Peak shaving method, device, equipment and system for power system

Abstract

The invention relates to the technical field of power system peak regulation, in particular to a power system peak regulation method, device, equipment and system.The method comprises the steps that the wind direction vector and the output power of each wind turbine generator in each wind field and the position coordinate vector of each wind field are obtained in real time; calculating the wind power disorder degree of each wind field at each moment; determining the wind power influence degree of any two wind fields at each moment, and outputting the correlation degree; determining the wind field interference degree of each wind field at the current moment; on the basis of the wind field interference degree of each wind field at the current moment and the output power of all the wind turbine generators, the predicted total power of each wind field after the current moment is obtained in combination with a neural network model; the output of the thermal power generating unit is regulated in real time, and peak regulation is performed on the power system. The prediction accuracy of the total power output by each wind field can be improved, so that accurate peak regulation is performed on the power of the power system, and the output power quality of the power system is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power system peak regulation, and specifically to a power system peak regulation method, device, equipment and system. Background Art

[0002] With the popularization of new energy power generation equipment, the power system uses new energy power generation equipment to supply power. Since the output power of new energy power generation equipment is affected by environmental changes, the output power fluctuates greatly, and the power system needs to ensure the stability of the output power, so it is necessary to perform peak load regulation on the power system.

[0003] Among the new energy power generation equipment, wind power generation equipment usually has the largest output power fluctuation. Wind power generation equipment usually arranges a wind power array in a wind farm and outputs electrical energy in units of wind power arrays. However, due to the instability of wind energy in the environment, the power output of the wind power array fluctuates greatly. When peaking the output power of the wind power array, statistical prediction is mainly performed based on the historical data of the wind power array, and then the power system is peaked based on the predicted value. This method does not fully utilize the geographic information of the wind power array, ignores the characteristics of synchronous fluctuations in the output power of adjacent wind farms, and easily leads to inaccurate peak regulation, resulting in reduced power supply quality of the power grid. Summary of the invention

[0004] In order to solve the above technical problems, a power system peak load regulation method, device, equipment and system are provided to solve the existing problems.

[0005] The solution to the technical problem of the present application is to provide a power system peak load regulation method, device, equipment and system, including the following steps: In a first aspect, an embodiment of the present application provides a method for peak load regulation of a power system, the method comprising the following steps: Obtain the wind direction vector, output power, and position coordinate vector of each wind turbine in each wind farm in real time; Based on the wind direction vector and output power of each wind turbine at each moment, the wind force vector of each wind turbine at each moment is obtained; Analyze the degree of deviation of wind vectors of different wind turbines in each wind farm at each time, and calculate the wind turbulence degree of each wind farm at each time; The wind influence of any two wind farms at each moment is determined by the difference between the position coordinate vectors of any two wind farms at each moment, the consistency between the overall wind direction of the any two wind farms and the relative distribution direction of their positions, and the wind turbulence degree; Based on the wind force influence, the relevant changes in the output power of all wind turbines between any two wind farms at multiple moments before the current moment are analyzed to determine the output correlation of any two wind farms at the current moment; the wind field interference degree of each wind farm at the current moment is determined by combining the output power of all wind turbines in each wind farm at the current moment; Based on the wind field interference degree of each wind farm and the output power of all wind turbines at the current moment, combined with the neural network model, the predicted total power of each wind farm after the current moment is obtained; based on the predicted total power of all wind farms at the current moment, the output of the thermal power units is regulated in real time to peak the power system.

[0006] Preferably, the wind force vector of each wind turbine set at each moment is the product of the wind direction vector of each wind turbine set at each moment and the output power.

[0007] Preferably, the calculating of the wind turbulence degree of each wind field at each moment includes: Calculate the mean of the wind vectors of all wind turbines in each wind farm at each moment as the average wind vector of each wind farm at each moment; Calculate the sine value of the angle between the wind vector of each wind turbine in each wind farm at each moment and the average wind vector, and record the product of the modulus of the wind vector of each wind turbine in each wind farm at each moment and the sine value as the wind deviation; The wind turbulence degree is the ratio between the mean of the wind deviations of all wind turbines in each wind farm at each moment and the modulus of the average wind vector.

[0008] Preferably, the determining the wind force influence of any two wind farms at each moment includes: The difference between the position coordinate vectors of any two wind fields is recorded as a position difference vector; Calculating the absolute value of the cosine value of the angle between the average wind force vector of each wind field in the arbitrary two wind fields and the position difference vector at each moment; Taking the average of the absolute values ​​between any two wind fields at each moment as the wind direction similarity between any two wind fields at each moment; Time next wind farm and The wind force influence between wind farms The calculation formula is: ,in, for Time next wind farm and The wind direction similarity between wind farms is for Time next The modulus of the average wind vector in the wind field is for Time next The modulus of the average wind vector in the wind field is for Time next The wind turbulence of a wind farm, for Time next The wind turbulence of a wind farm, For the wind farm and The modulus of the position difference vector between wind fields, The default value is greater than 0.

[0009] Preferably, the determining the output correlation between any two wind farms at the current moment includes: Calculate the sum of the output power of all wind turbines in each wind farm at each time, and record it as the total output power; The total output power of each wind farm at multiple moments before the current moment is used to form a power output vector; The wind influence degrees of the arbitrary two wind farms at multiple moments before the current moment are combined into a wind influence vector; and the wind influence vector is normalized to form an influence weight vector; Taking the elements in the influence weight vector as weights, a weighted correlation coefficient of the power output vectors of the arbitrary two wind farms at the current moment is calculated as the output correlation degree of the arbitrary two wind farms at the current moment.

[0010] Preferably, determining the wind field interference degree of each wind field at the current moment includes: A result of normalizing the output correlation between any wind farm and the other wind farms at the current moment is recorded as a correlation weight; Based on the association weight between any one wind farm and the remaining wind farms at the current moment, a weighted sum is taken for the total output power of all the remaining wind farms at the current moment as the wind farm interference degree of any one wind farm at the current moment.

[0011] Preferably, the real-time control of the output of the thermal power unit includes: Based on the wind farm interference degree and the total output power of each wind farm at the current moment, prediction is performed through a neural network model to obtain a predicted total power of each wind farm after the current moment; Calculate the sum of the predicted total powers of all wind farms at the current moment, and record it as the wind farm predicted power; If the predicted power of the wind farm is less than a preset threshold, the output of the thermal power unit is increased; otherwise, the output of the thermal power unit is reduced.

[0012] In a second aspect, an embodiment of the present application further provides a power system peak-shaving device, the device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above-mentioned power system peak-shaving methods when executing the computer program.

[0013] In a third aspect, an embodiment of the present application further provides a power system peak-shaving device, wherein the device stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned power system peak-shaving methods are implemented.

[0014] In a fourth aspect, an embodiment of the present application further provides a power system peak load regulation system, the system comprising: The data acquisition module is used to obtain the wind direction vector, output power, and position coordinate vector of each wind turbine in each wind farm in real time; The power prediction module obtains the wind vector of each wind turbine at each moment based on the wind direction vector and output power of each wind turbine at each moment; analyzes the degree of deviation of the wind vectors of different wind turbines in each wind farm at each moment, and calculates the wind turbulence degree of each wind farm at each moment; determines the wind influence degree of any two wind farms at each moment by the difference between the position coordinate vectors of any two wind farms at each moment, and the consistency between the overall wind direction of the any two wind farms and the relative distribution direction of their positions, combined with the wind turbulence degree; based on the wind influence degree, analyzes the relevant changes in the output power of all wind turbines between the any two wind farms at multiple moments before the current moment, and determines the output correlation degree of the any two wind farms at the current moment; determines the wind field interference degree of each wind farm at the current moment in combination with the output power of all wind turbines in each wind farm at the current moment; obtains the predicted total power of each wind farm after the current moment based on the wind field interference degree of each wind farm and the output power of all wind turbines at the current moment in combination with the neural network model; The thermal power peak regulation module is used to adjust the output of the thermal power units in real time through the predicted total power of all wind farms at the current moment, so as to perform peak regulation on the power system.

[0015] This application has at least the following beneficial effects: The present application calculates the wind vector through the wind direction vector and output power of each wind turbine, and then calculates the wind turbulence of each wind farm at each moment. The beneficial effect of this application is that it takes into account the wind size and wind direction characteristics of each wind turbine in each wind farm, and reflects the degree of chaos of the overall wind force of each wind farm by analyzing the wind force and wind direction deviation of different wind turbines in each wind farm, and then explains the influence of the wind force of this wind farm on other wind farms; secondly, the wind influence of any two wind farms at each moment is calculated, and the beneficial effect of this application is that it takes into account the position distribution between the two wind farms, as well as the consistency of the overall wind direction distribution of the two wind farms with the relative distribution direction of the positions of the two wind farms, and the overall wind strength of the two wind farms, so as to evaluate the mutual influence of the wind force between the two wind farms; the output correlation of any two wind farms at the current moment is determined, and the beneficial effect of this application is that it takes into account all the wind forces of the two wind farms. The output power of the generator sets is correlated with the changes in the synchronous fluctuations in the power output of the two wind farms; the wind field interference degree of each wind farm at the current moment is determined, which has the beneficial effect of reflecting that each wind farm is affected by the wind force of the other wind farms, resulting in significant synchronous fluctuations in the output power, thereby explaining the interference situation of the wind farm; through the wind field interference degree of each wind farm at the current moment and the output power of all wind turbines, combined with the neural network model, the total power output of each wind farm after the current moment is predicted, and based on the predicted total power of all wind farms at the current moment, the output of the thermal power units is adjusted in real time to peak the power system. The beneficial effect is that it takes into account the trend of synchronous fluctuations in the output power of adjacent wind farms, improves the accuracy of the prediction of the total power output of each wind farm, can more accurately peak the power of the power system, and improves the output power quality of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] A power system peak regulation method of the present application is further described in detail below with reference to the accompanying drawings.

[0017] Figure 1 A flowchart of a method for peak load regulation of a power system provided in an embodiment of the present application; Figure 2 A flowchart of the steps of a method for obtaining the output correlation degree of any two wind farms at the current moment provided in an embodiment of the present application; Figure 3 A flowchart of power system peak load regulation provided in an embodiment of the present application; Figure 4 A block diagram of a power system peak load regulation system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the following is a further detailed description of a power system peak-shaving method, device, equipment and system proposed in the present application in combination with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0020] See also Figure 1 , which shows a flowchart of a method for peak load regulation of a power system provided by an embodiment of the present application, the method comprising the following steps: Step 1: Obtain the wind direction vector, output power, and position coordinate vector of each wind turbine in each wind farm in real time.

[0021] Wind power comes from wind energy, and its power output is highly random, fluctuating, and difficult to control. In the operation of the power system, the instability and intermittency of wind power generation have brought challenges to the peak regulation of the power system. However, thermal power units are a traditional way of power supply, and their power generation can be controlled artificially. Therefore, by predicting the output power of wind power generation, the power generation of thermal power units can be adjusted in real time, so as to dynamically regulate the power system. For example, when it is predicted that the output power of wind power generation will decrease, the power grid may have a power shortage. At this time, it is necessary to start or increase the power generation of thermal power units in advance to make up for the shortage of wind power; conversely, when it is predicted that the output power of wind power generation will increase, the power generation of thermal power units can be reduced to avoid excess power. Wind farms are usually arranged in arrays. Due to the change of the dominant wind direction, the output power of adjacent wind farms will rise or fall sharply, forming synchronous fluctuations, resulting in inaccurate prediction of the output power of wind power generation, and then resulting in poor peak regulation of the power system. Therefore, it is necessary to analyze the interference between different wind farms.

[0022] Secondly, a power generation unit formed by arranging multiple wind turbines in a certain layout and spacing is called a wind turbine array. The layout of the wind turbine array is very important, and there are many arrangements, such as plum blossom type, field type, etc. The wind farm where each wind turbine array is located is recorded as each wind farm. Dozens or hundreds of wind turbines in the wind farm directly affect the actual power generation of the wind farm.

[0023] For each wind farm, each wind turbine will adjust the direction of the blades in real time so that the blades face the wind to capture wind energy. Therefore, by installing a wind vane on each wind turbine, where the installation position of the wind vane is parallel to the blade rotation plane, the direction angle of the back of the blade of the wind turbine at each moment is obtained, which is recorded as the wind direction of each wind turbine at each moment, and the wind direction is converted into a unit vector to obtain the wind direction vector of each wind turbine at each moment; It should be noted that, assuming Wind turbines in The wind direction angle at the moment is , then the wind direction vector is .

[0024] By installing a power sensor on each wind turbine, the output power of each wind turbine at each moment is obtained; It should be noted that the data collection time interval is 1 second. As other implementation methods, the implementer can set it according to the actual situation.

[0025] Get the position coordinate vector of each wind field; It should be noted that wind power generation usually chooses plains or plateaus, and the wind farms that affect each other usually have a small altitude difference, so the position coordinate vector obtained from the wind farm is a two-dimensional coordinate vector.

[0026] At this point, the wind direction vector, output power of each wind turbine in each wind farm at each moment, and the position coordinate vector of each wind farm are obtained.

[0027] Step 2: Based on the wind direction vector and output power of each wind turbine at each moment, the wind vector of each wind turbine at each moment is obtained; the degree of deviation of the wind vectors of different wind turbines in each wind farm at each moment is analyzed, and the wind turbulence degree of each wind farm at each moment is calculated.

[0028] When a wind farm is generating electricity, the output power of two adjacent wind farms tends to fluctuate synchronously. Therefore, during the peak-shaving process of the power system, the wind characteristics of the adjacent wind farms can be used to improve the control accuracy of the power peak-shaving system. In order to improve the accuracy of the peak-shaving of the power system, it is necessary to evaluate the wind characteristics of the wind farm, especially the intensity and direction of the wind, as well as the wind stability within the wind farm. If the wind power in the wind farm where a wind power array is located is stronger and the wind direction is more stable, it will have a greater impact on the wind power in the surrounding wind farms.

[0029] Therefore, the wind conditions at the locations of each wind turbine are analyzed through the output power and wind volume vector of each wind turbine, and the wind vector is obtained, which is specifically: The product of the wind direction vector and the output power of each wind turbine generator set at each moment is taken as the wind force vector of each wind turbine generator set at each moment; It should be noted that the wind force can be characterized by the output power of the wind turbine. The greater the output power of the wind turbine, the greater the wind force at the location of the corresponding wind turbine.

[0030] Secondly, for different wind turbines in the same wind farm, when the wind direction difference between wind turbines is large, it means that the wind conditions in the wind farm are relatively chaotic and unstable, and the unstable wind will affect the neighboring wind farms. Therefore, the wind turbulence is determined by the wind vectors of all wind turbines in each wind farm to evaluate the wind fluctuation of different wind turbines in the wind farm. Specifically: Calculate the mean of the wind vectors of all wind turbines in each wind farm at each time as the average wind vector of each wind farm at each time; It should be noted that, for ease of understanding, it is assumed that There are 3 wind turbines in each wind farm. At this moment, Wind turbines, Wind turbines, The wind force vectors of each wind turbine are , , ,but Time next The average wind force vector of a wind field is , where the average wind vector reflects the overall wind direction and wind force of the wind field.

[0031] Calculate the sine value of the angle between the wind vector of each wind turbine in each wind farm at each moment and the average wind vector, and record the product of the modulus of the wind vector of each wind turbine in each wind farm at each moment and the sine value as the wind deviation; The ratio between the mean of the wind force deviations of all wind turbines in each wind farm at each moment and the modulus of the average wind force vector is used as the wind turbulence degree of each wind farm at each moment; It should be noted that the greater the wind force deviation, the greater the deviation between the wind force of the corresponding wind turbine and the overall wind force in the wind farm where it is located, and the greater the resulting wind turbulence, which means the more turbulent the wind force inside the corresponding wind farm is, and the smaller the impact of its wind force on the surrounding wind farms.

[0032] At this point, the wind turbulence degree of each wind field at each moment is obtained.

[0033] Step 3, determining the wind influence of any two wind fields at each moment through the difference between the position coordinate vectors of any two wind fields at each moment, the consistency between the overall wind direction of the any two wind fields and the relative distribution direction of their positions, and combining the wind turbulence degree.

[0034] Furthermore, different wind forces, different wind directions, and different position distributions between wind farms will lead to the mutual influence of wind forces between two wind farms. Therefore, the degree of proximity between the direction of the position distribution difference of any two wind farms and the average wind vector is analyzed, and the wind direction similarity is calculated to reflect the mutual influence of the two wind farms at different times. Specifically, The difference between the position coordinate vectors of any two wind fields is recorded as the position difference vector; It should be noted that if any two wind farms are wind farm and wind farm, The position coordinate vector of the wind field is The difference between the position coordinate vectors of the wind fields is taken as the position difference vector.

[0035] calculate Time next The absolute value of the cosine value of the angle between the average wind vector of each wind field and the position difference vector is recorded as the first absolute value; calculate Time next The absolute value of the cosine value of the angle between the average wind vector of each wind field and the position difference vector is recorded as the second absolute value; Calculate the mean of the first absolute value and the second absolute value as The similarity of wind directions of any two wind fields at the time; It should be noted that the larger the first absolute value or the second absolute value is, the closer the direction of the average wind vector is to the position difference vector, and the greater the similarity of the obtained wind direction is, which means that the wind directions of the two wind farms at this time are more consistent with the geographical locations of the two wind farms, and the stronger the mutual influence of the wind forces in the two wind farms is.

[0036] Further, based on the wind direction similarity and the wind turbulence, the wind influence is calculated, specifically: The calculation formula of the wind force influence degree of any two wind fields at each time is: in, for Time next wind farm and The wind force influence between wind farms is for Time next wind farm and The wind direction similarity between wind farms is for Time next The modulus of the average wind vector in the wind field is for Time next The modulus of the average wind vector in the wind field is for Time next The wind turbulence of a wind farm, for Time next The wind turbulence of a wind farm, For the wind farm and The modulus of the position difference vector between wind fields, To preset a value greater than 0 to avoid the denominator being 0, in this embodiment, The value of is 1. As other implementation methods, the implementer can set it according to the actual situation.

[0037] It should be noted that the greater the wind direction similarity, the Wind farm and The closer the wind directions of the two wind farms are, the stronger the wind force will be, and the stronger the mutual influence between the two wind farms will be. , Respectively reflects the Wind farm, The wind intensity of a wind farm, , The larger the value, the greater the wind intensity of the corresponding wind farm, and the greater the wind force of the corresponding wind farm, and the more likely it is to affect the wind force of other surrounding wind farms; secondly, Reflects the wind farm and The distance between wind farms, The smaller the wind speed, the closer the distance between the two wind farms is, and the greater the degree of mutual influence between the wind forces of the two wind farms. , The smaller the wind force is, the stronger the mutual influence of the two wind fields is, and the greater the wind force influence is, the greater the wind force influence is. wind farm and The greater the degree of mutual influence of wind forces in different wind farms.

[0038] So far, the wind force influence of any two wind fields at each moment is obtained.

[0039] Step 4: Based on the wind influence, analyze the relevant changes in the output power of all wind turbines between any two wind farms at multiple moments before the current moment, and determine the output correlation between any two wind farms at the current moment; combine the output power of all wind turbines in each wind farm at the current moment to determine the wind field interference degree of each wind farm at the current moment.

[0040] Furthermore, the wind farms where different wind power arrays are located have different power characteristics, and the output power under different wind conditions is different. Therefore, by analyzing the change of the output power of the two wind farms, the output correlation is calculated to reflect the trend of synchronous fluctuation of the output power of the two wind farms. The step flow chart of the method for obtaining the output correlation of any two wind farms at the current moment provided by the embodiment of the present application is as follows: Figure 2 As shown, specifically including: Calculate the sum of the output power of all wind turbines in each wind farm at each time, and record it as the total output power; The total output power of each wind farm at multiple moments before the current moment is used to form a power output vector; In this embodiment, the total output power of each wind farm at all times within 15 minutes before the current time is used to form a power output vector. As other implementation methods, the implementer can set it according to the actual situation.

[0041] The wind influence degrees of the arbitrary two wind farms at multiple moments before the current moment are combined into a wind influence vector; and the wind influence vector is normalized to form an influence weight vector; In this embodiment, the wind influence degrees of any two wind fields at all times within 15 minutes before the current moment are combined to form a wind influence vector. As other implementation methods, the implementers can set them according to actual conditions. Secondly, the normalization process is: calculate the cumulative sum of all elements in the wind influence vector, and form an influence weight vector with the ratio of each element in the wind influence vector to the cumulative sum.

[0042] Taking the elements in the influence weight vector as weights, calculating the weighted correlation coefficient of the power output vectors of any two wind farms at the current moment as the output correlation degree of the any two wind farms at the current moment; In this embodiment, the weighted correlation coefficient is measured by calculating the weighted Pearson correlation coefficient of the power output vectors of any two wind farms at the current moment, wherein the calculation of the weighted Pearson correlation coefficient is a well-known technology and will not be repeated here. As other implementation methods, the implementer may adopt other methods of the prior art, such as the weighted Spearman correlation coefficient, etc. This embodiment does not impose any special restrictions on this.

[0043] It should be noted that, the greater the output correlation is, the more obvious the trend of synchronous fluctuation of the total power output of the two wind farms is under the influence of wind power.

[0044] Furthermore, the wind farm interference degree is calculated through the output correlation degree to evaluate the synchronous fluctuation of the total power output of each wind farm when each wind farm is affected by other adjacent wind farms, specifically: Normalizing the output correlation between the mth wind farm and the other wind farms at the current moment, and recording the normalized result as the correlation weight; In this embodiment, the normalization process is: calculate the sum of the output correlations between the mth wind farm and all other wind farms at the current moment, and record the ratio of the output correlation between the mth wind farm and the other wind farms to the sum as the correlation weight.

[0045] Based on the association weights between the mth wind farm and the remaining wind farms at the current moment, a weighted sum is taken for the total output power of all the remaining wind farms at the current moment as the wind farm interference degree of the mth wind farm at the current moment; It should be noted that, the greater the wind farm interference degree is, the greater the interference caused by the remaining wind farms to the wind force of the m-th wind farm is, and the higher the degree of synchronous fluctuation of the power output by the m-th wind farm is.

[0046] At this point, the wind field interference degree of each wind field at the current moment is obtained.

[0047] Step 5: Based on the wind field interference degree of each wind farm and the output power of all wind turbines at the current moment, combined with the neural network model, the predicted total power of each wind farm after the current moment is obtained; based on the predicted total power of all wind farms at the current moment, the output of the thermal power units is adjusted in real time to peak the power system.

[0048] Furthermore, the total output power of the wind farm is predicted through the wind farm interference degree, and then the power of the power system is optimized and dispatched. Since thermal power units have slow response and long ramp-up time, it is necessary to predict the power grid fluctuation caused by the wind power array in advance, so that the thermal power units can optimize the power dispatch according to the fluctuation.

[0049] According to the above method, the wind farm interference degree and total output power at each moment in the historical period at the current moment can be obtained; the wind farm interference degree and total output power of each wind farm at all moments in the historical period are used as a training set; In this embodiment, the length of the historical period is 10,000, that is, there are 10,000 wind farm interference degrees and total output powers in the training set. As other implementation methods, the implementer can set them according to actual conditions.

[0050] Using the training set as input of the neural network model to train the neural network model; In this embodiment, a long short-term memory network model (LSTM) is used for training, wherein the long short-term memory network model is a well-known technology and will not be described in detail here. As other implementation methods, the implementer can adopt other methods of the prior art, such as a convolutional neural network model, etc. This embodiment does not impose any special restrictions on this. Secondly, in the long short-term memory network model, the activation function adopts the ReLU function, and the optimizer adopts the Adam optimizer; the mean square error is used as the loss function.

[0051] The wind field interference degree and total output power of each wind farm at the current moment are used as the input of the trained neural network model for prediction, and the predicted total power of each wind farm after the current moment is obtained; In this embodiment, the predicted total power of each wind farm in 15 minutes at the current moment is obtained. As other implementation methods, the implementer can set them according to the actual situation.

[0052] Calculate the sum of the predicted total powers of all wind farms at the current moment, and record it as the wind farm predicted power; If the predicted power of the wind farm is less than the preset threshold, the output of the thermal power unit is increased to provide additional power support for the power grid and ensure the stability of the power grid. Otherwise, the output of the thermal power unit is reduced to avoid excess power, thereby completing the power peak regulation of the power system with higher accuracy and improving the output power quality of the power system.

[0053] The flowchart of the power system peak load regulation provided in the embodiment of the present application is as follows: Figure 3 shown.

[0054] In this embodiment, the preset threshold value is 50 megawatts. As for other implementation methods, the implementer can set it according to the actual situation.

[0055] An embodiment of the present application also provides a power system peak-shaving device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned power system peak-shaving methods.

[0056] An embodiment of the present application further provides a power system peak-shaving device, wherein the device stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned power system peak-shaving methods are implemented.

[0057] Based on the same inventive concept as the above method, the embodiment of the present application further provides a power system peak load regulation system, the system comprising: The data acquisition module is used to obtain the wind direction vector, output power, and position coordinate vector of each wind turbine in each wind farm in real time; The power prediction module obtains the wind vector of each wind turbine at each moment based on the wind direction vector and output power of each wind turbine at each moment; analyzes the degree of deviation of the wind vectors of different wind turbines in each wind farm at each moment, and calculates the wind turbulence degree of each wind farm at each moment; determines the wind influence degree of any two wind farms at each moment by the difference between the position coordinate vectors of any two wind farms at each moment, and the consistency between the overall wind direction of the any two wind farms and the relative distribution direction of their positions, combined with the wind turbulence degree; based on the wind influence degree, analyzes the relevant changes in the output power of all wind turbines between the any two wind farms at multiple moments before the current moment, and determines the output correlation degree of the any two wind farms at the current moment; determines the wind field interference degree of each wind farm at the current moment in combination with the output power of all wind turbines in each wind farm at the current moment; obtains the predicted total power of each wind farm after the current moment based on the wind field interference degree of each wind farm and the output power of all wind turbines at the current moment in combination with the neural network model; The thermal power peak regulation module is used to adjust the output of the thermal power units in real time through the predicted total power of all wind farms at the current moment, so as to perform peak regulation on the power system.

[0058] A block diagram of a peak load regulation system of a power system provided in an embodiment of the present application is as follows Figure 4 shown.

[0059] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0060] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0061] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the present application. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the content of the technical solution of the present application, shall fall within the protection scope of the technical solution of the present application.

Claims

1. A method for peak load regulation of a power system, characterized in that: The method comprises the following steps: Obtain the wind direction vector, output power, and position coordinate vector of each wind turbine in each wind farm in real time; Based on the wind direction vector and output power of each wind turbine at each moment, the wind force vector of each wind turbine at each moment is obtained; Analyze the degree of deviation of wind vectors of different wind turbines in each wind farm at each time, and calculate the wind turbulence degree of each wind farm at each time; The wind influence of any two wind farms at each moment is determined by the difference between the position coordinate vectors of any two wind farms at each moment, the consistency between the overall wind direction of the any two wind farms and the relative distribution direction of their positions, and the wind turbulence degree; Based on the wind force influence, the relevant changes in the output power of all wind turbines between any two wind farms at multiple moments before the current moment are analyzed to determine the output correlation of any two wind farms at the current moment; the wind field interference degree of each wind farm at the current moment is determined by combining the output power of all wind turbines in each wind farm at the current moment; Based on the wind field interference degree of each wind farm and the output power of all wind turbines at the current moment, combined with the neural network model, the predicted total power of each wind farm after the current moment is obtained; based on the predicted total power of all wind farms at the current moment, the output of the thermal power units is regulated in real time to peak the power system.

2. A method for peak load regulation of a power system according to claim 1, characterized in that: The wind force vector of each wind turbine generator set at each moment is the product of the wind direction vector of each wind turbine generator set at each moment and the output power.

3. A method for peak load regulation of a power system according to claim 1, characterized in that: The calculation of the wind turbulence degree of each wind field at each moment includes: Calculate the mean of the wind vectors of all wind turbines in each wind farm at each moment as the average wind vector of each wind farm at each moment; Calculate the sine value of the angle between the wind vector of each wind turbine in each wind farm at each moment and the average wind vector, and record the product of the modulus of the wind vector of each wind turbine in each wind farm at each moment and the sine value as the wind deviation; The wind turbulence degree is the ratio between the mean of the wind deviations of all wind turbines in each wind farm at each moment and the modulus of the average wind vector.

4. A method for peak load regulation of a power system as claimed in claim 3, characterized in that: The determining of the wind force influence of any two wind farms at each time comprises: The difference between the position coordinate vectors of any two wind fields is recorded as a position difference vector; Calculating the absolute value of the cosine value of the angle between the average wind force vector of each wind field in the arbitrary two wind fields and the position difference vector at each moment; Taking the average of the absolute values ​​between any two wind fields at each moment as the wind direction similarity between any two wind fields at each moment; Time next wind farm and The wind force influence between wind farms The calculation formula is: ,in, for Time next wind farm and The wind direction similarity between wind farms is for Time next The modulus of the average wind vector in the wind field is for Time next The modulus of the average wind vector in the wind field is for Time next The wind turbulence of a wind farm, for Time next The wind turbulence of a wind farm, For the wind farm and The modulus of the position difference vector between wind fields, The default value is greater than 0.

5. A method for peak load regulation of a power system according to claim 1, characterized in that: The determining the output correlation degree of any two wind farms at the current moment includes: Calculate the sum of the output power of all wind turbines in each wind farm at each time, and record it as the total output power; The total output power of each wind farm at multiple moments before the current moment is used to form a power output vector; The wind influence degrees of the arbitrary two wind farms at multiple moments before the current moment are combined into a wind influence vector; and the wind influence vector is normalized to form an influence weight vector; Taking the elements in the influence weight vector as weights, a weighted correlation coefficient of the power output vectors of the arbitrary two wind farms at the current moment is calculated as the output correlation degree of the arbitrary two wind farms at the current moment.

6. A method for peak load regulation of a power system as claimed in claim 5, characterized in that: The determining of the wind field interference degree of each wind field at the current moment includes: A result of normalizing the output correlation between any wind farm and the other wind farms at the current moment is recorded as a correlation weight; Based on the association weight between any one wind farm and the remaining wind farms at the current moment, a weighted sum is taken for the total output power of all the remaining wind farms at the current moment as the wind farm interference degree of any one wind farm at the current moment.

7. A method for peak load regulation of a power system as claimed in claim 5, characterized in that: The real-time control of the output of the thermal power unit includes: Based on the wind farm interference degree and the total output power of each wind farm at the current moment, prediction is performed through a neural network model to obtain a predicted total power of each wind farm after the current moment; Calculate the sum of the predicted total powers of all wind farms at the current moment, and record it as the wind farm predicted power; If the predicted power of the wind farm is less than a preset threshold, the output of the thermal power unit is increased; otherwise, the output of the thermal power unit is reduced.

8. A peak load regulation device for a power system, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of a power system peak regulation method as described in any one of claims 1 to 7 when executing the computer program.

9. A peak load shaving device for a power system, wherein the device stores a computer program, characterized in that: When the computer program is executed by a processor, the steps of a power system peak regulation method as described in any one of claims 1 to 7 are implemented.

10. A power system peak shaving system, using a power system peak shaving method as claimed in claim 1, characterized in that: The system comprises: The data acquisition module is used to obtain the wind direction vector, output power, and position coordinate vector of each wind turbine in each wind farm in real time; The power prediction module obtains the wind vector of each wind turbine at each moment based on the wind direction vector and output power of each wind turbine at each moment; analyzes the degree of deviation of the wind vectors of different wind turbines in each wind farm at each moment, and calculates the wind turbulence degree of each wind farm at each moment; determines the wind influence degree of any two wind farms at each moment by the difference between the position coordinate vectors of any two wind farms at each moment, and the consistency between the overall wind direction of the any two wind farms and the relative distribution direction of their positions, combined with the wind turbulence degree; based on the wind influence degree, analyzes the relevant changes in the output power of all wind turbines between the any two wind farms at multiple moments before the current moment, and determines the output correlation degree of the any two wind farms at the current moment; determines the wind field interference degree of each wind farm at the current moment in combination with the output power of all wind turbines in each wind farm at the current moment; obtains the predicted total power of each wind farm after the current moment based on the wind field interference degree of each wind farm and the output power of all wind turbines at the current moment in combination with the neural network model; The thermal power peak regulation module is used to adjust the output of the thermal power units in real time through the predicted total power of all wind farms at the current moment, so as to perform peak regulation on the power system.

Images