Power grid load adjustment method, device, storage medium and computer equipment

Abstract

The present invention discloses a method, device, storage medium and computer equipment for regulating power grid load, which relates to the technical field of load regulation, and is mainly capable of reducing power supply costs and improving the efficiency of power grid load regulation. The method includes: in response to a load regulation signal of a target power grid, obtaining load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in the power supply area corresponding to the target power grid; based on the load regulation demand information and the power station attribute information, determining a target load aggregator charging station that meets the load regulation conditions among each load aggregator charging station; based on the load regulation demand information, using each electric vehicle in the target load aggregator charging station to load regulate the target power grid. The present invention is suitable for regulating power grid load.

Description

Technical Field

[0001] The present invention relates to the technical field of load regulation, and in particular to a method, device, storage medium and computer equipment for regulating power grid load. Background Art

[0002] Since the power generation of the power grid is characterized by the fact that power generation, power supply and power consumption are completed simultaneously and cannot be stored in large quantities, and various types of power loads have their own inherent power consumption time characteristics, thus forming peaks and troughs in power consumption in the power grid system, making it impossible to fully utilize the power generation and power supply equipment or resulting in power shortages. Based on this, in order to ensure the reliability of power supply, it is necessary to adjust the load of the power grid system.

[0003] At present, the load regulation of the power grid system is usually achieved by adjusting the output of the power grid generator sets. However, this regulation method will increase the power supply cost by adding generator sets when the power demand increases, and will notify the staff to remove some generator sets when the power demand decreases, which will waste the staff's time and reduce the efficiency of power grid load regulation. Summary of the invention

[0004] The present invention provides a method, device, storage medium and computer equipment for regulating power grid load, which are mainly capable of reducing power supply costs and improving the efficiency of power grid load regulation.

[0005] According to a first aspect of the present invention, there is provided a method for regulating a power grid load, comprising:

[0006] In response to a load regulation signal of a target power grid, obtaining load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid;

[0007] Based on the load regulation demand information and the power station attribute information, determining a target load aggregator charging station that meets the load regulation condition among the load aggregator charging stations;

[0008] Based on the load regulation demand information, the target power grid is load regulated by using each electric vehicle in the target load aggregator charging station.

[0009] According to a second aspect of the present invention, there is provided a power grid load regulating device, comprising:

[0010] An acquisition unit, configured to acquire, in response to a load regulation signal of a target power grid, load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid;

[0011] A determination unit, configured to determine a target load aggregator charging station that meets a load regulation condition among the load aggregator charging stations based on the load regulation demand information and the power station attribute information;

[0012] The regulating unit is used to perform load regulation on the target power grid by utilizing each electric vehicle in the charging station of the target load aggregator based on the load regulation demand information.

[0013] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which implements the above power grid load regulation method when executed by a processor.

[0014] According to a fourth aspect of the present invention, there is provided a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above power grid load regulation method when executing the program.

[0015] According to a power grid load regulation method, device, storage medium and computer equipment provided by the present invention, compared with the current way of achieving load regulation of the power grid system by adjusting the output of the power grid generator set, the present invention obtains the load regulation demand information of the target power grid and the power station attribute information of each load aggregator charging station in the power supply area corresponding to the target power grid by responding to the load regulation signal of the target power grid; and based on the load regulation demand information and the power station attribute information, determines the target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations; finally, based on the load regulation demand information, uses each electric vehicle in the target load aggregator charging station to load regulate the target power grid. Therefore, by comprehensively analyzing the grid's regulation demand information and the power station attribute information of each load aggregator charging station, a target load aggregator charging station that can meet the load regulation conditions is selected, and finally the grid load is regulated by using each electric vehicle in the target load aggregator charging station. This can avoid increasing the power supply cost wasted by the generator set, and also avoid reducing the time wasted by the generator set. Therefore, the present invention can reduce the power supply cost and improve the grid load regulation efficiency. At the same time, since electric vehicles have strong regulation elasticity and regulation capacity, they are suitable for participating in the dispatch of the grid. Therefore, the present invention can improve the regulation effect of the grid load by using electric vehicles to participate in the grid load regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 A flow chart of a method for regulating power grid load provided by an embodiment of the present invention is shown;

[0018] Figure 2 A probability distribution curve diagram of daily mileage of an electric vehicle provided by an embodiment of the present invention is shown;

[0019] Figure 3 A probability distribution curve diagram of the charging start time of an electric private car provided by an embodiment of the present invention is shown;

[0020] Figure 4 A charging load curve diagram of an electric private car provided by an embodiment of the present invention is shown;

[0021] Figure 5 A curve diagram of disorderly charging load of electric vehicles and original load of power grid provided by an embodiment of the present invention is shown;

[0022] Figure 6 A load curve diagram of an electric vehicle under different electricity price systems provided by an embodiment of the present invention is shown;

[0023] Figure 7 A flow chart of another method for regulating power grid load provided by an embodiment of the present invention is shown;

[0024] Figure 8 A schematic diagram of the structure of a power grid load regulating device provided by an embodiment of the present invention is shown;

[0025] Fig. 9 A schematic structural diagram of another power grid load regulating device provided by an embodiment of the present invention is shown;

[0026] Fig.10 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0028] At present, the load regulation of the power grid system is achieved by adjusting the output of the power grid generator sets. When the electricity demand increases, the generator sets will be added, which will increase the power supply cost. When the electricity demand decreases, the staff will be notified to remove some generator sets, which will consume the staff's time and reduce the efficiency of the power grid load regulation.

[0029] In order to solve the above problems, an embodiment of the present invention provides a method for adjusting power grid load, such as Figure 1 As shown, the method includes:

[0030] 101. In response to a load regulation signal of a target power grid, obtain load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid.

[0031] Among them, the load regulation demand information includes: the load regulation amount corresponding to the target power grid, the load regulation method information, the power grid location information, etc., and the load regulation method information includes: peak-shifting charging regulation method, reverse power supply regulation method, etc.; the power station attribute information includes: the number of charging piles in each load aggregator charging station, the charging pile type information, the regional location information, etc.; the power supply area can be based on provinces or cities, and the embodiment of the present invention does not specifically limit the division of power supply areas; the load aggregator is the entity that uniformly operates and controls various response resources in a certain area, and aggregates the charging load of electric vehicles through charging stations where electric vehicle charging piles are concentrated to form load aggregator charging stations.

[0032] For the embodiment of the present invention, since electric vehicles are a large-capacity adjustable load with outstanding advantages such as large adjustment capacity, high adjustment flexibility, and the ability to achieve two-way interaction of charging and discharging with the power grid, the embodiment of the present invention uses electric vehicles to adjust the load of the power grid. Specifically, when it is determined that the target power grid will have a power supply peak or a power supply valley in the next period of time, a load adjustment signal needs to be triggered. When the load adjustment system receives the load adjustment signal, it will obtain the load adjustment demand information of the target power grid and the power station attribute information of each load aggregator charging station in the power supply area corresponding to the target power grid in real time, and select the target load aggregator charging station that meets the load adjustment conditions from each load aggregator charging station based on the above information, and finally use each electric vehicle in the target load aggregator charging station to load adjust the target power grid. Therefore, a target load aggregator charging station that meets the load regulation conditions is selected by comprehensively analyzing the load regulation demand information of the target power grid and the power station attribute information of the load aggregator charging station, and finally the load regulation of the target power grid is realized by using the electric vehicles in the target load aggregator charging station. This can improve the regulation effect of the power grid load, avoid losses caused by power outages during peak periods of electricity demand, and avoid the problem of wasting power supply resources during periods of low electricity demand. Therefore, the embodiment of the present invention can save power supply resources and ensure continuous and stable power supply to the power grid.

[0033] 102. Based on the load regulation demand information and the power station attribute information, determine a target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations.

[0034] For the embodiment of the present invention, after obtaining the load regulation demand information of the target power grid and the power station attribute information of each load aggregator charging station, the target load aggregator charging station that meets the load regulation demand is determined among the various load aggregator charging stations through the load regulation demand information and the power station attribute information, and finally the load regulation of the target power grid is realized by using the various electric vehicles in the target load aggregator charging station. For example, if the target power grid will have a power supply peak period in a certain period of time in the future, then at this time, it is necessary to adopt corresponding strategies to reduce the charging of various electric vehicles in the target load aggregator charging station during the power supply peak period, so as to avoid the target power grid being damaged due to the large power load during the power supply peak period; if the target power grid will have a power supply valley period in a certain period of time in the future, then at this time, the corresponding strategy can be adopted to encourage the various electric vehicles in the target load aggregator charging station to charge during the power supply valley period, so as to avoid the waste of power supply resources of the target power grid.

[0035] 103. Based on the load regulation demand information, the target power grid is load regulated by using each electric vehicle in the charging station of the target load aggregator.

[0036] For the embodiment of the present invention, electric vehicles are divided into electric private cars, electric taxis, electric buses and electric official vehicles according to usage needs, and the behavior characteristics of electric vehicles are analyzed from the aspects of the charging mode, daily mileage, charging start time, battery SOC (state of charge) state, etc. Since electric private cars and electric official vehicles have a short daily mileage, they are usually charged once a day or once every two days. And since the charging location of electric private cars and electric official vehicles is usually the workplace or residence, the charging method used is generally conventional charging. Since electric taxis and electric buses have a long daily mileage and are concentrated in daytime operations, they usually use a fast charging method to replenish the power once during the day. After returning to the parking point for a rest after the operation, they will use a conventional charging method to fully charge the power during the night when they are not in operation. The daily mileage of electric vehicles is the main determinant of their daily power consumption. The daily mileage of electric private cars and electric official cars is relatively short, for example, usually between 20 kilometers and 40 kilometers; the daily mileage of electric buses and electric taxis is relatively long, between 200 kilometers and 300 kilometers and 300 kilometers and 400 kilometers respectively, and the daily mileage of various types of electric vehicles obeys the normal distribution. By analyzing and fitting the daily mileage data of a large number of electric vehicles, it is concluded that the daily mileage of electric vehicles satisfies the normal distribution, and its probability density function is as follows:

[0037]

[0038]

[0039] Where x is the daily mileage of the electric vehicle, D x 、E x are the variance and standard deviation of the normal distribution, σ D , μ D are the standard deviation and average value of lnx, and Table 1 shows the standard deviation and average value of lnx of various electric vehicles.

[0040] Table 1 Standard deviation and mean value of lnx of various electric vehicles

[0041] type Electric private car Electric taxi Electric Bus Electric business car <![CDATA[σ D ]]> 0.88 0.35 0.35 0.88 <![CDATA[μ D ]]> 3.2 5.1 4.4 3.5

[0042] The charging locations for electric private cars are mainly charging piles at residences and workplaces. The charging time is usually to charge at the charging piles at the workplace after arriving at the workplace in the morning and to charge at the charging piles at the residence after returning to the residence in the afternoon. For example, since the departure time of electric private cars is generally 7:00-9:00 on the same day and the return time is 17:00-19:00 on the same day, the charging time of electric private cars is concentrated between 19:00-6:00 and 10:00 on the same day. The charging location and charging time of electric taxis are relatively more random. Usually, they choose to charge near the resting place during rest time and return to the residence to charge after the trip. Electric taxis usually finish their trips late. Referring to the data survey of Shanghai taxis, for example, the rest time of electric taxis is generally 2:00-4:00 at night and 11:00-14:00 in the afternoon, so the charging time of electric taxis basically coincides with these two time periods. The charging time of electric buses is mainly considered to avoid the rush hours on weekdays in cities. For example, the morning rush hour on weekdays is usually 6:30-9:30 on the same day, and the rush hour after work is 16:30-19:30 on the same day. The rest time of electric buses after the end of the trip is usually 23:00-6:00 on the same day. Therefore, the charging time of electric buses is concentrated between 10:00-16:00 and 24:00-5:00 on the same day. Electric official vehicles are usually in standby or working state during daytime work and are generally not charged. Therefore, the charging time of electric official vehicles is concentrated between 18:00-7:00 on the same day after the end of daytime work. The SOC state of an electric vehicle battery is numerically defined as the percentage of the current battery power to the total battery capacity, which is usually referred to as the battery's state of charge. The SOC state of an electric vehicle battery is mainly determined by the daily mileage and power consumption per kilometer of the electric vehicle, as shown in the following formula:

[0043]

[0044] In the above formula, SOC i is the i-th state of charge of the electric vehicle battery, SOC i-1is the i-1th state of charge of the electric vehicle battery, that is, the battery state of charge of the electric vehicle after the last charge, d is the mileage of the electric vehicle between two charges, E is the power consumption per kilometer of the electric vehicle battery, and B is the total capacity of the electric vehicle battery. Usually after charging is completed, the SOC state or initial power of the electric vehicle satisfies the normal distribution. According to the above overall analysis of the behavior characteristics of electric vehicles, since electric private cars account for the largest proportion of electric vehicles, according to relevant statistics, the average daily driving time of electric private cars is 1-2 hours, and more than 90% of the time throughout the year is in a non-driving state, that is, parked at a parking spot. Therefore, electric private cars have strong adjustment flexibility and adjustment capacity, and are suitable for participating in the dispatch of the power grid; electric taxis and electric buses are in operation most of the day. Through the analysis of the behavior characteristics of electric taxis and electric buses, it can be seen that the adjustable range of their charging time is small, and it is not easy to participate in the energy dispatch of the power grid, and they are generally concentrated after midnight to before six in the morning. The charging time also avoids the peak of the power grid load; the number of electric official cars is the smallest among the four types of electric vehicles, and their behavior characteristics are similar to those of electric private cars. The impact of their charging load on the power grid can be ignored, or they can be combined with electric private cars for calculation. In summary, when considering electric vehicles as adjustable loads to participate in the demand-side power grid regulation, the orderly dispatch optimization of the charging load of the power grid can be achieved mainly through electric private cars. Furthermore, from the above analysis of the daily mileage of electric private cars in the behavior characteristics of electric vehicles, it can be seen that the daily mileage of electric private cars is usually concentrated between 20 kilometers and 40 kilometers, and the daily mileage of electric private cars meets the normal distribution in probability statistics. By fitting and analyzing the daily mileage of electric vehicles through matlab (commercial digital software), the probability distribution curve of the daily mileage of electric private cars (electric vehicles) can be obtained as follows: Figure 2 As shown. Through the analysis of the charging start time of electric private cars in the behavior characteristics of electric vehicles, it can be seen that since the charging locations of electric private cars in daily life are mainly charging piles at residences and workplaces, the charging time of electric private cars is concentrated between 19:00-6:00 and 10:00-16:00 every day. The charging start time of electric private cars meets the piecewise normal distribution in probability statistics. Through matlab fitting analysis of the charging start time of electric private cars, the probability distribution curve of the charging start time of electric private cars can be obtained as shown below Figure 3 Through the analysis of the behavior characteristics of electric private cars, it can be seen that if the parameters of electric private cars are set as shown in Table 2 below.

[0045] Table 2 Parameter settings of electric private cars

[0046]

[0047]

[0048] Applying the Monte Carlo method, according to the above parameters, using matlab (matrix&laboratory, commercial digital software) to simulate and analyze the charging load model of electric private cars in disordered charging mode, its charging load curve can be obtained. Figure 4 As shown. Figure 4 It can be seen that as the number of electric private cars increases, the peak value and peak-to-valley difference of the electric private car charging load also increase. In order to compare the electric private car charging load curve with the original daily load curve of the power grid, the embodiment of the present invention plots the original daily load curve of the power grid without electric vehicles, the total load curve with the charging load of 200 electric vehicles, and the total load curve with the charging load of 300 electric vehicles in one load curve diagram, as shown in FIG. Figure 5 As shown, the peak values, valley values, peak-to-valley differences and peak-to-valley difference rates of the three loads are statistically shown in Table 3 below.

[0049] Table 3 Load parameters of electric vehicles and original loads

[0050] Load composition Peak value (kW) Valley value (kW) Peak-to-valley difference (kW) Peak-to-valley difference rate (%) Original load 4034.5 1876.2 2158.3 53.4961 200EV+Original load 4211.2 1887 2324.2 55.1898 300EV+Original load 4396.5 1896.3 2500.2 55.8627

[0051] Depend on Figure 5 As shown in Table 3, the peaks of the charging load curve of electric vehicles and the original daily load curve of the power grid both appear at 19:00-21:00 every day. When electric vehicles are charged in an unordered manner, the peak of the charging load of electric vehicles almost coincides with the peak of the original daily load of the power grid, which will cause the load of the power grid to "peak on peak", thereby increasing the burden on the power system during peak hours. It can be determined that private electric cars are crucial to the load regulation of the power grid. Furthermore, with the minimum peak-to-valley difference of the power grid load after adding the charging load of electric vehicles and the minimum charging cost of electric vehicles as the objective function, and the battery capacity, power balance, charging and discharging power and charging and discharging state of electric vehicles as constraints, the wolf pack algorithm is used to use matlab to establish the charging load model of electric vehicles under the orderly charging mode. The wolf pack algorithm is a group search algorithm based on random probability. The algorithm simulates the hunting behavior of wolves and the distribution of prey. It simulates the hunting behavior, attack behavior and competition update of wolves through the model. It can find the optimal solution to the problem in the solution space in a short time. It has fine search capabilities in both local and global solution spaces and is suitable for solving various nonlinear optimization problems. Before establishing the model, the embodiment of the present invention makes the following assumptions about electric private cars:

[0052] (1) The battery capacity of the electric private car is constant, and the charging power is kept constant during charging, ignoring the impact of external factors on the charging process of the electric vehicle;

[0053] (2) All private electric vehicles participating in grid dispatching use conventional charging methods and can participate in grid dispatching 24 hours a day;

[0054] (3) The embodiment of the present invention mainly considers the optimization of charging power and charging time. Based on the above assumptions, the parameters of the electric private car are set as shown in Table 4 below:

[0055] Table 4 Parameter settings of electric private cars

[0056] Parameter Type Setting Value Battery capacity (kW·h) 30 Charging power (kW) 5 Average speed (km / h) 40 Average power consumption per kilometer (kW·h / km) 0.2 Charging efficiency 0.9

[0057] The objective function is to minimize the peak-to-valley difference of the grid load after connecting to the charging load of electric private cars as follows:

[0058]

[0059] Among them, P L，t represents the original daily load of the power grid at time t, P EV,T represents the maximum load at time t, P avg represents the average load at time t, P EVC (i, t), P EVD (i, t) represent the charging power and discharging power of the i-th electric private car at time t respectively; μ EVC (i, t), μ EVD (i, t) represent the charging state and discharging state of the i-th electric private car at time t, which can be 0 or 1; N EV is the number of private electric cars; since a day is divided into 24 hours, t is 1, 2, 3, ..., 24. The objective function is to minimize the charging cost of electric vehicles under the time-of-use electricity price policy as follows:

[0060]

[0061] Among them, C EVC (i, t), C EVD (i, t) represent the charging price and discharging price respectively; Δt represents the time interval is 1. The constraints of the power balance of electric private cars are as follows:

[0062] S soc (i,t+1)=S soc (i,t)+[μ EVC (i,t)P EVC (i,t)η EVC (i) -μ EVD (i,t)P EVD (i,t) / η EVD (i)]ΔT / E EV (i)

[0063] Among them, Ssoc (i, t) is the battery SOC state of the i-th electric vehicle at time t, S soc (i, t+1) is the battery SOC state of the i-th electric vehicle at time t+1, E EV (i) represents the total battery capacity of the i-th electric private car; η EVC (i) represents the charging efficiency of the i-th electric private car, η EVD (i) represents the discharge efficiency of the i-th electric private car. In this paper, the charging efficiency and discharge efficiency of electric private cars are both taken as 0.9; μ EVC (i,t),μ EVD (i, t) represents the charging state and discharging state of the i-th electric car at time t, ΔT represents the time interval. If a total of 1,000 electric cars can participate in charging through load aggregators, and 300 electric cars respond to the incentive policy of time-of-use electricity prices, the original charging load of the power grid, the charging load under time-of-use electricity prices, and the charging load under fixed electricity prices are plotted by applying the wolf pack algorithm in matlab, and the optimization results of time-of-use electricity prices and fixed electricity prices are compared, as shown in the figure. Figure 6 ,Depend on Figure 6 It can be seen that when time-of-use electricity prices and fixed electricity prices are adopted, the charging load of electric private cars plays a role in shaving peaks and filling valleys on the original load. Among them, after adopting time-of-use electricity prices, the peak-to-valley difference of the power grid load is smaller, the user cost is lower, and the charging load absorbs more electrical energy. Therefore, electric private cars have a better load regulation effect on the power grid.

[0064] Furthermore, each electric vehicle in the target load aggregator charging station has a load regulating effect on the target power grid, but electric private cars have the best effect in load regulating the power grid. The embodiment of the present invention can use the electric private vehicles in the target load aggregator charging station to load regulate the target power grid according to the load regulation demand information, thereby improving the load regulation effect of the power grid, avoiding the increased power generation cost by adding generator sets during peak power consumption, and avoiding the time and manpower wasted by manually removing some generator sets during low power consumption. Therefore, the embodiment of the present invention can save power supply costs and improve the load regulation efficiency of the power grid.

[0065] Furthermore, a target category electric vehicle with the best grid load regulation effect can be selected from various electric vehicles in the following manner: historical daily mileage information, historical charging time information, battery attribute information, historical charging mode information, and historical daily charging times information of different types of electric vehicles in the power supply area are obtained; the historical daily mileage information, historical charging time information, battery attribute information, historical charging mode information, and historical daily charging times information of various electric vehicles are respectively input into a preset regulation elasticity analysis model for regulation elasticity analysis to obtain regulation elasticity scores of various electric vehicles for the target grid; based on the regulation elasticity scores, target category electric vehicles that meet the grid load regulation requirements are determined from various electric vehicles; based on the load regulation demand information, the target grid is load regulated using each target category electric vehicle in the target load aggregator charging station.

[0066] Among them, the battery attribute information refers to the capacity, voltage and other information of the battery of the electric vehicle, and the charging mode information refers to the fast charging, slow charging and other modes. Specifically, in order to improve the selection accuracy of the target category vehicle, it is necessary to pre-build and train the preset adjustment elasticity analysis model, and the specific training and construction method is: build at least one preset initial model; obtain sample data of different types of sample electric vehicles, wherein the sample data includes: sample daily mileage information, sample charging time information, sample battery attribute information, sample charging mode information, sample daily charging times information, and actual adjustment elasticity score; based on the number of models of the preset initial model, divide the above sample data into multiple groups of training data and multiple groups of test data; use each group of training data to train the corresponding preset initial model to obtain the trained preset initial model, wherein during training, the sample daily mileage information, sample charging time information, sample battery attribute information, sample charging mode information, and sample daily charging times information are used as input data, and the actual adjustment elasticity score is used as output data; use each group of test data to test the corresponding trained preset initial model to obtain the prediction accuracy corresponding to each preset initial model; finally select the preset initial model with the largest preset accuracy as the preset adjustment elasticity analysis model. Furthermore, the historical daily mileage information, historical charging time information, battery attribute information, historical charging mode information, and historical daily charging times information of various electric vehicles are respectively input into a preset regulation elasticity analysis model for regulation elasticity analysis to obtain the regulation elasticity scores of various electric vehicles for the target power grid. Then, the maximum regulation elasticity score is selected from each regulation elasticity score, and the type of electric vehicle corresponding to the maximum regulation elasticity score is determined as the target category electric vehicle. Finally, based on the load regulation demand information, the target category electric vehicles in the target load aggregator charging station are used to load regulate the target power grid. Therefore, by selecting the category of vehicles with the best load regulation effect to load regulate the power grid, the stable operation of the power grid can be guaranteed.

[0067] In another embodiment of the present invention, electric vehicles can also be used to participate in cross-provincial calls through load aggregator charging stations, thereby realizing load regulation of cross-provincial power grids. When electric vehicles participate in cross-provincial calls of adjustable load resources, the provinces can be divided into regions: for example, the regional level division of load aggregator charging stations in East China can be carried out, and the inner ring areas of cities such as Shanghai, Nanjing, Hangzhou, Hefei, Fuzhou, Suzhou, Wuxi, Ningbo, etc. can be set as Class I areas, the outer ring areas, industrial areas and development zones can be set as Class II areas, and other areas except the above areas can be set as Class III areas. After the regional level division of load aggregator charging stations in East China is carried out, different load aggregator charging station scales and types can be used according to the regional level to connect the electric vehicle charging load in the region to the power grid, and then unified scheduling and control can be carried out according to the regional level. For example, when the target power grid in Province A needs to be load regulated, the load aggregator charging station in Province B that meets the load regulation conditions can be selected according to the corresponding information, and the load aggregator charging station in Province B can be connected to the target power grid in Province A, thereby realizing load regulation of the target power grid in Province A through electric vehicles of various target categories in the target load aggregator charging station in Province B. Through the cross-provincial calling of electric vehicles, the load regulation of the power grid can be made more flexible and have a wider scope of application.

[0068] According to a method for regulating power grid load provided by the present invention, compared with the current way of achieving load regulation of the power grid system by adjusting the output of the power grid generator set, the present invention obtains the load regulation demand information of the target power grid and the power station attribute information of each load aggregator charging station in the power supply area corresponding to the target power grid by responding to the load regulation signal of the target power grid; and based on the load regulation demand information and the power station attribute information, determines the target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations; finally, based on the load regulation demand information, uses each electric vehicle in the target load aggregator charging station to load regulate the target power grid. Therefore, by comprehensively analyzing the grid's regulation demand information and the power station attribute information of each load aggregator charging station, a target load aggregator charging station that can meet the load regulation conditions is selected, and finally the grid load is regulated by using each electric vehicle in the target load aggregator charging station. This can avoid increasing the power supply cost wasted by the generator set, and also avoid reducing the time wasted by the generator set. Therefore, the present invention can reduce the power supply cost and improve the grid load regulation efficiency. At the same time, since electric vehicles have strong regulation elasticity and regulation capacity, they are suitable for participating in the dispatch of the grid. Therefore, the present invention can improve the regulation effect of the grid load by using electric vehicles to participate in the grid load regulation.

[0069] Further, in order to better illustrate the above process of adjusting the power grid load, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another method for adjusting the power grid load, such as Figure 7 As shown, the method includes:

[0070] 201. In response to a load regulation signal of a target power grid, obtain load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid.

[0071] Specifically, as a large-capacity adjustable load, electric vehicles have outstanding advantages such as large adjustment capacity, high adjustment flexibility, and the ability to achieve two-way interaction between charging and discharging with the power grid. Since electric vehicles interact with the power grid and participate in the regulation of the power grid load through charging piles, it is time-consuming and labor-intensive for the dispatching agency of the power grid to dispatch the charging load of electric vehicles with a single charging pile as a unit. The participation of electric vehicle charging load in power grid load regulation and cross-provincial calls should be achieved through load aggregator charging stations. Therefore, managing electric vehicles through load aggregator charging stations to achieve power grid load regulation can improve the dispatching efficiency of the power grid and reduce labor costs. When the target power grid is about to generate a peak or valley of electricity consumption, the adjustment signal of the power grid load will be triggered. When the adjustment signal is received, the load adjustment demand information corresponding to the target power grid is first obtained. At the same time, the power station attribute information of each load aggregator charging station in the power supply area of ​​the target power grid is obtained. Then, according to the load adjustment demand information and power station attribute information, the target load aggregator charging station with the best load adjustment effect is selected, and finally the load adjustment of the target power grid is achieved by charging and dispatching each electric vehicle in the target load aggregator charging station.

[0072] 202. Based on the load regulation demand information and the power station attribute information, determine a target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations.

[0073] Among them, the load regulation demand information includes: at least one of the load regulation amount corresponding to the target power grid, the load regulation method information, and the power grid location information; the power station attribute information includes: at least one of the charging pile quantity information, charging pile type information, and regional location information of each load aggregator charging station.

[0074] For the embodiment of the present invention, after obtaining the load regulation demand information of the target power grid and the power station attribute information of each load aggregator charging station, it is necessary to select the target load aggregator charging station that meets the load regulation conditions from among the load aggregator charging stations according to the above information. Based on this, step 202 specifically includes: based on the load regulation amount and the charging pile quantity information, determining a guaranteed load aggregator charging station that can meet the load regulation amount demand from among the load aggregator charging stations; based on the load regulation mode information and the charging pile type information, determining an expected load aggregator charging station that can realize the load regulation mode of the target power grid from among the guaranteed load aggregator charging stations; based on the power grid location information and the regional location information, determining a target load aggregator charging station that is closest to the location of the target power grid from among the expected load aggregator charging stations.

[0075] Specifically, when the target power grid is about to reach a large power supply peak, in order to reduce the peak, the load regulation amount of the target power grid will also increase; or when the target power grid is about to reach a large power supply valley value, in order to fill the underestimation value, the load regulation amount of the target power grid will also increase. If the target power grid is about to reach a small power supply peak, the load regulation amount of the target power grid will also be small. When the load regulation amount of the target power grid is large, more electric vehicles are needed to participate in the load regulation. Therefore, it is necessary to select a guaranteed load aggregator charging station with a number of charging piles that meets the load regulation demand among each load aggregator charging station. Only when multiple charging piles charge and discharge electric vehicles can effective load regulation of the target power grid be achieved. At the same time, the regulation demand information of the target power grid also includes load regulation method information. In order to meet the load regulation demand, it is also necessary to select the expected load aggregator charging station that can meet the regulation method from the guaranteed load aggregator charging stations, and then select the target load aggregator charging station that is closest to the location of the target power grid from the expected load aggregator charging stations. In this way, the load aggregator charging station is selected according to the load regulation amount, load regulation method, and power grid location, which can make the selected load aggregator charging station better meet the load regulation needs of the power grid, thereby improving the load regulation effect of the power grid.

[0076] In another embodiment of the present invention, in order to determine a target load aggregator charging station that meets the load regulation conditions among each load aggregator charging station, the method also includes: determining an adjustment feature vector corresponding to the load regulation demand information and a power station feature vector corresponding to the power station attribute information, and fusing the adjustment feature vector and each of the power station feature vectors respectively to obtain an adjustment fusion feature vector between the target power grid and each of the load aggregator charging stations; inputting each of the adjustment fusion feature vectors into a preset adjustment effect scoring model for score prediction to obtain a load regulation effect score of each load aggregator charging station corresponding to the target power grid; based on the load regulation effect score, determining a target load aggregator charging station that meets the load regulation conditions among each of the load aggregator charging stations. Among them, the method for fusing the adjustment characteristic vector and the power station characteristic vector includes: constructing a characteristic matrix based on the adjustment characteristic vector and any one of the power station characteristic vectors; determining the element mean of each element in the characteristic matrix, and subtracting each element in the characteristic matrix from the element mean to obtain a centralized characteristic matrix; determining the covariance matrix corresponding to the centralized characteristic matrix; performing eigenvalue decomposition on the covariance matrix to obtain matrix eigenvalues ​​and matrix eigenvectors; based on the size of the matrix eigenvalues, selecting a preset number of principal component adjustment characteristic vectors from the matrix characteristic vector; horizontally splicing each of the principal component adjustment characteristic vectors to obtain a regulation fusion characteristic vector between the target power grid and any load aggregator charging station, wherein any one of the power station characteristic vectors belongs to any one of the load aggregator charging station.

[0077] Specifically, in order to improve the prediction accuracy of the preset regulation effect scoring model, it is first necessary to train and construct the preset regulation effect scoring model. The specific training and construction methods are as follows: construct a preset initial scoring model; obtain sample data, wherein the sample data includes sample regulation demand information of the sample power grid, sample power station attribute information of each sample in the power supply area of ​​the sample power grid that meets the charging station of the aggregator, and the actual regulation score of each sample that meets the charging station of the aggregator; fuse the sample regulation feature vector corresponding to the regulation demand information with the sample power station feature vector corresponding to each sample power station attribute information to obtain a sample fusion feature vector; input each sample fusion feature vector decibel into the preset initial scoring model for score prediction to obtain a predicted regulation score; based on the actual regulation score and the predicted regulation score, construct a loss function corresponding to the preset initial scoring model; based on the loss function, iteratively train the preset initial scoring model to obtain a preset regulation effect scoring model. The preset regulation effect scoring model is further used to predict the load regulation effect score, so as to further improve the regulation efficiency and regulation accuracy of the power grid load.

[0078] Among them, the preset number is a value set according to actual needs. Specifically, the adjustment feature vector corresponding to the load adjustment demand information and the power station feature vector corresponding to the power station attribute information can be determined by word embedding and other methods, and then the adjustment feature vector is fused with each power station feature vector respectively. The specific fusion method is: if the adjustment feature vector is [100 4 0] and any power station feature vector is [1 01 4 4], the feature matrix composed of the adjustment feature vector and any power station feature vector is as follows:

[0079]

[0080] Among them, T represents the feature matrix. Then, the element mean corresponding to the elements in the first row of the feature matrix is ​​determined, and each element in the first row of elements is subtracted from the mean to obtain the subtraction result corresponding to each element in the first row. At the same time, the element mean corresponding to each element in the second row is determined, and each element in the second row is subtracted from the corresponding element mean to obtain the subtraction result corresponding to each element in the second row. Finally, the subtraction result corresponding to each element in the first row and the subtraction result corresponding to each element in the second row are used to form the centralized feature matrix as follows:

[0081]

[0082] Among them, T z represents the centralized feature matrix, and then calculates the covariance between each row of the centralized feature matrix. For example, the covariance between the first row of elements Cov(X1, X1) = [(0) 2 +(-1) 2 +(-1) 2 +(3) 2 +(-1) 2] / (5-1)=3, the covariance between the first row elements and the second row elements Cov(X1,X2)=[(0)×(-1)+(-1)×(-2)+(-1)×(-1)+3×2+(-1)×(2)] / (5-1)=2.75, thus the covariance between all row elements can be calculated, and then all covariances form a covariance matrix, and the covariance matrix is ​​subjected to eigenvalue decomposition. The specific decomposition method is: first determine the eigenvector group of the covariance matrix, and calculate the corresponding eigenvalue based on the eigenvector group. For example, if the obtained eigenvector group is k, then the corresponding eigenvalues ​​are k, and each eigenvalue has its corresponding eigenvector. Then the k eigenvalues ​​are decomposed from large to small. Sorting is performed to obtain the sorted eigenvalues, and then the eigenvalues ​​ranked in the top n (preset number) are selected from the sorted eigenvalues, and the eigenvectors corresponding to the eigenvalues ​​of the top n are determined as the principal component adjustment eigenvectors, and then each principal component adjustment eigenvector is horizontally spliced ​​to obtain the adjustment fusion eigenvector between the target power grid and any load aggregator charging station, and further, the adjustment fusion eigenvector is input into the preset adjustment effect scoring model for score prediction to obtain the load adjustment effect score of the load aggregator charging station corresponding to the target power grid, thereby obtaining the load adjustment effect score corresponding to each load aggregator charging station, and finally determining the load aggregator charging station corresponding to the maximum score as the target load aggregator charging station. Since the load adjustment demand information and power station attribute information in the embodiment of the present invention belong to data from different data sources and different dimensions, by fusing data from different data sources and different dimensions into more significant and deeper features, and using the model to analyze and predict the more significant and deeper features, the prediction performance of the model can be improved, thereby improving the accuracy of power grid load adjustment and ensuring the stable operation of the power grid.

[0083] 203. If the load of the target power grid is adjusted by using the peak-load charging adjustment method, the peak charging electricity price during the peak power consumption period and the valley charging electricity price during the valley power consumption period are determined.

[0084] Among them, the load regulation demand information includes at least one of the peak-shifting charging regulation mode and the reverse power supply regulation mode in the load regulation mode information. For the embodiment of the present invention, if the load regulation mode in the load regulation demand information is the peak-shifting charging regulation mode, in order to realize the peak-shifting charging of electric vehicles, different charging electricity prices need to be set for the charging peak period and the charging valley period. Based on this, the method includes: obtaining the historical peak charging electricity prices of the peak power consumption period and the historical valley charging electricity prices of the valley power consumption period in different historical time periods, and obtaining the participation information of the charging users in each of the historical time periods for the peak-shifting charging; based on the historical peak charging electricity prices, the historical valley charging electricity prices, and the participation information, determine the peak charging electricity prices of the peak power consumption period and the valley charging electricity prices of the valley power consumption period for load regulation of the target power grid.

[0085] Among them, participation information refers to the ratio of the number of electric vehicles participating in off-peak charging to the total number of electric vehicles in the statistical area. Specifically, the historical peak charging electricity prices during the peak electricity consumption period and the historical valley charging electricity prices during the valley electricity consumption period corresponding to the target power grid in each historical time period in the past are counted. At the same time, the participation information of electric vehicles with different electricity prices is counted, and the target historical peak charging electricity price and target valley charging electricity price when the participation is the highest are determined. The target historical peak charging electricity price is determined as the peak charging electricity price during the peak electricity consumption period for load regulation of the target power grid, and the target valley charging electricity price is determined as the valley charging electricity price during the valley electricity consumption period for load regulation of the target power grid.

[0086] 204. Based on the peak charging electricity price and the valley charging electricity price, each electric vehicle in the charging station of the target load aggregator is controlled to perform peak-shifting charging to achieve load regulation of the target power grid.

[0087] Specifically, after formulating the peak charging electricity price for the peak power supply period and the valley charging electricity price for the valley power supply period corresponding to the target power grid, the peak charging electricity price and its corresponding charging time and the valley charging electricity price and its corresponding charging time are sent to the target load aggregator charging station. The target load aggregator charging station dispatches the corresponding electric vehicles for peak-shifting charging based on the peak charging electricity price and the valley charging electricity price and their corresponding charging time, thereby realizing load regulation of the target power grid, and realizing peak shaving and valley filling of the power supply of the target power grid through electric vehicles, which maintains the stable power supply of the power grid while reducing the charging costs of electric vehicles.

[0088] 205. If the reverse power supply regulation method is used to regulate the load of the target power grid, the power information, driving demand information and user intention information of the user of the electric vehicle for reverse power supply of each electric vehicle in the charging station of the target load aggregator are obtained.

[0089] 206. Based on the power information, the driving demand information, and the user intention information, determine a target electric vehicle that meets the reverse power supply condition from among the electric vehicles.

[0090] 207. Control the target electric vehicle to reversely supply power to the target power grid based on a preset reverse power supply charging pile in the target load aggregator charging station, so as to achieve load regulation of the target power grid.

[0091] Among them, reverse power supply refers to the transmission of electricity in electric vehicles to the target power grid through preset reverse power supply charging piles, such as V2G (Vehicle To Grid) charging piles. Preset reverse power supply charging piles can not only realize the power grid to supply electric energy to electric vehicles, but also realize the supply of electric energy in electric vehicles to the power grid. Electricity information refers to the current storage of electricity in each electric vehicle in the charging station of the target load aggregator when receiving the load adjustment signal. Driving demand information refers to the estimated daily mileage of each electric vehicle. User intention information refers to whether the user of the electric vehicle is willing to supply the electricity in the vehicle to the target power grid.

[0092] For the embodiment of the present invention, if the power grid encounters a peak power supply period, the reverse power supply regulation method can also be used to implement load regulation of the power grid. At this time, it is necessary to obtain the power information, driving demand information and user intention information of the electric vehicle users in the target load aggregator charging station. Then, according to the power information, driving demand information and user intention information, the target electric vehicle that meets the reverse power supply conditions is determined among the electric vehicles. Based on this, the method includes: based on the power information, determining the available vehicles whose current power is greater than the preset power threshold among the electric vehicles; based on the driving demand information, determining the short-distance vehicles whose expected driving distance is less than the preset distance threshold among the electric vehicles; based on the user intention information, determining the cooperating vehicles for the user to accept reverse power supply among the electric vehicles; determining overlapping vehicles among the available vehicles, short-distance vehicles and cooperating vehicles, and determining the overlapping vehicles as target electric vehicles that meet the reverse power supply conditions.

[0093] Among them, the preset power threshold is a value set according to actual needs, and the preset distance threshold is a value set according to actual needs. Specifically, among the electric vehicles, select the target electric vehicle whose storage power is greater than the preset power threshold, the pre-travel distance on the day is less than the preset distance threshold, and the user of the electric vehicle agrees to reverse power supply, and finally control the target electric vehicle to reverse power supply to the target power grid based on the preset reverse power supply charging pile in the charging station of the target load aggregator, so as to realize load regulation of the target power grid. Therefore, under the premise of meeting the daily driving needs and charging needs of electric vehicles, the two-way interaction between the power grid and the power battery of electric vehicles is realized through the two-way charging pile, and the two-way interaction with the electric vehicle is carried out according to the needs of the power grid, which can conveniently realize the load regulation of the power grid, alleviate the power consumption pressure during the peak load of the power grid, and increase the output of the power grid. In addition, under certain conditions, this part of the reversely transmitted electric energy can also be supplied to other provinces and cities for use, further enriching the mode of adjustable load resources participating in cross-provincial calls.

[0094] According to another grid load regulation method provided by the present invention, compared with the current method of achieving load regulation of the grid system by adjusting the output of the grid generator set, the present invention obtains the load regulation demand information of the target grid and the power station attribute information of each load aggregator charging station in the power supply area corresponding to the target grid by responding to the load regulation signal of the target grid; and based on the load regulation demand information and the power station attribute information, determines the target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations; and finally, based on the load regulation demand information, uses each electric vehicle in the target load aggregator charging station to load regulate the target grid. Therefore, by comprehensively analyzing the grid's regulation demand information and the power station attribute information of each load aggregator charging station, a target load aggregator charging station that can meet the load regulation conditions is selected, and finally the grid load is regulated by using each electric vehicle in the target load aggregator charging station. This can avoid increasing the power supply cost wasted by the generator set, and also avoid reducing the time wasted by the generator set. Therefore, the present invention can reduce the power supply cost and improve the grid load regulation efficiency. At the same time, since electric vehicles have strong regulation elasticity and regulation capacity, they are suitable for participating in the dispatch of the grid. Therefore, the present invention can improve the regulation effect of the grid load by using electric vehicles to participate in the grid load regulation.

[0095] Further, as Figure 1 In a specific implementation, an embodiment of the present invention provides a power grid load regulating device, such as Figure 8 As shown, the device includes: an acquisition unit 31, a determination unit 32 and an adjustment unit 33.

[0096] The acquisition unit 31 may be configured to respond to a load regulation signal of a target power grid and acquire load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid.

[0097] The determining unit 32 may be configured to determine a target load aggregator charging station that meets a load regulation condition among the load aggregator charging stations based on the load regulation requirement information and the power station attribute information.

[0098] The regulating unit 33 may be configured to perform load regulation on the target power grid using the electric vehicles in the target load aggregator charging station based on the load regulation demand information.

[0099] In a specific application scenario, the load regulation demand information includes: at least one of the load regulation amount, load regulation mode information, and power grid location information corresponding to the target power grid, and the power station attribute information includes: at least one of the charging pile quantity information, charging pile type information, and regional location information of each of the load aggregator charging stations. In order to determine the target load aggregator charging station that meets the load regulation conditions, the determination unit 32 can be specifically used to determine, based on the load regulation amount and the charging pile quantity information, a guaranteed load aggregator charging station that can meet the load regulation amount requirement in each of the load aggregator charging stations; based on the load regulation mode information and the charging pile type information, determine an expected load aggregator charging station that can realize the load regulation mode of the target power grid in the guaranteed load aggregator charging station; based on the power grid location information and the regional location information, determine the target load aggregator charging station that is closest to the location of the target power grid in the expected load aggregator charging station.

[0100] In a specific application scenario, the load regulation demand information includes at least one of the peak-shifting charging regulation mode and the reverse power supply regulation mode in the load regulation mode information. In order to use each electric vehicle to perform load regulation on the target power grid, such as Fig. 9 As shown, the adjusting unit 33 includes a determining module 331 , a controlling module 332 , and an acquiring module 333 .

[0101] The determination module 331 may be used to determine the peak charging electricity price during the peak power consumption period and the valley charging electricity price during the valley power consumption period if the target power grid is load regulated by the peak-load charging regulation method.

[0102] The control module 332 can be used to control each electric vehicle in the target load aggregator charging station to perform off-peak charging based on the peak charging electricity price and the valley charging electricity price, so as to achieve load regulation of the target power grid.

[0103] The acquisition module 333 can be used to obtain the power information, driving demand information and user intention information of the electric vehicle users for reverse power supply of each electric vehicle in the charging station of the target load aggregator if the reverse power supply regulation method is used to regulate the load of the target power grid.

[0104] The determination module 331 may be specifically configured to determine a target electric vehicle that meets the reverse power supply condition among the electric vehicles based on the power information, the driving demand information, and the user intention information.

[0105] The control module 332 may be specifically used to control the target electric vehicle to reversely supply power to the target power grid based on a preset reverse power supply charging pile in the target load aggregator charging station, so as to achieve load regulation of the target power grid.

[0106] In a specific application scenario, in order to determine the peak charging electricity price during peak electricity consumption periods and the valley charging electricity price during valley electricity consumption periods, the determination module 331 can be specifically used to obtain the historical peak charging electricity price during peak electricity consumption periods and the historical valley charging electricity price during valley electricity consumption periods in different historical time periods, as well as to obtain the participation information of charging users in each of the historical time periods for off-peak charging; based on the historical peak charging electricity price, the historical valley charging electricity price and the participation information, determine the peak charging electricity price during peak electricity consumption periods and the valley charging electricity price during valley electricity consumption periods for load adjustment of the target power grid.

[0107] In a specific application scenario, in order to determine the target electric vehicle that meets the reverse power supply conditions among various electric vehicles, the determination module 331 can be specifically used to determine, based on the power information, a callable vehicle whose current power is greater than a preset power threshold among each of the electric vehicles; based on the driving demand information, determine a short-distance vehicle whose expected driving distance is less than a preset distance threshold among each of the electric vehicles; based on the user intention information, determine a cooperating vehicle for which the user accepts reverse power supply among each of the electric vehicles; determine overlapping vehicles among the callable vehicles, short-distance vehicles, and cooperating vehicles, and determine the overlapping vehicles as target electric vehicles that meet the reverse power supply conditions.

[0108] In a specific application scenario, in order to perform load regulation on the target power grid, the regulation unit 33 further includes an elasticity analysis module 334 and an adjustment module 335 .

[0109] The acquisition module 333 may also be used to acquire historical daily mileage information, historical charging time information, battery property information, historical charging mode information, and historical daily charging times information of different types of electric vehicles in the power supply area.

[0110] The elasticity analysis module 334 can be used to input the historical daily mileage information, historical charging time information, battery property information, historical charging mode information, and historical daily charging times information of various electric vehicles into a preset regulation elasticity analysis model to perform regulation elasticity analysis, and obtain the regulation elasticity scores of various electric vehicles for the target power grid.

[0111] The determination module 331 may also be used to determine, based on the regulation flexibility score, a target category of electric vehicles that meets the grid load regulation requirements among various electric vehicles.

[0112] The regulation module 335 may be configured to perform load regulation on the target power grid using electric vehicles of each target category in the target load aggregator charging station based on the load regulation demand information.

[0113] In a specific application scenario, in order to determine a target load aggregator charging station that meets the load regulation conditions, the determination unit 32 includes a fusion module 321 and a prediction module 322 .

[0114] The fusion module 321 can be used to determine the regulation feature vector corresponding to the load regulation demand information and the power station feature vector corresponding to the power station attribute information, and respectively fuse the regulation feature vector and each of the power station feature vectors to obtain the regulation fusion feature vector between the target power grid and each of the load aggregator charging stations.

[0115] The prediction module 322 can be used to input each of the regulation fusion feature vectors into a preset regulation effect scoring model for score prediction, so as to obtain the load regulation effect score of each load aggregator charging station corresponding to the target power grid; based on the load regulation effect score, determine the target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations.

[0116] Among them, in order to fuse different vectors, the fusion module 321 can be specifically used to construct a feature matrix based on the adjustment feature vector and any power station feature vector in the power station feature vector; determine the element mean of each element in the feature matrix, and subtract each element in the feature matrix from the element mean to obtain a centralized feature matrix; determine the covariance matrix corresponding to the centralized feature matrix; perform eigenvalue decomposition on the covariance matrix to obtain matrix eigenvalues ​​and matrix eigenvectors; based on the size of the matrix eigenvalues, select a preset number of principal component adjustment feature vectors from the matrix feature vector; horizontally splice each of the principal component adjustment feature vectors to obtain a regulation fusion feature vector between the target power grid and any load aggregator charging station, wherein any power station feature vector belongs to any load aggregator charging station.

[0117] It should be noted that for other corresponding descriptions of the functional modules involved in the power grid load regulation device provided in the embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0118] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented: in response to a load regulation signal of a target power grid, the load regulation demand information of the target power grid and the power station attribute information of each load aggregator charging station in the power supply area corresponding to the target power grid are obtained; based on the load regulation demand information and the power station attribute information, a target load aggregator charging station that meets the load regulation conditions is determined among each load aggregator charging station; based on the load regulation demand information, each electric vehicle in the target load aggregator charging station is used to load regulate the target power grid.

[0119] Based on the above Figure 1 The method shown and Figure 8 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Fig.10 As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43. When the processor 41 executes the program, the following steps are implemented: in response to a load regulation signal of a target power grid, load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid are obtained; based on the load regulation demand information and the power station attribute information, a target load aggregator charging station that meets the load regulation conditions is determined among each of the load aggregator charging stations; based on the load regulation demand information, each electric vehicle in the target load aggregator charging station is used to load regulate the target power grid.

[0120] Through the technical solution of the present invention, compared with the method of realizing load regulation of the power grid system by adjusting the output of the power grid generator set, the present invention obtains the load regulation demand information of the target power grid and the power station attribute information of each load aggregator charging station in the power supply area corresponding to the target power grid by responding to the load regulation signal of the target power grid; and based on the load regulation demand information and the power station attribute information, determines the target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations; finally, based on the load regulation demand information, uses each electric vehicle in the target load aggregator charging station to load regulate the target power grid. Therefore, by comprehensively analyzing the grid's regulation demand information and the power station attribute information of each load aggregator charging station, a target load aggregator charging station that can meet the load regulation conditions is selected, and finally the grid load is regulated by using each electric vehicle in the target load aggregator charging station. This can avoid increasing the power supply cost wasted by the generator set, and also avoid reducing the time wasted by the generator set. Therefore, the present invention can reduce the power supply cost and improve the grid load regulation efficiency. At the same time, since electric vehicles have strong regulation elasticity and regulation capacity, they are suitable for participating in the dispatch of the grid. Therefore, the present invention can improve the regulation effect of the grid load by using electric vehicles to participate in the grid load regulation.

[0121] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0122] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for regulating power grid load, characterized in that: include: In response to a load regulation signal of a target power grid, obtaining load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid; Based on the load regulation demand information and the power station attribute information, determining a target load aggregator charging station that meets the load regulation condition among the load aggregator charging stations; Based on the load regulation demand information, load regulation is performed on the target power grid using each electric vehicle in the charging station of the target load aggregator; The method for determining a target load aggregator charging station that meets the load regulation condition among the load aggregator charging stations based on the load regulation demand information and the power station attribute information includes: Determine the regulation feature vector corresponding to the load regulation demand information and the power station feature vector corresponding to the power station attribute information, and fuse the regulation feature vector and each of the power station feature vectors respectively to obtain a regulation fusion feature vector between the target power grid and each of the load aggregator charging stations; Input each of the regulation fusion feature vectors into a preset regulation effect scoring model for score prediction, and obtain a load regulation effect score of each load aggregator charging station corresponding to the target power grid; Based on the load regulation effect score, a target load aggregator charging station that meets the load regulation condition is determined among the load aggregator charging stations.

2. The method according to claim 1, characterized in that The load regulation requirement information includes: at least one of the load regulation amount, load regulation mode information, and grid location information corresponding to the target power grid; the power station attribute information includes: at least one of the number of charging piles, charging pile type information, and regional location information of each of the load aggregator charging stations; the target load aggregator charging station that meets the load regulation condition is determined among the load aggregator charging stations based on the load regulation requirement information and the power station attribute information, including: Based on the load regulation amount and the charging pile quantity information, determining a guaranteed load aggregator charging station that can meet the load regulation amount requirement among the load aggregator charging stations; Based on the load regulation mode information and the charging pile type information, determining a desired load aggregator charging station that can realize the load regulation mode of the target power grid among the guaranteed load aggregator charging stations; Based on the power grid location information and the regional location information, a target load aggregator charging station that is closest to the location of the target power grid is determined among the desired load aggregator charging stations.

3. The method according to claim 1, characterized in that The load regulation requirement information includes at least one of a peak-shift charging regulation mode and a reverse power supply regulation mode in the load regulation mode information; the load regulation of the target power grid using each electric vehicle in the charging station of the target load aggregator based on the load regulation requirement information includes: If the load of the target power grid is adjusted by using the peak-shift charging adjustment method, the peak charging electricity price during the peak power consumption period and the valley charging electricity price during the valley power consumption period are determined; Based on the peak charging electricity price and the valley charging electricity price, control each electric vehicle in the charging station of the target load aggregator to perform peak-shift charging, so as to achieve load regulation of the target power grid; If the reverse power supply regulation method is used to regulate the load of the target power grid, the power information, driving demand information and user intention information of the user of the electric vehicle for reverse power supply of each electric vehicle in the charging station of the target load aggregator are obtained; Based on the power information, the driving demand information and the user intention information, determining a target electric vehicle that meets the reverse power supply condition among the electric vehicles; The target electric vehicle is controlled to reversely supply power to the target power grid based on a preset reverse power supply charging pile in a target load aggregator charging station, so as to achieve load regulation of the target power grid.

4. The method according to claim 3, characterized in that The step of determining the peak charging electricity price during the peak electricity consumption period and the valley charging electricity price during the valley electricity consumption period includes: Obtain the historical peak charging electricity prices during the peak electricity consumption period and the historical valley charging electricity prices during the valley electricity consumption period in different historical time periods, and obtain the participation information of charging users in off-peak charging during each of the historical time periods; Based on the historical peak charging electricity prices, historical valley charging electricity prices, and the participation information, a peak charging electricity price during a peak power consumption period and a valley charging electricity price during a valley power consumption period for load regulation of the target power grid are determined.

5. The method according to claim 3, characterized in that: The step of determining a target electric vehicle that meets a reverse power supply condition among the electric vehicles based on the power information, the driving demand information, and the user intention information includes: Based on the power information, determining a callable vehicle whose current power is greater than a preset power threshold among the electric vehicles; Based on the driving demand information, determining a short-distance vehicle whose expected driving distance is less than a preset distance threshold among the electric vehicles; Based on the user intention information, determining a matching vehicle from among the electric vehicles from which the user can accept reverse power supply; An overlapping vehicle is determined among the available vehicles, the short-distance vehicles, and the cooperating vehicles, and the overlapping vehicle is determined as a target electric vehicle that meets a reverse power supply condition.

6. The method according to claim 1, characterized in that The method of performing load regulation on the target power grid by using each electric vehicle in the charging station of the target load aggregator based on the load regulation demand information includes: Obtain historical daily mileage information, historical charging time information, battery attribute information, historical charging mode information, and historical daily charging times information of different types of electric vehicles in the power supply area; Inputting historical daily mileage information, historical charging time information, battery attribute information, historical charging mode information, and historical daily charging times information of various electric vehicles into a preset regulation elasticity analysis model to perform regulation elasticity analysis, and obtaining regulation elasticity scores of various electric vehicles for the target power grid; Based on the regulation elasticity score, determining a target category of electric vehicles that meets the grid load regulation requirements among various electric vehicles; Based on the load regulation demand information, the target power grid is load regulated by using the target category electric vehicles in the target load aggregator charging station.

7. The method according to claim 1, characterized in that The fusing the adjustment feature vector and each of the power station feature vectors to obtain the adjustment fusion feature vector between the target power grid and each of the load aggregator charging stations includes: constructing a characteristic matrix based on the adjustment characteristic vector and any one of the power station characteristic vectors; Determine the element mean of each element in the feature matrix, and subtract each element in the feature matrix from the element mean to obtain a centralized feature matrix; Determine the covariance matrix corresponding to the centralized feature matrix; Performing eigenvalue decomposition on the covariance matrix to obtain matrix eigenvalues ​​and matrix eigenvectors; Based on the magnitude of the matrix eigenvalues, a preset number of principal component adjustment eigenvectors are selected from the matrix eigenvectors; The principal component adjustment feature vectors are horizontally spliced ​​to obtain an adjustment fusion feature vector between the target power grid and any load aggregator charging station, wherein the feature vector of any power station belongs to any load aggregator charging station.

8. A power grid load regulating device, characterized in that: include: An acquisition unit, configured to acquire, in response to a load regulation signal of a target power grid, load regulation demand information of the target power grid and power station attribute information of each load aggregator charging station in a power supply area corresponding to the target power grid; A determination unit, used to determine the regulation feature vector corresponding to the load regulation demand information and the power station feature vector corresponding to the power station attribute information, and respectively fuse the regulation feature vector and each of the power station feature vectors to obtain the regulation fusion feature vector between the target power grid and each of the load aggregator charging stations; respectively input each of the regulation fusion feature vectors into a preset regulation effect scoring model for score prediction to obtain the load regulation effect score of each of the load aggregator charging stations corresponding to the target power grid; based on the load regulation effect score, determine the target load aggregator charging station that meets the load regulation conditions among the load aggregator charging stations; A regulating unit is used to perform load regulation on the target power grid by utilizing each electric vehicle in the charging station of the target load aggregator based on the load regulation demand information.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images