Electric vehicle ordered charging optimization method and system based on user sensitive portrait

By building a user-sensitive portrait model and predicting load rates, and generating a dynamic electricity price plan, the problem of inaccurate matching of electric vehicle charging demand in the existing technology is solved, and orderly charging of electric vehicles and optimization of grid load is achieved.

CN119093389APending Publication Date: 2024-12-06GUANGDONG DIANWANG GONGSI YUNFU POWER SUPPLY BUREAU
View PDF 0 Cites 7 Cited by

Patent Information

Application Number
CN202411201617.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art is difficult to accurately match the charging demand of electric vehicles when optimizing the charging electricity price by using the demand ratio set by user behavior habits, especially due to inaccurate charging load regulation caused by differences in behavior habits on weekdays and weekends.

Method used

By collecting historical distribution network data and time-sharing electricity price data, a user's sensitive image model for charging electricity prices is built, the load rate of the next day is predicted, and a dynamic electricity price plan is generated based on this, and the charging period and electricity price are optimized to guide the charging of electric vehicles. Discharge time and power.

Benefits of technology

It has achieved accurate electricity price optimization for different periods of working days and weekends, improved the orderliness of electric vehicle charging and the matching degree of grid load, reduced dependence on user behavior data, and improved application operability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119093389A_ABST
    Figure CN119093389A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of smart power grids, and provides an electric vehicle ordered charging optimization method and system based on user sensitive portraits. Comprising the following steps: collecting historical power distribution network data and historical time-of-use electricity price data of a target station area; calculating sensitive factors of the user to the charging electricity price in different time periods of which the day types are workdays and weekends, and constructing a sensitive portrait model of the user to the charging electricity price; predicting a predicted load rate at each moment of the next day according to the power distribution network data, and determining a charging optimization time period of the next day based on the predicted load rate; and on the basis of the sensitive portrait model, determining the electricity price regulation and control quantity in each charging optimization period of the next day, generating a charging optimization scheme about the dynamic electricity price in each period of the next day, outputting the charging optimization scheme to a charging pile of a target station area for execution, and guiding the charging and discharging time and active power of the electric vehicle through a price signal to realize ordered charging optimization of the electric vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and more specifically, to a method and system for optimizing orderly charging of electric vehicles based on user sensitive portraits. Background Art

[0002] In recent years, with the vigorous development and popularization of electric vehicles, their application in daily life has become more and more extensive, and the impact of disorderly charging of electric vehicles on the power grid has gradually become significant. Therefore, how to achieve orderly charging of electric vehicles has always been a research point that has attracted much attention.

[0003] At present, there are two ways to regulate charging load: remote control and price guidance. Among them, remote control requires charging pile transformation and construction of control and monitoring platform in actual application, which is not conducive to large-scale promotion and application; and the method of charging price guidance has the following problems. On the one hand, the electricity price regulation strategy model that uses a large amount of user behavior data has the problem of difficulty in collecting relevant parameters in the actual application process. On the other hand, the existing charging electricity price regulation method has weak consideration of the day type factor, and generally predicts the charging load demand based on the analysis of user behavior habits. However, due to the obvious impact of different day types on the behavior habits of charging users, for example, there is a significant difference in the charging behavior habits of users on weekdays and weekends. Therefore, it is difficult to accurately match the user's charging demand when directly using the demand ratio set based on user behavior habits to optimize the charging electricity price and use it for charging load regulation. Summary of the invention

[0004] In order to overcome the defects of the above-mentioned prior art that directly uses the demand ratio set based on user behavior habits to optimize charging electricity prices and is difficult to accurately match user charging demands when used for charging load regulation, the present invention provides an electric vehicle orderly charging optimization method and system based on user sensitive portraits.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] A method for optimizing orderly charging of electric vehicles based on user sensitive portraits comprises the following steps:

[0007] Collect historical distribution network data and historical time-of-use electricity price data of the target area;

[0008] Calculate the user's sensitivity factors to charging electricity prices at different time periods on weekdays and weekends, and build a user's sensitive profile model to charging electricity prices;

[0009] Predicting the predicted load rate at each moment of the next day according to the distribution network data, and determining the charging optimization period of the next day based on the predicted load rate;

[0010] Based on the sensitive portrait model, the amount of electricity price regulation in each charging optimization period of the next day is determined, and a charging optimization plan for the dynamic electricity price in each period of the next day is generated and output to the charging piles in the target area for execution.

[0011] Furthermore, the present invention also proposes an electric vehicle orderly charging optimization system based on user sensitive portraits, and applies the electric vehicle orderly charging optimization method proposed by the present invention. The system includes:

[0012] Data collection module, used to collect historical distribution network data and historical time-of-use electricity price data of the target substation;

[0013] The sensitive portrait module is used to calculate the user's sensitivity factors to charging electricity prices at different time periods on weekdays and weekends;

[0014] The substation load prediction module is used to predict the predicted load rate at each moment of the next day according to the distribution network data, and determine the charging optimization period of the next day based on the predicted load rate;

[0015] The charging optimization module is used to determine the electricity price control amount in each charging optimization period of the next day based on the sensitive portrait model, generate a charging optimization plan for the dynamic electricity price in each period of the next day and output it to the charging piles in the target area, and guide the charging and discharging time and power of electric vehicles through price signals.

[0016] Furthermore, the present invention also proposes a device, including a memory and a processor, wherein the memory stores computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, the processor executes the steps of the electric vehicle orderly charging optimization method as described in the present invention.

[0017] Furthermore, the present invention also proposes a storage medium on which computer-readable instructions are stored, characterized in that when the computer-readable instructions are executed by a processor, the steps of the electric vehicle orderly charging optimization method as described in the present invention are implemented.

[0018] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0019] The present invention constructs a user sensitivity portrait model based on user habits for different time periods on weekdays and weekends, optimizes the electricity price for each charging optimization period of the next day according to the user's sensitivity factors to the charging electricity price in different time periods and predicts the load rate of the area in different time periods of the next day, and outputs the optimized charging electricity price plan to the charging piles in the target area for execution, guides the charging and discharging time and active power of electric vehicles through price signals, and realizes orderly charging optimization of electric vehicles;

[0020] The present invention fully considers the impact of day types on user charging and the user's sensitivity to electricity prices, has high accuracy, and can play a good guiding effect on regional charging users;

[0021] The present invention does not need to collect behavioral data on the charging user side, but only needs to collect transformer load data in the power grid area and low-voltage charging pile meter data to perform strategy calculation, and has strong practical application operability. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The present invention is a flowchart of an electric vehicle orderly charging optimization method based on user sensitivity portraits according to an embodiment of the present invention.

[0023] Figure 2 The present invention is an architectural diagram of an orderly charging optimization system for electric vehicles based on user sensitivity portraits according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0025] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0026] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0027] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] Example 1

[0029] This embodiment proposes an electric vehicle orderly charging optimization method based on user sensitive portraits, such as Figure 1 , which is a flow chart of the orderly charging optimization method for electric vehicles of this embodiment.

[0030] The method for optimizing orderly charging of electric vehicles based on user sensitive portraits proposed in this embodiment includes the following steps:

[0031] S1. Collect historical distribution network data and historical time-of-use electricity price data of the target area;

[0032] S2. Calculate the user's sensitivity factors to charging electricity prices at different time periods on weekdays and weekends, and build a user's sensitive profile model to charging electricity prices;

[0033] S3. Predicting the predicted load rate at each moment of the next day according to the distribution network data, and determining the charging optimization period of the next day based on the predicted load rate;

[0034] S4. Based on the sensitive portrait model, determine the amount of electricity price regulation in each charging optimization period of the next day, generate a charging optimization plan for the dynamic electricity price in each period of the next day and output it to the charging piles in the target area for execution, and guide the charging and discharging time and power of electric vehicles through price signals.

[0035] This embodiment builds a user sensitivity portrait model based on user habits for different time periods on weekdays and weekends, optimizes the electricity price for each charging optimization period of the next day according to the user's sensitivity factor to the charging electricity price in different time periods and the predicted load rate of the substation in different time periods of the next day, and outputs the optimized charging electricity price plan to the charging piles in the target substation for execution. The charging and discharging time and active power of electric vehicles are guided by price signals to achieve orderly charging optimization of electric vehicles.

[0036] This embodiment does not need to collect behavioral data on the charging user side, but only needs to collect transformer load data in the power grid area and low-voltage charging pile meter data to perform strategy calculation, which has strong practical application operability.

[0037] This embodiment fully considers the impact of day types on user charging and the user's sensitivity to electricity prices, has high accuracy, and can play a good guiding effect on regional charging users. In addition, the method does not involve model optimization and solution, the calculation of the control plan is relatively convenient, and the background operation pressure of related software and hardware is low.

[0038] In an optional embodiment, in step S1, the historical distribution network data includes the load active power of the target substation transformer at each time in the past month, the rated capacity of the substation, and the load active power of each user in the target substation at each time in the past month; the historical time-of-use electricity price data includes the specific time periods of peak, flat and valley electricity prices, and the charging electricity prices of electric vehicles in the target substation at each time period.

[0039] Specifically, the collection point interval of the historical distribution network data and the historical time-of-use electricity price data can be optionally set to 15 minutes, and the historical distribution network data and historical time-of-use electricity price data collected in one day include data at 96 moments.

[0040] In an optional embodiment, in step S2, calculating the user's sensitivity factor to the charging electricity price at different time periods of the day type being weekdays and weekends includes the following steps:

[0041] S210. Calculate the proportion of charging load during peak, flat and valley periods in the user's historical records based on the historical distribution network data; the expression is:

[0042]

[0043] Among them, α f,m,j ,α p,m,j ,α g,m,j They represent the proportion of charging load of electric vehicle user m during the peak period, flat period and valley period on the i-th day in history; P EV,m,i,t represents the load active power of electric vehicle user m at time t on the i-th day in history; T f ,T p ,T g They are the time sets for peak period, flat period and valley period respectively;

[0044] S220. According to the historical time-of-use electricity price data, the charging electricity price difference between the peak-to-flat period, the peak-to-valley period, and the flat-to-valley period is obtained; the expression is:

[0045]

[0046] Among them, Δc f-p ,Δc f-g ,Δc p-g Respectively represent the charging price difference between peak and flat periods, peak and valley periods, and flat and valley periods; c f 、c p 、c g are the original electricity prices during peak hours, flat hours, and off-peak hours respectively;

[0047] S230, according to the charging load proportion and the charging electricity price difference, respectively calculate the sensitivity factor of the electric vehicle users to the charging electricity price difference during the peak and valley periods on weekdays and weekends; the expression is:

[0048]

[0049] Among them, D∈{weekday,weekend} represents the day type of weekday or weekend;δ D,f-p,m ,δD,f-g,m ,δ D,p-g,m They represent the sensitivity factors of user m to the charging price difference during peak-to-average, peak-to-valley, and flat-to-valley periods when the day type is D; D Represents a set of historical days with day type D; N D Indicates the total number of days in the historical day set with day type D; δ D,f,m ,δ D,p,m ,δ D,g,m They represent the sensitivity factors of user m to the charging price difference during peak hours, flat hours and valley hours when the type is D; β f ,β p ,β g They are the proportion of peak time, average time and off-peak time to the total time of the day.

[0050] Specifically, the peak time period, flat time period and valley time period mentioned in this embodiment refer to the time period division of peak power consumption, valley power consumption and general power consumption. Among them, the peak time period usually refers to the time period of peak power demand, generally during the daytime of working days, especially at noon and in the evening. The flat time period refers to the time period of relatively stable power demand, generally between the morning and evening peaks. The valley time period refers to the time period of low power demand, generally in the late night or early morning.

[0051] Exemplarily, the peak, flat and valley time periods in Guangdong Province are divided into: peak period: 10:00-12:00, 14:00-19:00; valley period: 0:00-8:00; flat period: 8:00-10:00; 12:00-14:00; 19:00-24:00.

[0052] Furthermore, in this embodiment, based on the proportion of charging load of electric vehicle users in peak and off-peak periods on weekdays and weekends as a reference value for user charging habits, the user's sensitivity factor to the difference in charging electricity prices is calculated, thereby constructing a user sensitivity portrait model for further design of charging optimization solutions, which has high accuracy and is conducive to achieving a better orderly charging guidance effect for charging users in the target area.

[0053] Further, in step S3 of an optional embodiment, predicting the load rate at each time of the next day includes the following steps:

[0054] S310, calculate the load fluctuation rate at different times of the target area on weekdays and weekends; the expression is:

[0055]

[0056] Where D∈{weekday,weekend} represents the day type of weekday or weekend; X Drepresents the historical day set of day type D; P trans,i,t is the active power of the load of the transformer in the area at the tth moment on the i-th day in history; μ D,i,t represents the load fluctuation rate at the tth time on the i-th day of the history with day type D;

[0057] S320, combining the active power data of the transformer load in the target area on the current day, predicting the load value of the target area on the next day; the expression is:

[0058]

[0059] Where D is the day type of the next day; P trans,t,2 P represents the predicted load of the transformer in the next day at time t; trans,t,1 N represents the predicted load of the transformer in the current day at time t; D Indicates the total number of days in the historical day set with day type D;

[0060] S330, based on the predicted load value of the target substation for the next day, calculate the predicted load rate η at each time of the next day t ; Its expression is:

[0061]

[0062] Among them, S trans is the rated capacity of the transformer in the substation; cosθ is the power factor in the substation.

[0063] Exemplarily, the substation power factor cosθ is optionally set to 0.95.

[0064] Further, in step S3 of an optional embodiment, determining the optimal charging period for the next day based on the predicted load rate includes the following steps:

[0065] S340: Based on the predicted load rate, determine the demand for regulation during all time periods, wherein:

[0066] For the period [t, t+1], if the predicted load rate at time t is greater than the preset first threshold, and the predicted load rate at time t+1 is greater than the preset first threshold, then the period [t, t+1] is judged as a period with upward regulation demand, and the load amount ΔP to be guided by the target area is predicted. t,t+1 ; Its expression is:

[0067] ΔP t,t+1 =max{P trans,t,2 ,P trans,t+1,2}-γ 1 S trans cosθ

[0068] Among them, P trans,t,2 ,Ptrans,t+1,2 They represent the predicted load values ​​of the transformer at time t and time t+1 of the next day; γ 1 is the first threshold;

[0069] If the predicted load rate at time t is less than the preset second threshold, and the predicted load rate at time t+1 is less than the preset second threshold, then the period [t, t+1] is judged to be a load transfer period, that is, a period with downward regulation demand, and the load amount ΔP to be guided by the target area is predicted. t,t+1 ; Its expression is:

[0070] ΔP t,t+1 =γ 2 S trans cosθ-min{P trans,t,2 ,P trans,t+1,2};

[0071] Among them, γ 2 is the second threshold;

[0072] Otherwise, it is determined that there is no regulation demand during the period [t, t+1], and the load amount to be guided in the target area is ΔP t,t+1 =0.

[0073] In this embodiment, the load of the next day is predicted in combination with the active power data of the transformer load in the station area on that day, and the load rate of the whole day of the next day is further predicted. The charging optimization period of the next day is determined according to the load rate at each moment to improve the accuracy of the orderly charging optimization plan.

[0074] Specifically, in step S340, the first threshold value may be optionally set to 80%; the second threshold value may be optionally set to 30% of the maximum load rate of the transformer in the substation on the next day.

[0075] Furthermore, in step S4 of an optional embodiment, based on the sensitive portrait model, determining the amount of electricity price regulation in each charging optimization period of the next day includes the following steps:

[0076] According to the load fluctuation rate at time t the next day, the load active power P of each user in the target substation at time t the next day is predicted. EV,m,t And the predicted value of charging load for each user in the target area for the next day P EV,m ;in:

[0077]

[0078] In the formula, μ m,i,t is the load fluctuation rate of user m at time t on the i-th day; P EV,m,i,t is the load active power of user m at time t on the i-th day;

[0079] For the next day when there is an upward regulation demand period [t, t+1], calculate the charging price regulation amount Δc for this period deal,up,t ; Its expression is:

[0080]

[0081] Among them, N EV is the total number of electric vehicle charging users; D is the day type of the next day; P EV,t is the charging load value of all users in the target area at time t the next day; m,D represents the sensitive portrait model, and its value is the sensitivity factor of user m to the charging price difference when time t is in the peak, flat and valley period;

[0082] For the period of downward regulation demand on the next day, calculate the charging price regulation amount Δc for this period deal,down,t ; Its expression is:

[0083]

[0084] Among them, N deal,up T is the time for upward adjustment of electricity price. deal,up The downward control amount calculation in this embodiment is determined according to the upward control situation transfer.

[0085] Furthermore, in step S4, a charging optimization plan for the dynamic electricity price in each time period of the next day is generated according to the electricity price control amount in each charging optimization time period of the next day. Specifically, the charging electricity price of the corresponding time period and the charging point electricity price after the control amount are combined to obtain the charging optimization plan for the dynamic electricity price in each time period of the next day.

[0086] Specifically, for the period [t, t+1] when there is upward regulation demand, the electricity price at each moment is adjusted as follows:

[0087] c tomorrow,t =c d +Δc deal,up,t ;

[0088] For the period [t, t+1] when there is downward regulation of demand, the electricity price at each moment is adjusted as follows:

[0089] c tomorrow,t =c d -Δc deal,down,t

[0090] Among them, c dis the original electricity price of the peak period, flat period and valley period at time t, that is, d∈{f,p,g}. For the period when there is no regulation demand, the electricity price at each time is the original electricity price of the peak period, flat period and valley period at the corresponding time.

[0091] This embodiment generates a charging optimization plan for dynamic electricity prices for each time period of the next day based on user sensitivity portraits, and outputs it to the charging piles in the target area for execution. It guides the charging and discharging time and active power of electric vehicles through price signals, thereby achieving guidance and optimization of orderly charging of electric vehicles.

[0092] Example 2

[0093] This embodiment proposes an electric vehicle orderly charging optimization system based on user sensitive portraits, and applies the electric vehicle orderly charging optimization method proposed in Example 1. Figure 2 , which is an architecture diagram of the electric vehicle orderly charging optimization system of this embodiment.

[0094] The electric vehicle orderly charging optimization system based on user sensitive portraits proposed in this embodiment includes:

[0095] Data collection module, used to collect historical distribution network data and historical time-of-use electricity price data of the target substation;

[0096] The sensitive portrait module is used to calculate the user's sensitivity factors to charging electricity prices at different time periods on weekdays and weekends;

[0097] The substation load prediction module is used to predict the predicted load rate at each moment of the next day according to the distribution network data, and determine the charging optimization period of the next day based on the predicted load rate;

[0098] The charging optimization module is used to determine the electricity price control amount in each charging optimization period of the next day based on the sensitive portrait model, generate a charging optimization plan for the dynamic electricity price in each period of the next day and output it to the charging piles in the target area, and guide the charging and discharging time and power of electric vehicles through price signals.

[0099] It can be understood that the system of this embodiment corresponds to the method of the above-mentioned embodiment 1, and the options in the above-mentioned embodiment 1 are also applicable to this embodiment, so they will not be described repeatedly here.

[0100] Example 3

[0101] This embodiment proposes a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the orderly charging optimization method for electric vehicles proposed in Example 1.

[0102] Example 4

[0103] This embodiment provides a storage medium on which computer-readable instructions are stored, wherein the computer-readable instructions, when executed by a processor, implement the steps of the electric vehicle orderly charging optimization method provided in Embodiment 1.

[0104] Exemplarily, the storage medium includes, but is not limited to, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0105] Exemplarily, the instructions, programs, code sets or instruction sets may be implemented using conventional programming languages.

[0106] Exemplarily, the processor includes but is not limited to a smart phone, a personal computer, a server, a network device, etc., and is used to execute all or part of the steps of the electric vehicle orderly charging optimization method described in Example 1.

[0107] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely exemplary, in which the modules described as separate components may or may not be physically separated, and the functions of each module can be implemented in the same or one or more software and / or hardware when implementing the scheme of the present invention. It is also possible to select some or all of the modules according to actual needs to achieve the purpose of the scheme of this embodiment.

[0108] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for optimizing orderly charging of electric vehicles based on user sensitive portraits, characterized in that: The following steps are involved: Collect historical distribution network data and historical time-of-use electricity price data of the target area; Calculate the user's sensitivity factors to charging electricity prices at different time periods on weekdays and weekends, and build a user's sensitive profile model to charging electricity prices; Predicting the predicted load rate at each moment of the next day according to the distribution network data, and determining the charging optimization period of the next day based on the predicted load rate; Based on the sensitive portrait model, the amount of electricity price regulation in each charging optimization period of the next day is determined, and a charging optimization plan for the dynamic electricity price in each period of the next day is generated and output to the charging piles in the target area for execution.

2. The method for optimizing orderly charging of electric vehicles according to claim 1, characterized in that: The calculation of the user's sensitivity factors to charging electricity prices at different time periods of the day type being weekdays and weekends includes the following steps: According to the historical distribution network data, the proportion of charging load in the peak, flat and valley periods in the user's historical records is calculated; the expression is: Among them, α f,m,j ,α p,m,j ,α g,m,j They represent the proportion of charging load of electric vehicle user m during the peak period, flat period and valley period on the i-th day in history; P EV,m,i,t represents the load active power of electric vehicle user m at time t on the i-th day in history; T f ,T p ,T g They are the time sets for peak period, flat period and valley period respectively; According to the historical time-of-use electricity price data, the charging electricity price difference between peak-to-flat, peak-to-valley, and flat-to-valley periods is obtained; its expression is: Among them, Δc f-p ,Δc f-g ,Δc p-g Respectively represent the charging price difference between peak and flat periods, peak and valley periods, and flat and valley periods; c f 、c p 、c g are the original electricity prices during peak hours, flat hours, and off-peak hours respectively; According to the charging load proportion and the charging electricity price difference, the sensitivity factor of electric vehicle users to the charging electricity price difference during the peak and valley periods on weekdays and weekends is calculated respectively; the expression is: Among them, D∈{weekday,weekend} represents the day type of weekday or weekend;δ D,f-p,m ,δ D,f-g,m ,δ D,p-g,m They represent the sensitivity factors of user m to the charging price difference during peak-to-average, peak-to-valley, and flat-to-valley periods when the day type is D; D Represents a set of historical days with day type D; N D Indicates the total number of days in the historical day set with day type D; δ D,f,m ,δ D,p,m ,δ D,g,m They represent the sensitivity factors of user m to the charging price difference during peak hours, flat hours and valley hours when the type is D; β f ,β p ,β g They are the proportion of peak time, average time and off-peak time to the total time of the day.

3. The method for optimizing orderly charging of electric vehicles according to claim 1, characterized in that: The method of predicting the load rate at each moment of the next day includes the following steps: Calculate the load fluctuation rate at different times of the target area on weekdays and weekends; the expression is: Where D∈{weekday,weekend} represents the day type of weekday or weekend; X D represents the historical day set of day type D; P trans,i,t is the active power of the load of the transformer in the area at the tth moment on the i-th day in history; μ D,i,t represents the load fluctuation rate at time t on the i-th day of history with day type D; Combined with the active power data of the transformer load in the target area on the day, the load value of the target area on the next day is predicted; its expression is: Where D is the day type of the next day; P trans,t,2 P represents the predicted load of the transformer in the next day at time t; trans,t,1 N represents the predicted load of the transformer in the current day at time t; D Indicates the total number of days in the historical day set with day type D; Calculate the predicted load factor η at each time of the next day based on the predicted load value of the target substation for the next day t ; Its expression is: Among them, S trans is the rated capacity of the transformer in the substation; cosθ is the power factor in the substation.

4. The method for optimizing orderly charging of electric vehicles according to claim 3, characterized in that: The method of determining the charging optimization period for the next day based on the predicted load rate comprises the following steps: Based on the predicted load rate, full-time regulation demand determination is performed, wherein: For the period [t, t+1], if the predicted load rate at time t is greater than the preset first threshold, and the predicted load rate at time t+1 is greater than the preset first threshold, then the period [t, t+1] is judged as a period with upward regulation demand, and the load amount ΔP to be guided by the target area is predicted. t,t+1 ; Its expression is: ΔP t,t+1 =max{P trans,t,2 ,P trans,t+1,2 }-γ1S trans cosθ Among them, P trans,t,2 ,P trans,t+1,2 They represent the predicted load values ​​of the transformer in the next day at time t and time t+1 respectively; γ1 is the first threshold; If the predicted load rate at time t is less than the preset second threshold, and the predicted load rate at time t+1 is less than the preset second threshold, then the period [t, t+1] is judged to be a load transfer period, that is, a period with downward regulation demand, and the load amount ΔP to be guided by the target area is predicted. t,t+1 ; Its expression is: ΔP t,t+1 =γ2S trans cosθ-min{P trans,t,2 ,P trans,t+1,2 } Among them, γ2 is the second threshold; Otherwise, it is determined that there is no regulation demand during the period [t, t+1], and the load amount to be guided in the target area is ΔP t,t+1 =0.

5. The method for optimizing orderly charging of electric vehicles according to claim 4, characterized in that: The first threshold is 80%; the second threshold is 30% of the maximum load rate of the transformer in the substation on the next day.

6. The method for optimizing orderly charging of electric vehicles according to claim 4, characterized in that: The step of determining the amount of electricity price regulation in each charging optimization period of the next day based on the sensitive portrait model includes the following steps: According to the load fluctuation rate at time t the next day, the load active power P of each user in the target substation at time t the next day is predicted. EV,m,t And the predicted value of charging load for each user in the target area for the next day P EV,m ; In the formula, μ m,i,t is the load fluctuation rate of user m at time t on the i-th day; P EV,m,i,t is the load active power of user m at time t on the i-th day; For the next day when there is an upward regulation demand period [t, t+1], calculate the charging price regulation amount Δc for this period deal,up,t ; Its expression is: Among them, N EV is the total number of electric vehicle charging users; D is the day type of the next day; P EV,t is the charging load value of all users in the target area at time t the next day; m,D represents the sensitive portrait model, and its value is the sensitivity factor of user m to the charging price difference when time t is in the peak, flat and valley period; For the period of downward regulation demand on the next day, calculate the charging price regulation amount Δc for this period deal,down,t ; Its expression is: Among them, N deal,up T is the time for upward adjustment of electricity price. deal,up is the set of moments during which there are periods of upward regulation of demand.

7. The method for optimizing orderly charging of electric vehicles according to any one of claims 1 to 6, characterized in that: The historical distribution network data include the load active power of the target substation transformer at each time in the past month, the rated capacity of the substation, and the load active power of each user in the target substation at each time in the past month; the historical time-of-use electricity price data include the specific time periods of peak, flat and valley electricity prices, and the charging electricity prices of electric vehicles in the target substation at each time period.

8. An electric vehicle orderly charging optimization system based on user sensitive portraits, applying the electric vehicle orderly charging optimization method according to any one of claims 1 to 7, characterized in that: include: Data collection module, used to collect historical distribution network data and historical time-of-use electricity price data of the target substation; The sensitive portrait module is used to calculate the user's sensitivity factors to charging electricity prices at different time periods on weekdays and weekends; The substation load prediction module is used to predict the predicted load rate at each moment of the next day according to the distribution network data, and determine the charging optimization period of the next day based on the predicted load rate; The charging optimization module is used to determine the electricity price control amount in each charging optimization period of the next day based on the sensitive portrait model, generate a charging optimization plan for the dynamic electricity price in each period of the next day and output it to the charging piles in the target area, and guide the charging and discharging time and power of electric vehicles through price signals.

9. A device comprising a memory and a processor, wherein the memory stores computer-readable instructions, characterized in that: When the computer-readable instructions are executed by the processor, the processor executes the steps of the electric vehicle orderly charging optimization method according to any one of claims 1 to 7.

10. A storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the steps of the method for optimizing orderly charging of an electric vehicle as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Intelligent power grid adjusting method for electric vehicle charging load prediction and analysis

    CN119742779A

  • Electric vehicle real-time electricity price calculation method and system considering charging pile utilization rate

    CN119904059A

  • A charging pile utilization rate considering electric vehicle real-time electricity price calculation method and system

    CN119904059B

  • Charging equipment monitoring, operation and maintenance management system and method based on multi-source data

    CN120197835A

  • Charging pile group load intelligent regulation and control method and system based on dynamic power balance

    CN120396753A