension of the prediction result to obtain a short-term prediction result of a multi-dimensional charging load; S300. Using a first preset rule to optimize the short-term prediction result of the multi-dimensional charging load to obtain the final short-term prediction result of the electric vehicle charging load. The present invention further expands the dimensional information of the load prediction output, and can obtain information on the number of electric vehicles connected at each time point, the charging demand time, and the charging start time of each electric vehicle. This method is superior in terms of prediction accuracy and the dimensionality of the load prediction result output information.

[0043] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 This is a flow chart of a method for short-term prediction of electric vehicle charging load based on vehicle-grid interaction strategy optimization in Example 1 of the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of an electronic device in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0047] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0048] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization.

[0049] Example 1

[0050] The present invention discloses a short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization, which is characterized by comprising:

[0051] S100. A data-driven approach is used to obtain short-term prediction results of charging load, where charging load refers to the power load that electric vehicles may consume when they are charged by charging facilities. This concept is of great significance in the planning of electric vehicle charging facilities, stable operation of power grids, and energy management.

[0052] In S100 of this embodiment, a data-driven method is used to obtain a short-term prediction result of the charging load. The specific method includes:

[0053] Use a data-driven forecasting method to obtain the initial short-term forecast sequence P da ,in, The first discrete moment, the tth discrete moment and the eth discrete moment in a day to be predicted respectively represent the electric vehicle charging load power corresponding to the first discrete moment, the tth discrete moment and the eth discrete moment in a day to be predicted, and then the autoregressive integrated moving average model is used to calculate the initial short-term prediction sequence P da To make a prediction, the autoregressive integrated moving average model is expressed as follows:

[0054]

[0055] where α 1 , α 2 , ....., αe represents the load forecast weighting coefficient, β 1 , β 2 ,....., β e Represents the load forecast error weighting coefficient.

[0056] S200. Expand the prediction result dimension by using a model-driven method to obtain a short-term prediction result of multi-dimensional charging load;

[0057] In S200 of this embodiment, a model-driven method is used to expand the dimension of the prediction result to obtain a short-term prediction result of multi-dimensional charging load; the specific method includes:

[0058] Get the maximum value max(P da ), the maximum value max(P da ) The charging load distribution according to low, medium and high time points is as follows: The time t corresponding to the value of the charging load at low, medium and high time points is recorded as the time of low, medium and high charging load; the time t corresponding to the value of the charging load at low, medium and high time points is expressed as:

[0059]

[0060] where t l ,t m and t h Indicates the charging times corresponding to low, medium, and high power charging loads.

[0061] After obtaining the time t corresponding to the value of the charging load, the driving distance of the electric vehicle is continued to be obtained. The driving distance of the electric vehicle approximately obeys the log-normal distribution. The driving distance function of the electric vehicle f s (s) means as follows:

[0062]

[0063] The probability density of the driving distance of electric vehicles is represented by fs(s); the mathematical expectation and standard deviation are represented by σ d and μ d According to the car's driving distance data, σ is determined by the maximum likelihood estimation method. d and μ d The Monte Carlo simulation method is used to combine the electric vehicle driving distance function f s (s), generating EV mileages of different driving distances.

[0064] In this embodiment, after the driving distance of the electric vehicle is obtained, the charging duration Tc(i) of each electric vehicle is calculated. The calculation formula of the charging duration Tc(i) is:

[0065]

[0066] Where T c (i) represents the charging duration of the i-th one; s (i) represents the driving distance of the i-th electric car generated in, w 1 Indicates the power consumption of electric vehicles per 100 kilometers; P c represents the charging power of electric vehicles; η represents the charging efficiency; according to the time t corresponding to the values ​​of low, medium and high charging loads, the number of electric vehicles connected to the area at each time k is determined 0 , the number of electric vehicles k 0 The expression is:

[0067]

[0068] where kl, km and kh represent the number of connected EVs at low, medium and high charging moments, and tl, tm and th represent the charging times corresponding to low, medium and high power charging loads.

[0069] If k 0 If an electric vehicle is connected to the area at time t, the charging load of the area can be expressed as:

[0070]

[0071] Where P m1 (t) represents the regional predicted charging load; a(i,t) represents the charging status of the i-th electric vehicle at time t, with a value of 1 representing the charging state and 0 representing the charging idle state; the expression of a(i,t) is:

[0072]

[0073] Where Tc,s(i) represents the charging start time of the i-th electric vehicle, T c (i) represents the charging duration of the i-th one.

[0074] When the regional predicted charging load P is obtained m1 (t), the mean absolute percentage error of the short-term forecast sequence Pda and the regional all-day charging load sequence Pm1 are calculated, and the values ​​of kl, km and kh are adjusted to minimize P da and P m1 (t), repeat step S200 to obtain Pm1 with the minimum mean absolute percentage error.

[0075] S300. Optimize the short-term prediction result of the multi-dimensional charging load using a first preset rule to obtain a final short-term prediction result of the electric vehicle charging load.

[0076] In S300, the first preset rule is used to optimize the short-term prediction result of the multi-dimensional charging load. The specific method includes: setting the number of electric vehicles connected to the area at each moment in S200 to the number of connected vehicles at each moment bt, correcting the predicted load in S200, and replacing unreasonable setting parameter values; based on the regional charging load Pm1 generated in, bt is connected to the area at time t to correct the load between Pda and the load Pm1 generated in S200, and obtaining b t ; The correction area charging load prediction result Pm2(t) under electric vehicles, the expression of Pm2(t) is:

[0077]

[0078] Among them, P m2 (t) represents b t Correction of regional charging load forecast results under electric vehicles, adjusting b at each time t t value, so that at each moment t the load P m1 (t) and load P m2 The sum of (t) is approximately equal to P da .

[0079] Specifically, therefore, the generated all-day load sequence Pm2 is the correction load.

[0080] p m (t) = p m1 (t)+p m2 (t)

[0081] Where Pm(t) represents the final regional charging load at the corrected time t based on the driving pattern prediction. At time t, the number of electric vehicles connected to the area is k0+bt. Since the load forecast correction based on driving characteristics is a load mechanism derived from the charging of electric vehicles, it is a model-driven method. The model-driven method corrects the short-term load forecast results according to the degree of use of the charging piles and changes the unreasonable values. Therefore, the integration of model-driven and data-driven methods can obtain more accurate load forecast results. The combination of model-driven and data-driven methods can also obtain the number of electric vehicles connected at each moment and the charging demand time and start charging time of each electric vehicle.

[0082] This embodiment also verifies this method, and selects the historical charging load data of W City from May to July 2023 for simulation verification. The historical data of the first 79 days are divided into a training set for training the model, and the data of the last 13 days are divided into a test set. The method in this section sets the learning rate to 0.01 based on historical experience, and obtains the prediction results after 150 iterations of the model. Constructed load forecasting ARIMA prediction model. Short-term load forecasting results based on charging pile utilization in W City from July 19 to 21. Except for the large difference between the charging load peak prediction curve and the actual load curve on the 20th and 21st, the prediction results at other times are not much different from the actual load, which shows that the data-driven short-term load forecasting of charging load based on charging load is more effective.

[0083] Based on the data-driven short-term prediction of charging load, a prediction correction method based on tripping characteristics is proposed. Ne takes the value of 300; kl, km and kh take the values ​​of 2, 5 and 8 respectively; the number of operations Num takes the value of 100; and the values ​​of are 3.20 and 0.88 respectively; the electric vehicle uses the parameters of BYD e6, the wl consumption of the electric vehicle is 19.5kWh / 100km; the power of the charging electric vehicle Pc is 9.6kW; the charging efficiency is 0.9.

[0084] The load in the first stage of the prediction results from 19 to 20 is somewhat different from Pda. The final prediction correction result Pm based on the EV driving characteristics is the sum of the main load Pm1 and the correction load Pm2, the main load is corrected by the correction of the correction load, and Pm almost completely overlaps with Pda. Therefore, the prediction results about the EV driving characteristics are corrected for Pda in some time periods, and the unreasonable load value in Pda is changed.

[0085] Table 1 shows the calculation results of the prediction evaluation index of the final prediction results of W City from July 19 to 21. The traditional data-driven prediction method is based on LSTM. The prediction model of our proposed method is completely

[0086] The structure and parameter selection are consistent. As shown in Table 1, the average MAPE of the three-day forecast results of the proposed method is 14.7%, while the MAPE of the traditional method is 17.2%. The prediction accuracy of the proposed method is nearly 3 percentage points higher than that of the load data format conversion method. This shows the effectiveness of the proposed method. At the same time, the RMSE and MAE of the proposed method are much smaller than those of the traditional iterative forecasting method.

[0087] Table 1 Comparison of different charging load prediction methods in W City from July 19 to 21

[0088]

[0089] This embodiment discloses a short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization, including: S100. Using a data-driven method to obtain a short-term prediction result of the charging load; S200. Using a model-driven method to expand the dimension of the prediction result to obtain a short-term prediction result of a multi-dimensional charging load; S300. Using a first preset rule to optimize the short-term prediction result of the multi-dimensional charging load to obtain the final short-term prediction result of the electric vehicle charging load. The present invention further expands the dimensional information of the load prediction output, and can obtain information on the number of electric vehicles connected at each time point, the charging demand time, and the charging start time of each electric vehicle. This method is superior in terms of prediction accuracy and the dimensionality of the load prediction result output information.

[0090] Example 2

[0091] Based on the same inventive concept, an embodiment of the present disclosure also provides an electronic device. Figure 2 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Figure 2 As shown, an embodiment of the present disclosure provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any optimization method in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, and are configured to implement information interaction between the processor and the memory.

[0092] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus), etc.

[0093] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0094] In some embodiments, the one or more processors 101 include a field programmable gate array.

[0095] According to an embodiment of the present disclosure, a computer-readable medium is further provided, wherein a computer program is stored on the computer-readable medium, wherein when the program is executed by a processor, the steps in any optimization method in the above-mentioned embodiment are implemented.

[0096] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0097] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0098] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0099] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0100] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0101] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization, characterized in that: include: S100. Using a data-driven method to obtain a short-term prediction result of the charging load; In S100, a data-driven method is used to obtain a short-term prediction result of the charging load. The specific method includes: Use a data-driven forecasting method to obtain the initial short-term forecast sequence P da ,in, The first discrete moment, the tth discrete moment and the eth discrete moment in a day to be predicted respectively represent the electric vehicle charging load power corresponding to the first discrete moment, the tth discrete moment and the eth discrete moment in a day to be predicted, and then the autoregressive integrated moving average model is used to calculate the initial short-term prediction sequence P da To make a prediction, the autoregressive integrated moving average model is expressed as follows: Among them, α1, α2, ....., αe represent the load forecast weighting coefficients, β1, β2, ....., β e Indicates the load forecast error weighting coefficient, e1, e2, e3.....e e represents the error term at the e-th discrete moment; S200. Expand the prediction result dimension using a model-driven method to obtain a short-term prediction result of a multi-dimensional charging load; In S200, expand the prediction result dimension using a model-driven method to obtain a short-term prediction result of a multi-dimensional charging load; the specific method includes: Get the maximum value max(P da ), the maximum value max(P da ) The charging load distribution according to low, medium and high time points is as follows: The time t corresponding to the value of the charging load at the low, medium and high time points is recorded as the time of low, medium and high charging load; the expression of the time t corresponding to the value of the charging load at the low, medium and high time points is: where t l ,t m and t h Indicates the charging time corresponding to low-power, medium-power, and high-power charging loads; S300. The short-term prediction result of the multi-dimensional charging load is optimized by using the first preset rule to obtain the final short-term prediction result of the electric vehicle charging load; In S300, the short-term prediction result of the multi-dimensional charging load is optimized by using the first preset rule, and the specific method includes: setting the number of electric vehicle charging connected at each moment in the area in S200 to the number of connected vehicles at each moment b t , correct the predicted load in S200 and replace the unreasonable setting parameter values; based on the regional charging load Pm1 generated in S200, b t An electric vehicle is connected in the region at time t to correct the load between Pda and the load Pm1 generated in S200, and obtain b t ; The correction area charging load prediction result Pm2(t) under electric vehicles, the expression of Pm2(t) is: Among them, P m2 (t) represents b t Correction of regional charging load forecast results under electric vehicles, adjusting b at each time t t value, so that at each moment t the load P m1 (t) and load P m2 The sum of (t) is approximately equal to P da ;P c is the charging power of electric vehicles, a(i,t) represents the charging state of the i-th electric vehicle at time t; According to the corrected load Pm2(t) of the generated all-day load sequence, the final short-term forecast result of electric vehicle charging load Pm(t) is obtained. The formula of Pm(t) is: p m (t)=p m1 (t)+p m2 (t) Here, Pm(t) represents the final regional charging load at the corrected time t predicted based on the driving pattern.

2. A short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization as claimed in claim 1, characterized in that: After obtaining the time t corresponding to the value of the charging load, the driving distance of the electric vehicle is continued to be obtained. The driving distance of the electric vehicle approximately obeys the log-normal distribution. The driving distance function of the electric vehicle f s (s) is represented as follows: The probability density of the electric vehicle's driving distance s is represented by fs(s); the mathematical expectation and standard deviation are represented by σ d and μ d According to the car's driving distance data, σ is determined by the maximum likelihood estimation method. d and μ d The Monte Carlo simulation method is used to combine the electric vehicle driving distance function f s (s), generating EV mileages of different driving distances.

3. The short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization according to claim 1 is characterized in that: In S200, a model-driven method is used to expand the dimension of the prediction result to obtain a short-term prediction result of the multi-dimensional charging load; the specific method also includes: after obtaining the driving distance of the electric vehicle, the charging duration Tc(i) of each electric vehicle is calculated, and the charging duration Tc(i) is calculated as follows: Where T c (i) represents the charging duration of the i-th one; s (i) represents the driving distance of the i-th electric vehicle generated in, w1 represents the power consumption of the electric vehicle per 100 kilometers; P c represents the charging power of electric vehicles; η represents the charging efficiency; according to the time t corresponding to the values ​​of low, medium and high charging loads, the number of electric vehicles connected to the area at each time k is determined 0 , the number of electric vehicles k 0 The expression is: where kl, km and kh represent the number of connected EVs at low, medium and high charging moments, and tl, tm and th represent the charging times corresponding to low, medium and high power charging loads.

4. A short-term prediction method for electric vehicle charging load based on vehicle-grid interaction strategy optimization as claimed in claim 3, characterized in that: If k0 electric vehicles are connected in the area at time t, the charging load in the area can be expressed as: Where P m1 (t) represents the regional predicted charging load; a(i,t) represents the charging status of the i-th electric vehicle at time t, with a value of 1 representing the charging state and 0 representing the charging idle state; the expression of a(i,t) is: Where Tc,s(i) represents the charging start time of the i-th electric vehicle, T c (i) represents the charging duration of the i-th one.

5. The method for short-term prediction of electric vehicle charging load based on vehicle-grid interaction strategy optimization according to claim 4 is characterized in that: When the regional predicted charging load P is obtained m1 (t), the mean absolute percentage error of the short-term forecast sequence Pda and the regional all-day charging load sequence Pm1 are calculated, and the values ​​of kl, km and kh are adjusted to minimize P da and P m1 (t), repeat step S200 to obtain Pm1 with the minimum mean absolute percentage error.

6. An electronic device comprising: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the charging load short-term prediction method according to any one of claims 1 to 5.

Images