A method for accurate prediction and control of interactive resources for distributed vehicle-grid charging and discharging services

Abstract

The present invention discloses a method for accurately predicting and controlling interactive resources of distributed vehicle-grid charging and discharging services, and the present invention relates to the technical field of vehicle-grid interactive charging and discharging prediction and control methods. The method for accurately predicting and controlling interactive resources of distributed vehicle-grid charging and discharging services introduces the data decision response value β, the charging decision response amount CDX and the discharging decision response amount FDX of the target network-connected new energy vehicle in response to the charging and discharging policy, and then provides data support to the aggregator when making charging and discharging decisions, which is beneficial for the aggregator to make accurate adjustments to the current charging and discharging decisions based on the last response, greatly improving the accuracy of the decision adjustment, and then effectively improving the effect of relieving the load of the power grid when the power grid is under high load, and can also provide adjustment support when the aggregator makes incentive adjustments to the target network-connected new energy vehicle owners, so that the incentive system can be more data-based and accurate, and the enthusiasm of new energy vehicle owners to participate in vehicle-grid interaction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-grid interactive charging and discharging prediction and control methods, and specifically to an interactive resource precise prediction and control method for distributed vehicle-grid charging and discharging services. Background Art

[0002] At a time when new energy vehicles are developing rapidly and the number of new energy vehicles is growing rapidly, vehicle-grid interaction can effectively utilize the batteries of new energy vehicles when they are parked, interact with each new energy vehicle with the power grid, and use new energy vehicles to charge during off-peak hours and discharge during peak hours, thus achieving the effect of shaving peaks and filling valleys to relieve the pressure on the power grid;

[0003] Referring to a method for peak shaving and valley filling of a regional integrated energy system disclosed in publication number CN117332989A, such as the method for peak shaving and valley filling of a regional integrated energy system, the prior art charging and discharging control schemes for vehicle-grid interaction all construct prediction models, combine the charging and usage data of new energy vehicles, the load electricity price data of the power grid, and the usage data of charging piles to make predictions on the charging conditions of new energy vehicles and the load conditions of the power grid, and then the aggregator makes charging and discharging adjustment strategies for new energy vehicles participating in vehicle-grid interaction based on the prediction models;

[0004] Although it can effectively alleviate the load on the power grid and achieve the effect of peak shaving and valley filling, in actual operation, the existing prediction model does not make effective calculations for the corresponding decisions of new energy vehicle owners. Therefore, when suppliers make charging and discharging decisions, they only have the power grid load forecast data and new energy vehicle charging demand forecast data obtained by the model. The decisions made based on this often do not fully consider the response values ​​of new energy vehicles actually participating in charging and discharging. As a result, the decisions made in actual implementation often fail to achieve the expected results in alleviating the peak load of the power grid. At the same time, due to the lack of corresponding response value calculations, the incentives for new energy vehicle owners cannot be adjusted in a timely and accurate manner, so the actual execution effect of the vehicle-grid interaction of new energy vehicle owners cannot be effectively improved.

[0005] Therefore, it is necessary to provide a method for accurately predicting and controlling interactive resources of distributed vehicle-grid charging and discharging services to solve the above technical problems. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In order to solve the above technical problems, the present invention provides a method for accurately predicting and controlling interactive resources of distributed vehicle network charging and discharging services.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for accurately predicting and controlling interactive resources of distributed vehicle network charging and discharging services, specifically comprising the following steps:

[0010] A1. The data acquisition module collects new energy vehicle charging and discharging data, grid load, and charging pile usage data;

[0011] A2, the processing module uses the collected historical new energy vehicle charging and discharging data, grid load and charging pile usage data to establish a prediction model;

[0012] A3. The processing module uses the prediction model and real-time new energy vehicle charging and discharging data, grid load, and charging pile usage data to predict the charging demand of target new energy vehicles and the load status of the grid. The prediction results are output to the aggregator terminal for the aggregator to make decisions and adjustments;

[0013] A4. The data collection module is used to collect charging and discharging data of the target new energy vehicles that are connected to the network. The aggregator terminal calculates the data on the target new energy vehicles that are connected to the network in response to the charging and discharging policy in the previous accounting cycle P, and provides the aggregator with the prediction results for reference in adjusting charging and discharging decisions in the current accounting cycle P, as well as for decision-making on incentives for the owners of the target new energy vehicles that are connected to the network.

[0014] Preferably, the situation data in response to the charge and discharge policy specifically include a decision response value β, a charge decision response amount CDX and a discharge decision response amount FDX.

[0015] Preferably, the steps for the aggregator to make incentive decisions for the target new energy vehicle owners in step A4 are specifically as follows:

[0016] B1. Use the data collection module to collect the total valley-filling charging amount TC of the target connected new energy vehicles in the charging time period specified by the charging decision of the aggregator and the charging location, the total peak-shaving discharge amount XF in the discharge time period specified by the discharge decision of the aggregator and the total charging amount ZC in the previous calculation period P;

[0017] B2. Calculate the decision response value β of the target grid-connected new energy vehicle in the previous calculation cycle P using the total valley filling charging amount TC and the total peak shaving discharge amount XF. The decision response value β is calculated using the following formula:

[0018] ;

[0019] Among them, JZF is the sum of the decision discharge of all discharge decisions made by the aggregator in the last accounting period P of the target network-connected new energy vehicle, a and b are both influence coefficients, a+b=100%, and a <b;

[0020] B3. At the end of the previous accounting cycle P, the aggregator terminal arranges all target network-connected new energy vehicles in descending order according to the value of the decision response value β, and obtains an incentive decision report, which is output to the aggregator. The aggregator uses this as a decision support for incentivizing the owners of target network-connected new energy vehicles within the current accounting cycle P.

[0021] Preferably, in step A4, the aggregator adjusts the charge and discharge decision reference within the current accounting period P in response to the situation data of the charge and discharge policy, specifically including two aspects: discharge decision adjustment and charge decision adjustment.

[0022] Preferably, the discharge decision adjustment specifically comprises the following steps:

[0023] C1. Calculate the average value AP of the discharge decision response of all target connected new energy vehicles in the previous calculation period P:

[0024] ;

[0025] Among them, FDXm represents the discharge decision response of the mth target network-connected new energy vehicle in the previous calculation cycle P;

[0026] C2. When AP is less than 100%, the missing value QZ is predicted and calculated each time a charge and discharge decision is made within the current calculation period P. The calculation formula for the missing value QZ is as follows:

[0027] ;

[0028] Among them, JF is the decision discharge amount required by the aggregator to make a discharge decision for the target network-connected new energy vehicle without considering the average value AP of the discharge decision response amount;

[0029] C3. The aggregator makes corresponding discharge strategy adjustments based on the predicted vacancy value. The discharge strategy adjustments at least include increasing the decision-making discharge amount, adjusting the peak discharge reward mechanism, and adjusting the peak-valley electricity price difference.

[0030] Preferably, the charging decision adjustment specifically comprises the following steps:

[0031] D1. Calculate the average value BP of charging decision response of all target connected new energy vehicles in the previous calculation period P:

[0032] ;

[0033] Among them, CDXn is the charging decision response of the mth target network-connected new energy vehicle in the previous calculation cycle P;

[0034] D2. When BP is less than the set value U, the prediction module will sort all target connected new energy vehicles in descending order according to the value of the charging decision response CDX in the previous calculation cycle P, and send the sorting report to the transmission module for the aggregator to adjust the decision;

[0035] D3. The aggregator makes charging decision adjustments within the current accounting period P based on the ranking report. The charging decision adjustments at least include coordinating with the power grid to adjust the peak and valley electricity prices and adjusting the valley charging incentive mechanism.

[0036] Preferably, a vehicle-grid interactive resource prediction and control system is used for prediction and control, and the vehicle-grid interactive resource prediction and control system specifically includes:

[0037] Data collection module: including new energy vehicle charging behavior collection module, power grid load information collection module and charging pile information collection module, collecting new energy vehicle charging and discharging data, power grid load data and charging pile usage data;

[0038] Processing module: including a model building module for establishing a prediction model using the data collected by the data collection module and a calculation module for predicting results using the prediction model;

[0039] an aggregator terminal, comprising a communication module for receiving the prediction result output by the processing module and outputting the adjustment decision and a re-prediction module for calculating the situation data of the response charging and discharging policy in step A4;

[0040] New energy vehicle terminal: It is used by owners of new energy vehicles that target the network to accept instructions from aggregators.

[0041] Preferably, the calculation period P ranges from one week to one month.

[0042] (III) Beneficial effects

[0043] The present invention provides a method for accurately predicting and controlling interactive resources of distributed vehicle network charging and discharging services. Compared with the prior art, it has the following beneficial effects:

[0044] 1. The present invention provides a method for accurately predicting and controlling interactive resources of distributed vehicle-grid charging and discharging services. By monitoring the charging and discharging data of target network-connected new energy vehicles, the target network-connected new energy vehicles are introduced to respond to charging and discharging policies. The data decision response value β, the charging decision response amount CDX and the discharging decision response amount FDX are introduced, and then when the aggregator makes a charging and discharging decision, the aggregator is given data support, which is beneficial for the aggregator to make accurate adjustments to the current charging and discharging decision according to the previous response situation, which greatly improves the accuracy of the decision adjustment, and then effectively improves the effect of alleviating the load of the power grid when the power grid is under high load;

[0045] 2. The present invention provides a method for accurately predicting and controlling interactive resources of distributed vehicle-grid charging and discharging services, and introduces data that responds to charging and discharging policy conditions. In addition to providing decision support to aggregators in terms of charging and discharging decisions, it can also provide adjustment support when aggregators make incentive adjustments to target owners of new energy vehicles that have joined the network, making the incentive system more data-based and accurate, thereby enhancing the enthusiasm of new energy vehicle owners to participate in vehicle-grid interaction, and greatly improving the multi-party benefits brought about by vehicle-grid interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0047] Figure 2 A schematic diagram of the steps for the aggregator to make incentive decisions for the target new energy vehicle owner in step A4 of the present invention;

[0048] Figure 3 A schematic diagram of the discharge decision adjustment steps of the present invention;

[0049] Figure 4 A schematic diagram of the charging decision adjustment steps of the present invention;

[0050] Figure 5 This is a schematic diagram of Embodiment 2 of the present invention;

[0051] Figure 6 A flow chart for adjusting the discharge strategy of the present invention;

[0052] Figure 7 The charging strategy adjustment flow chart of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] For example, see Figures 1 to 4 , Figure 6 and Figure 7 This embodiment provides a technical solution: a method for accurately predicting and controlling interactive resources of distributed vehicle network charging and discharging services, which specifically includes the following steps:

[0055] A1. The data acquisition module collects new energy vehicle charging and discharging data, grid load, and charging pile usage data;

[0056] A2, the processing module uses the collected historical new energy vehicle charging and discharging data, grid load and charging pile usage data to establish a prediction model;

[0057] A3. The processing module uses the prediction model and real-time new energy vehicle charging and discharging data, grid load, and charging pile usage data to predict the charging demand of target new energy vehicles and the load status of the grid. The prediction results are output to the aggregator terminal for the aggregator to make decisions and adjustments;

[0058] In steps A1 to A3, the construction of the prediction model applied to the vehicle-pile-grid interactive technology and the specific content of the model are all existing technologies. The main steps are to collect the charging data of new energy vehicles, the charging data of charging piles and the data of the power grid, and use the data from these three aspects to establish a prediction model. The prediction model finally obtained can use the real-time power grid load data, the electric travel situation data of new energy vehicles and the use data of charging piles to make real-time predictions. The prediction results include the prediction of the charging demand of new energy vehicles and the prediction of the power grid load. Therefore, the specific content of the model and the construction and calculation process are not described in detail here;

[0059] The steps for building the model are as follows:

[0060] E1. Demand analysis: clarify the application scenarios and goals of the vehicle-grid interaction model, such as improving grid stability, reducing energy waste, and optimizing vehicle charging experience; analyze user needs and expectations, and understand the charging habits and travel patterns of electric vehicle owners;

[0061] E2. Data collection and processing: Collect data related to vehicle-grid interaction, including grid load data, electric vehicle charging data, renewable energy output data, etc., clean, organize and analyze the collected data to extract information useful for model construction;

[0062] E3, Model framework design: Design the overall framework of the vehicle-grid interaction model, including vehicle model, grid model, energy interaction strategy, etc., determine the key parameters and variables in the model, and the interaction relationship between them;

[0063] E4. Vehicle model construction: Establish the charging and discharging model of electric vehicles, consider the battery's charging rate, discharging rate, state of charge and other characteristics, integrate the vehicle's driving mode and energy consumption prediction, so as to more accurately reflect the vehicle's actual status and needs;

[0064] E5. Grid model construction: Establish the load model and power supply capacity model of the grid, consider the load changes and renewable energy output at different time scales, analyze the stability and economy of the grid, and determine the grid's response capability to vehicle energy interaction;

[0065] E6. Energy interaction strategy formulation: Formulate energy interaction strategies between vehicles and the power grid, including charging time, charging power, discharging time, discharging power, etc., taking into account factors such as electricity price, load balance, and renewable energy utilization rate, optimize energy interaction strategies, and maximize economic and environmental benefits;

[0066] E7, Simulation verification and optimization: Use simulation tools to simulate and verify the vehicle-grid interaction model, simulate the energy interaction process in different scenarios, and evaluate the performance of the model based on the simulation results, including indicators such as energy interaction efficiency, grid stability, and user satisfaction. Optimize and adjust the model based on the evaluation results to improve the accuracy and practicality of the model;

[0067] E8, System Integration and Testing: Integrate the vehicle-grid interaction model with the actual vehicle and power grid system to ensure that the model can operate normally in the actual environment, and conduct system integration testing to verify whether the communication and energy interaction functions between the model and the vehicle and power grid are normal;

[0068] A4. The data collection module is used to collect charging and discharging data of target network-connected new energy vehicles. The aggregator terminal calculates the data on the response of the target network-connected new energy vehicles to the charging and discharging policy in the previous accounting cycle P, and the supply aggregator uses the prediction results to make reference adjustments to charging and discharging decisions in the current accounting cycle P, as well as to make decisions on incentives for the owners of target network-connected new energy vehicles. The accounting cycle P lasts from one week to one month. If it is less than one week, the amount of data calculated will be small and the reference value will be small. If the accounting cycle P is longer than one month, the adjustment interval will be too long, resulting in the inability to discover problems in a timely manner. The data on responding to the charging and discharging policy specifically include the decision response value β, the charging decision response amount CDX and the discharging decision response amount FDX.

[0069] The specific steps for the aggregator to make incentive decisions for target new energy vehicle owners in step A4 are as follows:

[0070] B1. Use the data collection module to collect the total valley-filling charging amount TC of the target connected new energy vehicles in the charging time period specified by the charging decision of the aggregator and the charging location, the total peak-shaving discharge amount XF in the discharge time period specified by the discharge decision of the aggregator and the total charging amount ZC in the previous calculation period P;

[0071] The total valley filling charging amount TC is explained as follows: it is assumed that the aggregator requires the target new energy vehicle to charge at the specified charging and discharging charging position between 22:00 and 5:00 on a certain day, and the target new energy vehicle charges 20 degrees in this time period. This 20 degrees is the effective single-day valley filling charging amount. Assuming that there are four charging decisions in the last accounting cycle P, the effective single-day valley filling charging amount of the target new energy vehicle in each of the four charging decisions is 20 degrees, 25 degrees, 25 degrees, and 30 degrees respectively. Then, the total valley filling charging amount TC of the target new energy vehicle in the charging time period specified by the aggregator's charging decision in the last accounting cycle P is 100 degrees.

[0072] The total amount of peak shaving discharge XF is explained as follows: suppose that the aggregator's one-time charge and discharge decision adjustment requires the target grid-connected new energy vehicle to discharge 5 degrees at the specified charge and discharge position between 10:00 and 13:00 on a certain day, and the target grid-connected new energy vehicle discharges 2 degrees during this time period, and this 2 degrees is the effective single-day peak shaving discharge. Assuming that there are four discharge decisions in the last accounting cycle P, and the effective single-day peak shaving discharge of the target grid-connected new energy vehicle in each of the four discharge decisions is 2 degrees, 2 degrees, 5 degrees, and 3 degrees, respectively, then the total amount of peak shaving discharge XF of the target grid-connected new energy vehicle in the last accounting cycle P at the discharge time period specified by the aggregator's discharge decision is 12 degrees.

[0073] The total charging amount ZC is explained as: the total charging degree of all charging behaviors of the target connected new energy vehicle in the previous accounting period P, regardless of any time period and whether or not at the specified location;

[0074] B2. Calculate the decision response value β of the target grid-connected new energy vehicle in the previous calculation cycle P using the total valley filling charging amount TC and the total peak shaving discharge amount XF. The decision response value β is calculated using the following formula:

[0075] ;

[0076] Among them, JZF is the sum of the decision discharge of all discharge decisions made by the aggregator in the last accounting period P of the target network-connected new energy vehicle, a and b are both influence coefficients, a+b=100%, and a <b;

[0077] B3. At the end of the previous accounting cycle P, the aggregator terminal arranges all target networked new energy vehicles in descending order according to the value of the decision response value β, obtains an incentive decision report and outputs it to the aggregator. The aggregator uses this as a decision support for incentivizing the owners of target networked new energy vehicles in this accounting cycle P;

[0078] Substituting actual data into steps B1, B2 and B3 for example explanation, we get the following:

[0079] The duration of the last calculation cycle P is 1 week. The aggregator makes a charge and discharge decision once a day. The data acquisition module monitors and obtains the actual charge and discharge data of the target network-connected new energy vehicles in response to 7 charge and discharge decisions in the last calculation cycle P, as shown in Table 1 below;

[0080] Table 1:

[0081]

[0082] (1)

[0083] (2)

[0084] Substituting the results of equations (1) and (2) into the decision response value β calculation formula, and setting a=40% and b=60%, we get:

[0085] ;

[0086] Therefore, the decision response value β of the target network-connected new energy vehicle in the last calculation period P is 824%;

[0087] Based on the above calculation process, within a calculation period P, the decision response values ​​β of all target network-connected new energy vehicles under the jurisdiction of the aggregator are set as shown in Table 2 below;

[0088] Table 2:

[0089] β1 β2 β3 β4 Target new energy vehicles 1 Target new energy vehicles 2 Target new energy vehicles 3 Target to connect new energy vehicles4 82.4% 90% 75.3% 88%

[0090] According to the numerical value of the decision response value β, all target new energy vehicles are ranked to obtain an incentive decision report, which is presented in the form shown in Table 3 below;

[0091] Table 3:

[0092] Target new energy vehicles 2 Target to connect new energy vehicles4 Target new energy vehicles 1 Target new energy vehicles 3 β2 β4 β1 β3 90% 88% 82.4% 75.3%

[0093] After receiving the incentive decision report, it will be fed back to the aggregator, who can then make accurate and fair incentive decisions based on it. In the actual decision-making process, the participation reward of the top-ranked target network-connected new energy vehicle owners can be increased. By introducing the decision response value β, the aggregator can have a more accurate understanding of the participation of each of its subordinate target network-connected new energy vehicles in the vehicle-grid interactive charging and discharging behavior, and can make corresponding incentive adjustments in a timely manner, thereby enhancing the participation enthusiasm of the target network-connected new energy vehicle owners, and greatly improving the multi-party benefits brought by the vehicle-grid interaction;

[0094] In step A4, the aggregator adjusts the charging and discharging decision reference within the current accounting period P in response to the situation data of the charging and discharging policy, which specifically includes two aspects: discharge decision adjustment and charging decision adjustment; the discharge decision adjustment specifically includes the following steps:

[0095] C1. Calculate the average value AP of the discharge decision response of all target connected new energy vehicles in the previous calculation period P:

[0096] ;

[0097] Among them, FDXm represents the discharge decision response of the mth target network-connected new energy vehicle in the previous calculation cycle P;

[0098] C2. When AP is less than 100%, the missing value QZ is predicted and calculated each time a charge and discharge decision is made within the current calculation period P. The calculation formula for the missing value QZ is as follows:

[0099] ;

[0100] Among them, JF is the decision discharge amount required by the aggregator to make a discharge decision for the target network-connected new energy vehicle without considering the average value AP of the discharge decision response amount;

[0101] C3. The aggregator makes corresponding discharge strategy adjustments based on the predicted vacancy value. The discharge strategy adjustments at least include increasing the decision-making discharge amount, adjusting the peak discharge reward mechanism, and adjusting the peak-valley electricity price difference;

[0102] Based on the above, the examples are as follows:

[0103] Assume that in the previous calculation period P, the discharge decision response FDX of all target network-connected new energy vehicle owners is =60%, =75%, =78%, =89%, and substitute it into the calculation formula of the average AP of the discharge decision response as follows:

[0104] ;

[0105] The calculated average discharge decision response value AP is 75.5%, which is less than 100%. The decision discharge value of the target grid-connected new energy vehicle that is not considered in this charge and discharge decision is set to 3 degrees. The missing value QZ is predicted and calculated within this calculation cycle P:

[0106] ;

[0107] From the above results, it can be concluded that, without considering the average value AP of the discharge decision response, according to the traditional method, the aggregator directly adjusts the decision according to the prediction results of the prediction model, and the final discharge decision may have a discharge demand of 0.735 degrees that cannot be met in actual situation. This is the result obtained by referring to the prediction of the average value AP of the discharge decision response in the previous calculation cycle P. Therefore, when the aggregator makes charging and discharging decisions in this calculation cycle P, it is necessary to take the decision response average value AP into consideration, and adjust the final discharge decision based on this to avoid the vacancy value QZ and ensure that the charging demand can be met. It should be emphasized that JZF is the sum of the decision discharge in all discharge decisions made by the aggregator for the target new energy vehicles in the previous calculation cycle P. All discharge decisions made by the aggregator in this description are discharge decisions made after considering the average value AP of the discharge decision response.

[0108] Charging decision adjustment specifically includes the following steps:

[0109] D1. Calculate the average value BP of charging decision response of all target connected new energy vehicles in the previous calculation period P:

[0110] ;

[0111] Among them, CDXn is the charging decision response of the mth target network-connected new energy vehicle in the previous calculation cycle P;

[0112] D2. When BP is less than the set value U, the prediction module will sort all target connected new energy vehicles in descending order according to the value of the charging decision response CDX in the previous calculation cycle P, and send the sorting report to the transmission module for the aggregator to adjust the decision;

[0113] D3. The aggregator makes charging decision adjustments within the current accounting period P based on the ranking report. The charging decision adjustments at least include coordinating with the power grid to adjust the peak and valley electricity prices and adjusting the valley charging incentive mechanism.

[0114] For the charging decision response average BP example, the calculation is as follows:

[0115] Assume that the charging decision response quantities CDX of all target connected new energy vehicles in the previous calculation period P are CDX1=90%, CDX2=80%, CDX3=80% and CDX4=95% respectively, and substitute them into the calculation formula of the average charging decision response quantity BP to obtain the following:

[0116] ;

[0117] Set U = 90%, and if the calculated result BP < U above, then sort all the target new energy vehicles to be connected to the grid in descending order according to the value of the charging decision response volume CDX within the previous accounting period P to obtain the following sorting report, and the sorting report is presented in the form of a table, as shown in Table 4 below:

[0118] Table 4:

[0119] CDX4 CDX1 CDX2 CDX3 95% 90% 80% 80% Target to connect new energy vehicles4 Target new energy vehicles 1 Target new energy vehicles 3 Target new energy vehicles 2

[0120] Feed back Table 4 above to the aggregator for adjustment decision-making. For the sorting between several charging decision response volumes CDX with the same value, the sorting can be done randomly;

[0121] By introducing the decision response value β, the charging decision response volume CDX, and the discharging decision response volume FDX, when the aggregator makes charging and discharging decisions, data support is provided to the aggregator, which is conducive to the aggregator making precise adjustments to the current charging and discharging decisions according to the previous response situation, greatly improving the accuracy of decision adjustment, and thus effectively enhancing the effect of relieving the grid load during high grid loads;

[0122] Example 2, please refer to Figure 5 , this example provides prediction and control for the vehicle-grid interaction resource prediction and control system in Example 1, specifically including:

[0123] Data acquisition module: It includes a new energy vehicle charging behavior acquisition module, a grid load information acquisition module, and a charging pile information acquisition module, which collect new energy vehicle charging and discharging data, grid load data, and charging pile usage data;

[0124] Processing module: It includes a model construction module that uses the data collected by the data acquisition module to establish a prediction model and a calculation module that uses the prediction model to predict the results;

[0125] Aggregator terminal, including a communication module for receiving the prediction results output by the processing module and outputting adjustment decisions and a re-prediction module for calculating the situation data of responding to the charging and discharging policies in step A4;

[0126] New energy vehicle terminal: For the owners of target new energy vehicles to receive the instructions of the aggregator.

[0127] At the same time, the content not described in detail in this specification belongs to the well-known prior art in the art.

[0128] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0129] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for accurately predicting and controlling interactive resources of distributed vehicle-grid charging and discharging services, characterized in that: The specific steps include: A1. The data acquisition module collects new energy vehicle charging and discharging data, grid load, and charging pile usage data; A2, the processing module uses the collected historical new energy vehicle charging and discharging data, grid load and charging pile usage data to establish a prediction model; A3. The processing module uses the prediction model and real-time new energy vehicle charging and discharging data, grid load, and charging pile usage data to predict the charging demand of target new energy vehicles and the load status of the grid. The prediction results are output to the aggregator terminal for the aggregator to make decisions and adjustments; A4. The data collection module is used to collect the charging and discharging data of the target network-connected new energy vehicles. The aggregator terminal calculates the data on the response of the target network-connected new energy vehicles to the charging and discharging policy in the previous accounting cycle P, and provides the aggregator with the prediction results for reference in adjusting the charging and discharging decision in the current accounting cycle P and for decision-making on incentives for the owners of the target network-connected new energy vehicles. The situation data responding to the charging and discharging policy specifically include a decision response value β, a charging decision response amount CDX, and a discharging decision response amount FDX; The specific steps for the aggregator to make incentive decisions for the target new energy vehicle owners in step A4 are as follows: B1. Use the data collection module to collect the total valley-filling charging amount TC of the target connected new energy vehicles in the charging time period specified by the charging decision of the aggregator and the charging location, the total peak-shaving discharge amount XF in the discharge time period specified by the discharge decision of the aggregator and the total charging amount ZC in the previous calculation period P; B2. Calculate the decision response value β of the target grid-connected new energy vehicle in the previous calculation cycle P using the total valley filling charging amount TC and the total peak shaving discharge amount XF. The decision response value β is calculated using the following formula: ； Among them, JZF is the sum of the decision discharge of all discharge decisions made by the aggregator for the target network-connected new energy vehicles in the previous accounting period P, a and b are both influence coefficients, a+b=100%, and a <b; B3. At the end of the previous accounting cycle P, the aggregator terminal arranges all target networked new energy vehicles in descending order according to the value of the decision response value β, obtains an incentive decision report and outputs it to the aggregator. The aggregator uses this as a decision support for incentivizing the owners of target networked new energy vehicles in this accounting cycle P; In step A4, the aggregator makes adjustments to the charging and discharging decision reference within the current accounting period P in response to the situation data of the charging and discharging policy, specifically including two aspects: discharge decision adjustment and charging decision adjustment.

2. According to claim 1, a method for accurately predicting and controlling interactive resources of distributed vehicle network charging and discharging services is characterized by: The discharge decision adjustment specifically includes the following steps: C1. Calculate the average value AP of the discharge decision response of all target connected new energy vehicles in the previous calculation period P: ； Among them, FDXm represents the discharge decision response of the mth target network-connected new energy vehicle in the previous calculation cycle P; C2. When AP is less than 100%, the missing value QZ is predicted and calculated each time a charge and discharge decision is made within the current calculation period P. The calculation formula for the missing value QZ is as follows: ； Among them, JF is the decision discharge amount required by the aggregator to make a discharge decision for the target network-connected new energy vehicle without considering the average value AP of the discharge decision response amount; C3. The aggregator makes corresponding discharge strategy adjustments based on the predicted vacancy value. The discharge strategy adjustments at least include increasing the decision-making discharge amount, adjusting the peak discharge reward mechanism, and adjusting the peak-valley electricity price difference.

3. According to claim 1, a method for accurately predicting and controlling interactive resources of distributed vehicle-grid charging and discharging services, characterized in that: The charging decision adjustment specifically includes the following steps: D1. Calculate the average value BP of charging decision response of all target connected new energy vehicles in the previous calculation period P: ； Among them, CDXn is the charging decision response of the mth target network-connected new energy vehicle in the previous calculation cycle P; D2. When BP is less than the set value U, the prediction module will sort all target connected new energy vehicles in descending order according to the value of the charging decision response CDX in the previous calculation cycle P, and send the sorting report to the transmission module for the aggregator to adjust the decision; D3. The aggregator makes charging decision adjustments within the current accounting period P based on the ranking report. The charging decision adjustments at least include coordinating with the power grid to adjust peak and valley electricity prices and adjusting the valley charging incentive mechanism.

4. According to claim 1, a method for accurately predicting and controlling interactive resources of distributed vehicle network charging and discharging services is characterized by: The vehicle-grid interactive resource prediction and control system is used for prediction and control. The vehicle-grid interactive resource prediction and control system specifically includes: Data collection module: including new energy vehicle charging behavior collection module, power grid load information collection module and charging pile information collection module, collecting new energy vehicle charging and discharging data, power grid load data and charging pile usage data; Processing module: including a model building module for establishing a prediction model using the data collected by the data collection module and a calculation module for predicting results using the prediction model; an aggregator terminal, comprising a communication module for receiving the prediction result output by the processing module and outputting the adjustment decision and a re-prediction module for calculating the situation data of the response charging and discharging policy in step A4; New energy vehicle terminal: It is used by owners of new energy vehicles that target the network to accept instructions from aggregators.

5. The interactive resource accurate prediction and control method for distributed vehicle network charging and discharging service according to claim 1 is characterized by: The duration of the calculation period P ranges from one week to one month.

Images