Method for promoting power consumption of new energy vehicle

Abstract

The invention relates to the technical field of power system optimization scheduling, and discloses a method for promoting power consumption of a new energy automobile, which comprises the following steps: firstly, acquiring real-time load data of a power grid to establish a prediction model, generating a charging demand space-time matrix in combination with user behavior data of the new energy automobile, and meanwhile, calculating a renewable energy consumption threshold value; and constructing a multi-objective optimization function. On this basis, electricity price excitation levels are divided, a dynamic electricity price adjustment coefficient is calculated, a user response probability model is established, and a differentiated charging guide instruction is generated. The method has the advantages that the utilization rate of renewable energy sources can be increased, and the electricity abandoning rate is reduced; power grid load is balanced, and peak-valley difference is reduced; the user charging cost is reduced; the intelligent level of energy management is improved, collaborative development of the new energy automobile and the power grid is promoted, good economic benefits and environmental benefits are achieved, and the problems of new energy automobile charging and renewable energy consumption are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimal dispatching, and particularly to a method for promoting electricity consumption by new energy vehicles. Background Art

[0002] Under the background of the global active response to climate change and the strong promotion of energy transformation, the new energy vehicle industry has developed vigorously and become a key force in achieving energy conservation and emission reduction in the transportation field. At the same time, with the continuous increase in the proportion of distributed renewable energy (such as solar energy, wind energy, etc.) in the power supply system, the problem of electricity consumption has become increasingly prominent and has become an important factor restricting the sustainable development of energy. In this general environment, exploring the collaborative development model between new energy vehicles, the power grid and renewable energy is of great significance for realizing the efficient utilization of energy and the stable operation of the power system.

[0003] In recent years, the ownership of new energy vehicles has shown an explosive growth. Although this growth trend helps to reduce the carbon emissions of traditional fuel vehicles, it also brings new challenges to the power system. The charging behavior of new energy vehicles is characterized by randomness and concentration. If a large number of vehicles charge at the same time, it is easy to cause a sudden increase in the load of the local power grid, increase the peak-valley difference of the power grid, and affect the power supply stability and reliability of the power grid.

[0004] As the main force of clean energy, renewable energy has developed rapidly. However, the problems of intermittent and fluctuating power generation are prominent. Taking solar photovoltaic power generation as an example, affected by weather and day-night changes, the power generation power is unstable. On cloudy days or at night, the photovoltaic power generation drops significantly or even stops; wind power generation is also restricted by changes in wind speed and wind direction and is difficult to supply power continuously and stably. This makes it extremely difficult for renewable energy to be incorporated into the power grid in terms of power balance and power quality control of the power grid, resulting in a large amount of renewable energy electricity that cannot be effectively consumed, and the phenomena of abandoned wind and abandoned light occur frequently.

[0005] To solve the above problems, various measures have been taken in the industry at present. In terms of the charging management of new energy vehicles, some charging pile operation enterprises adopt a timed charging strategy to encourage users to charge during the low-peak electricity price period at night. However, this method does not fully consider the actual needs of users and the real-time load changes of the power grid. The flexibility of users is limited, and the charging plan cannot be dynamically adjusted according to the renewable energy power generation situation. In terms of renewable energy consumption, some regions have built large-scale energy storage facilities, such as battery energy storage power stations, to store electric energy when renewable energy power generation is excessive and release electric energy when power generation is insufficient. However, the construction cost of energy storage facilities is high, the investment recovery period is long, and large-scale promotion faces economic pressure. At the same time, the existing energy storage capacity is limited and it is difficult to completely balance the large power fluctuations of renewable energy.

[0006] With the development of smart grid technology and big data analysis technology, new opportunities are provided for solving the problems of power consumption of new energy vehicles and the consumption of renewable energy. The smart grid can realize the intelligent monitoring, control, and management of the power system, and obtain information such as grid load data and power generation equipment output data in real time; big data analysis technology can mine and analyze massive amounts of user behavior data and energy data, providing a basis for accurately formulating energy management strategies. However, there is currently no mature and effective solution for using these technologies to comprehensively consider grid load, new energy vehicle charging demand, and the characteristics of renewable energy power generation for power consumption and consumption. Summary of the Invention

[0007] The purpose of the present invention is to provide a method for promoting power consumption and consumption of new energy vehicles to solve the problems raised in the above background technology.

[0008] To achieve the above purpose, the present invention provides the following technical solution: A method for promoting power consumption and consumption of new energy vehicles, the method comprising: Step 1, obtain the real-time load data of the target area power grid, extract the historical load fluctuation characteristics, and establish a power grid dynamic load prediction model; Step 2, based on the new energy vehicle user behavior data, statistically analyze the charging demand distribution in different time periods and geographical locations, and generate a charging demand spatio-temporal matrix; Step 3, identify the real-time output data of distributed renewable energy power generation equipment in the target area, and combine the remaining capacity of energy storage equipment to calculate the renewable energy consumption threshold; Step 4, according to the power grid dynamic load prediction model and the charging demand spatio-temporal matrix, construct a multi-objective optimization function, and the objectives of the multi-objective optimization function include power grid load balance, renewable energy utilization rate, and user charging cost; Step 5, based on the consumption threshold and the optimized charging period allocation result, divide the electricity price incentive levels in different time periods, and calculate the dynamic electricity price adjustment coefficient; Step 6, extract the user's historical charging behavior data, analyze the response sensitivity of the user to the dynamic electricity price, and establish a user response probability model; Step 7, according to the user response probability model and the dynamic electricity price adjustment coefficient, generate a differentiated charging guidance instruction, and send it to the user terminal through a communication network.

[0009] Preferably, the method for establishing the power grid dynamic load prediction model in the step 1 is: Divide the historical load data into multiple time periods according to the time series, extract the load characteristic parameters of each time period, including peak load, valley load, and load change gradient; the formula for constructing the load prediction model is:

[0010] Among them, is the predicted load value at time ; is the reference load at time , calculated by the mean of historical data; is the th abnormal load fluctuation amount, extracted by the outlier detection algorithm; , , are the model parameters fitted by machine learning; is the time corresponding to the rd abnormal fluctuation in the historical load data.

[0011] Preferably, the process of generating the charging demand spatio-temporal matrix in step 2 includes: Dividing the target area into multiple grid cells, and counting the charging start time, charging duration and charging power of new energy vehicles in each grid cell; Defining the charging demand spatio-temporal matrix as a three-dimensional tensor , where i represents the longitude partition, j represents the latitude partition, t represents the time slice, and each element value is the total charging demand of the corresponding grid cell in the time slice t.

[0012] Preferably, the method for calculating the renewable energy accommodation threshold in step 3 is: Obtaining the real-time output of distributed renewable energy and the remaining capacity of the energy storage device ; Setting the accommodation threshold as:

[0013] Among them, is the scheduling time interval, is the maximum reverse feed-in power allowed by the power grid.

[0014] Preferably, the specific formula for constructing the multi-objective optimization function in step 4 is:

[0015] Among them, is the net load of the power grid, is the average load, is the charging power allocation value, is the user's charging cost, , , are the weight coefficients, and satisfy .

[0016] Preferably, the calculation process of the dynamic electricity price adjustment coefficient in step 5 includes: According to the absorbable threshold and the charging power distribution value the difference, divide the electricity price incentive level; Set the dynamic electricity price adjustment coefficient as:

[0017] wherein, is the base electricity price, is the preset elasticity coefficient.

[0018] Preferably, the method for establishing the user response probability model in step 6 is as follows: Extract the electricity price sensitivity index and the charging urgency index from the user's historical charging behavior; Define the user response probability as:

[0019] where a, b, and c are coefficients obtained by logistic regression fitting.

[0020] Preferably, the process of generating the differentiated charging guidance instruction in step 7 includes: According to the user response probability divide the user groups, send priority charging instructions to users with high response probability, and send delayed charging suggestions to users with low response probability; The charging guidance instruction includes information on the recommended charging period, estimated cost, and the proportion of renewable energy.

[0021] Preferably, the present invention further includes an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to call the instructions stored in the memory to execute the method for promoting the consumption of electricity by new energy vehicles.

[0022] Preferably, the present invention further includes a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method for promoting the consumption of electricity by new energy vehicles as described above is implemented.

[0023] Compared with the prior art, the beneficial effects of the present invention are: Precisely calculate the absorbable threshold of renewable energy and incorporate it into the multi-objective optimization function and the electricity price incentive mechanism. By identifying the real-time output of distributed renewable energy generation equipment and the remaining capacity of energy storage equipment, the potential for renewable energy consumption can be fully explored.

[0024] A multi-objective optimization function is constructed using a power grid dynamic load prediction model and a charging demand spatio-temporal matrix to effectively regulate the charging behavior of new energy vehicles. The model considers the historical load fluctuation characteristics, accurately predicts the load changes, and optimizes the charging time periods in combination with the charging demand distribution. During peak load periods, the charging load of new energy vehicles is reduced; during low load periods, the charging load is increased. Based on the dynamic electricity price adjustment coefficient and the user response probability model, differential charging guidance is provided for users. Users with high electricity price sensitivity and low charging urgency can obtain charging recommendations preferentially during periods of low electricity prices, saving charging costs. By integrating smart grid technologies and big data analysis technologies, comprehensive monitoring and precise control of the power grid, new energy vehicles, and renewable energy are achieved. Various types of data are obtained in real time, and user behaviors and energy supply and demand laws are deeply analyzed to provide a scientific basis for energy management decisions.

[0025] By reasonably guiding the charging of new energy vehicles, the potential for vehicle-to-grid (V2G) bi-directional interaction is exploited. When the power grid load is tight, new energy vehicles can feed electricity back to the power grid to relieve power shortages; when there is an oversupply of renewable energy generation, excess electrical energy can be stored. This enhances the flexibility and resilience of the power grid, expands the application value of new energy vehicles, and promotes the collaborative innovation and development of the new energy vehicle industry and the power industry.

[0026] Reducing the curtailment of renewable energy, improving energy utilization efficiency, and reducing power generation costs; reducing the investment in power grid upgrade and transformation, alleviating the power supply and demand contradiction, and bringing significant economic benefits. Charging new energy vehicles with large-scale use of renewable energy reduces carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is the working principle diagram of the method for promoting electricity consumption by new energy vehicles according to the present invention; Figure 2 is the construction flow chart of the power grid dynamic load prediction model; Figure 3 is the generation flow chart of the charging demand spatio-temporal matrix. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] Please refer to Figures 1-3 , the present invention provides a method for promoting electricity consumption by new energy vehicles, and its overall implementation solution is as follows: Step 1: Obtain real-time grid load data and establish a prediction model: Interact with the monitoring system of the target area grid to obtain the grid load data in real time. At the same time, extract the load data for a past period (such as one year) from the historical data repository, and divide it into multiple time periods according to the time series. Each time period can be set according to the actual situation, for example, in hours. For each time period, extract load characteristic parameters such as peak load, valley load, and load change gradient.

[0030] Step 2: Statistically generate a spatio-temporal matrix of charging demand: Collect new energy vehicle user behavior data, which can come from the vehicle's on-board system, the operation data of charging piles, and user registration information, etc. Geographically divide the target area into multiple grid cells, and the size of each grid cell is determined according to the actual situation of the area and the data accuracy requirements. For each grid cell, count the charging start time, charging duration, and charging power of new energy vehicles in it. Construct a three-dimensional tensor form of the charging demand spatio-temporal matrix to accurately reflect the total charging demand at different geographical locations and times.

[0031] Step 3: Calculate the renewable energy accommodation threshold: Real-time monitor the output data of distributed renewable energy generation equipment (such as solar photovoltaic panels, wind turbines, etc.) and the remaining capacity of energy storage equipment (such as battery energy storage systems) in the target area. Combine the scheduling time interval and the maximum allowable reverse feed power of the grid to calculate the renewable energy accommodation threshold. This threshold is used to measure the upper limit of the renewable energy electricity that can be accommodated at a specific moment.

[0032] Step 4: Construct a multi-objective optimization function: Based on the grid dynamic load prediction model and the charging demand spatio-temporal matrix obtained above, construct a multi-objective optimization function. In this function, by setting different weight coefficients, balance the relationship among the three objectives of grid load balance, renewable energy utilization rate, and user charging cost to find the optimal charging power allocation scheme.

[0033] Step 5: Divide the electricity price incentive levels and calculate the adjustment coefficient: According to the difference between the renewable energy accommodation threshold and the charging power allocation value, divide the electricity price incentive levels for different time periods according to certain rules. This coefficient will be used to adjust the electricity price for different time periods to encourage users to charge during periods when renewable energy is sufficient and the grid load is low.

[0034] Step 6: Establish a user response probability model: Extract the electricity price sensitivity index and charging urgency index from the user's historical charging behavior data. Use these indexes to fit the correlation coefficient through machine learning methods such as logistic regression to predict the user's response probability to different electricity prices.

[0035] Step 7: Generate and send differential charging guidance instructions: Divide user groups according to the calculation results of the user response probability model. For users with a high response probability, send priority charging instructions; for users with a low response probability, send delayed charging suggestions. These charging guidance instructions are sent to the user terminal through a communication network (such as 4G / 5G network, Wi-Fi, etc.), and the instructions contain recommended charging periods, estimated costs, and the proportion of renewable energy, helping users make reasonable charging decisions.

[0036] The following further illustrates the implementation of the present invention in combination with Embodiments 1 to 5.

[0037] Embodiment 1: The function of this embodiment is to elaborate in detail on how to accurately establish a power grid dynamic load prediction model to improve the accuracy of load prediction and provide a reliable basis for subsequent charging strategy formulation.

[0038] After obtaining the real-time load data and historical load data of the target area power grid, the historical load data is divided into multiple time periods per hour. For each time period, the peak load, valley load, and load change gradient are extracted through a data analysis tool. Assume that the start time of a certain time period is , and the end time is hours. During this time period, through sampling and processing of the power grid monitoring data, the maximum load value within this time period is obtained as the peak load , the minimum load value as the valley load , and the load change gradient is obtained by calculating the ratio of the load change amount to the time within this time period, that is , where represents the power grid load value at time .

[0039] When constructing the load prediction model, the formula is:

[0040] Among them, is the predicted load value at time ; is the reference load at time , which is obtained by calculating the average value of the historical load data in the same time period (such as the same hour every day) as time in the past year. For example, calculate the load average value of 10:00 - 11:00 every day in the past year as the reference load at 10:00 .

[0041] is the An abnormal load fluctuation amount is extracted using an outlier detection algorithm (such as the density-based spatial clustering algorithm DBSCAN). Suppose that in a certain historical load data, 3 abnormal load fluctuation points are found through outlier detection, and the corresponding abnormal load fluctuation amounts are respectively and and , and the corresponding times are respectively and and .

[0042] and and are the model parameters fitted through machine learning. The gradient descent algorithm can be used to optimize these parameters. First, the historical load data is divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the accuracy of the model. During the training process, the values of and and are continuously adjusted to minimize the error (such as the mean square error) between the predicted load value and the actual load value. After multiple iterative calculations, the optimal model parameter values are obtained.

[0043] The power grid dynamic load prediction model established in this way can fully consider the normal trends and abnormal fluctuations in historical load data, improve the accuracy of load prediction, and provide accurate data support for subsequent optimization of power resource allocation.

[0044] Example 2: The function of this example is to elaborate in detail how to generate a spatio-temporal matrix of charging demand to more accurately grasp the charging demand of new energy vehicles in different spatio-temporal areas and provide a basis for optimizing charging strategies.

[0045] Taking a certain urban area as the target area, according to factors such as the geographical scope and traffic flow of the city, the area is divided into grid cells, and the side length of each grid cell can be set to 1 kilometer according to the actual situation. By docking with the operation platform of new energy vehicle charging piles, vehicle management systems, etc., the charging start time, charging duration, and charging power data of new energy vehicles in each grid cell are obtained.

[0046] Suppose that in a certain grid cell , within the time slice (the time slice can be set to one every 30 minutes), multiple new energy vehicles are charging. For one of the vehicles, the charging start time is , the charging duration is , and the charging power is . If Within a time slice and is also within the time slice , then the total charging demand of this vehicle within this time slice is . If is before the time slice but partially within the time slice , assuming the charging duration within the time slice is , then the total charging demand is .

[0047] Define the spatio-temporal matrix of charging demand as a three-dimensional tensor , where represents the longitude partition, represents the latitude partition, represents the time slice. For example, at a certain moment, in the grid cell with longitude partition 3 and latitude partition 5 within the time slice , there are multiple vehicles charging. After statistical calculation, the total charging demand of this grid cell within this time slice is kWh, then .

[0048] The spatio-temporal matrix of charging demand generated in this way can intuitively reflect the charging demand distribution of new energy vehicles at different geographical locations and times, providing a detailed data basis for subsequent multi-objective optimization and charging strategy formulation.

[0049] Example 3: The function of this example is to elaborate in detail the calculation process of the renewable energy accommodation threshold to reasonably determine the accommodable renewable energy electricity under the premise of considering grid safety and energy storage capacity.

[0050] In the target area, distributed renewable energy generation equipment (such as solar photovoltaic power stations, wind farms, etc.) monitors its own output data in real time through sensors , and energy storage equipment (such as large-scale battery energy storage systems) also feeds back its remaining capacity in real time . Assume that the scheduling time interval is set to 1 hour, and the maximum allowable reverse feed power of the grid is .

[0051] The formula for calculating the renewable energy accommodation threshold is:

[0052] For example, at a certain moment , the real-time output of a distributed solar photovoltaic power station in a certain area is , and the remaining capacity of the energy storage equipment supporting this area is , scheduling time interval hours, maximum reverse feed-in power allowed by the power grid .

[0053] First, calculate , then compare it with , and take the smaller value. Therefore, at moment, the renewable energy accommodation threshold in this area is .

[0054] Through such a calculation method, it is possible to comprehensively consider the real-time output of renewable energy generation equipment, the remaining capacity of energy storage equipment, and the safety limits of the power grid, accurately calculate the upper limit of the renewable energy electricity that can be accommodated at each moment, and provide an important reference basis for the subsequent optimal allocation of power resources.

[0055] Embodiment 4: The function of this embodiment is to explain in detail the construction process of the multi-objective optimization function and the meaning of each parameter, so as to achieve the comprehensive optimization of the power grid load balance degree, renewable energy utilization rate, and user charging cost.

[0056] According to the power grid dynamic load prediction model, the net load of the power grid is obtained , and the average load is obtained by statistically calculating the power grid load data over a period of time (such as one day) . In terms of charging power distribution, the charging power distribution value is determined according to the charging demand spatio-temporal matrix and the optimization algorithm , while considering the charging cost of users at different times .

[0057] The formula for constructing the multi-objective optimization function is:

[0058] Among them, , , are weight coefficients, and satisfy .

[0059] Assume that in a certain optimization scenario, the weight coefficients are set as , , . Within 24 hours of a day, the net load of the power grid for each hour is obtained through the power grid dynamic load prediction model , and the average load of this day is calculated . According to the charging demand spatio-temporal matrix and the optimization algorithm, the charging power distribution value for each hour is determined , and at the same time, the user charging cost is calculated according to the electricity price at different times .

[0060] For the grid load balance part, calculate , for example, at , , , then the value of this item is ; at , , then the value of this item is , and so on, calculate the sum of this item for 24 hours.

[0061] For the renewable energy utilization rate part, first calculate and , assuming , , then the value of this item is .

[0062] For the user charging cost part, calculate , assuming that the total user charging cost for this day is obtained through calculation as yuan, then the value of this item is .

[0063] Add the values of these three parts to obtain the value of the multi-objective optimization function . By continuously adjusting the charging power distribution value , make the value minimum, so as to realize the comprehensive optimization of grid load balance, renewable energy utilization rate and user charging cost.

[0064] Example 5: This example aims to elaborate in detail how to adjust the electricity price according to the relationship between the absorbable threshold and the charging power distribution value, construct a user response probability model, and generate targeted charging guidance instructions based on this to guide users to reasonably arrange their charging behaviors and improve the power utilization efficiency.

[0065] In terms of calculating the dynamic electricity price adjustment coefficient, divide it into three electricity price incentive levels according to the difference between the absorbable threshold and the charging power distribution value . When the difference is greater than 50kW, it is a high incentive level; when it is between 20kW (inclusive) and 50kW, it is a medium incentive level; when the difference is less than or equal to 20kW, it belongs to a low incentive level.

[0066] Taking a certain area as an example, set the benchmark electricity price as 0.6 yuan / kWh, and preset the elasticity coefficient as 0.7. At 16:00, the absorbable threshold of this area is 300kW, and the charging power distribution value is 230 kW, and the difference between the two is 70 kW, which is at a high incentive level. According to the formula calculate, the dynamic electricity price adjustment coefficient yuan / kWh. Compared with the benchmark electricity price, the electricity price during this period has increased, aiming to encourage more users to charge during the period when the renewable energy consumption space is larger.

[0067] When establishing the user response probability model, key indicators are extracted from the user's historical charging data. For example, when the electricity price of user A decreased by 15% in the past, the charging power increased by 25%, so it is judged that its electricity price sensitivity is relatively high; if the user often charges only when the power is less than 30%, it indicates a relatively high charging urgency. Through logistic regression analysis of a large amount of user data, determine the coefficients 、 、 .

[0068] For user A, assume that its electricity price sensitivity index is 0.7, and the charging urgency index is 0.6. At 16:00, the dynamic electricity price adjustment coefficient is 0.72. According to the formula , calculate its response probability .

[0069] Group users according to the response probability. Set the response probability greater than 0.7 as high-response-probability users, and less than 0.5 as low-response-probability users. For high-response-probability users like user A, the system sends a priority charging instruction, recommends the charging period from 16:00 to 18:00, and informs the estimated cost as 0.72 yuan / kWh multiplied by the estimated charging amount (assuming the estimated charging amount is 40 kWh, the estimated cost is 28.8 yuan). At the same time, it shows that the proportion of renewable energy in this period reaches 70%. For low-response-probability users, the system sends a delayed charging suggestion, recommending charging from 22:00 to 0:00. At this time, the electricity price may be lower due to different incentive levels, and the proportion of renewable energy is also relatively considerable, guiding users to charge during off-peak hours to balance the grid load.

[0070] It should be noted that in this article, relational terms such as first and second 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 term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0071] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for promoting electricity consumption and absorption in new energy vehicles, characterized in that, The method includes: Step 1: Obtain the real-time load data of the power grid in the target area, extract the historical load fluctuation characteristics, and establish a power grid dynamic load prediction model; Step 2: Based on the user behavior data of new energy vehicles, statistically analyze the charging demand distribution in different time periods and geographical locations, and generate a spatio-temporal matrix of charging demand; Step 3: Identify the real-time output data of distributed renewable energy generation equipment in the target area, and combine with the remaining capacity of energy storage equipment to calculate the renewable energy consumable threshold; Step 4: According to the power grid dynamic load prediction model and the spatio-temporal matrix of charging demand, construct a multi-objective optimization function, and the objectives of the multi-objective optimization function include the power grid load balance degree, the utilization rate of renewable energy, and the user charging cost; Step 5: Based on the consumable threshold and the optimized charging time period allocation result, divide the electricity price incentive levels in different time periods, and calculate the dynamic electricity price adjustment coefficient; Step 6: Extract the user's historical charging behavior data, analyze the response sensitivity of the user to the dynamic electricity price, and establish a user response probability model; Step 7: According to the user response probability model and the dynamic electricity price adjustment coefficient, generate a differentiated charging guidance instruction, and send it to the user terminal through the communication network.

2. The method for promoting electricity consumption by new energy vehicles according to claim 1, wherein The method for establishing the power grid dynamic load prediction model in Step 1 is: Divide the historical load data into multiple time periods according to the time series, and extract the load characteristic parameters of each period, including peak load, valley load and load change gradient; the formula for constructing the load prediction model is: Among them, is the predicted load value at time ; is the reference load at time , calculated by the mean value of historical data; is the th abnormal load fluctuation amount, extracted by the outlier detection algorithm; , , are the model parameters fitted by machine learning; is the moment corresponding to the th abnormal fluctuation in the historical load data.

3. The method for promoting power consumption by new energy vehicles according to claim 2, wherein The process of generating the spatio-temporal matrix of charging demand in Step 2 includes: Divide the target area into multiple grid cells, and statistically analyze the charging start time, charging duration, and charging power of new energy vehicles in each grid cell; Define the spatio-temporal matrix of charging demand as a three-dimensional tensor , where i represents the longitude partition, j represents the latitude partition, and t represents the time slice. The value of each element is the total charging demand of the corresponding grid cell within the time slice t.

4. The method for promoting electricity consumption by new energy vehicles according to claim 3, characterized in that The method for calculating the renewable energy consumable threshold in Step 3 is: Obtain the real-time output of distributed renewable energy and the remaining capacity of energy storage devices ; Set the consumable threshold as: Among them, is the scheduling time interval, is the maximum reverse feeding power allowed by the power grid.

5. The method for promoting power consumption by new energy vehicles according to claim 4, characterized in that, The specific formula for constructing the multi-objective optimization function in Step 4 is: Among them, is the net load of the power grid, is the average load, is the charging power distribution value, is the user's charging cost, , , are weight coefficients and satisfy .

6. The method for promoting electricity consumption in new energy vehicles according to claim 5, characterized in that, The calculation process of the dynamic electricity price adjustment coefficient in Step 5 includes: According to the absorbable threshold and the difference from the charging power distribution value to divide the electricity price incentive levels; Set the dynamic electricity price adjustment coefficient as: Among them, is the benchmark electricity price, is the preset elasticity coefficient.

7. The method for promoting power consumption by new energy vehicles according to claim 6, wherein The method for establishing the user response probability model in Step 6 is: Extract the electricity price sensitivity index and charging urgency index from the user's historical charging behavior and the charging urgency index ; Define the user response probability as: Among them, a, b, and c are coefficients fitted by logistic regression.

8. The method for promoting electricity consumption in new energy vehicles according to claim 7, wherein The process of generating the differentiated charging guidance instruction in Step 7 includes: According to the user response probability Divide the user groups, send a priority charging instruction to users with a high response probability, and send a delayed charging suggestion to users with a low response probability; The charging guidance instruction includes recommended charging time periods, estimated costs, and renewable energy proportion information.

9. An electronic device, characterized in that, Includes: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

Images