Energy storage capacity configuration method based on wind power imbalance power

Abstract

The invention provides an energy storage capacity configuration method based on wind power unbalanced power, and belongs to the technical field of power systems, and the method comprises the steps: carrying out the preprocessing of historical wind power data according to the historical meteorological data of a target region, dividing the preprocessing data according to the time scale, and obtaining a wind power data set; obtaining a double analysis algorithm under each time scale from the scale-algorithm comparison table, decomposing and analyzing the corresponding divided data to obtain an unbalanced power array of the corresponding time scale, determining unbalanced characteristics under the corresponding time scale based on the unbalanced power array, and optimizing the energy storage capacity configuration model. And a capacity configuration scheme is determined according to the current energy storage demand and the current actual energy storage condition of the target area, and the actual demand of the power system is met.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly to a method for configuring the energy storage capacity based on the unbalanced power of wind power. Background Art

[0002] With the increasing global demand for clean energy, wind power generation, as a clean and renewable energy source, is playing an increasingly important role in the power system. However, due to the randomness and volatility of wind resources, the output power of wind power has significant uncertainties, and this unbalanced power poses many challenges to the stability, reliability, and power quality of the power system.

[0003] To address the impact of the unbalanced power of wind power, configuring an appropriate energy storage system has become an effective solution. Currently, there are some problems in the configuration of the energy storage capacity. For example, most traditional configuration methods are based on empirical data or simple statistical analysis, without fully considering the dynamic change characteristics of wind power and the characteristics of unbalanced power at different time scales, resulting in either an oversized energy storage capacity, causing resource waste and cost increase; or an undersized energy storage capacity, which cannot effectively suppress the unbalanced power of wind power and is difficult to meet the actual needs of the power system.

[0004] Therefore, the present invention proposes a method for configuring the energy storage capacity based on the unbalanced power of wind power. Summary of the Invention

[0005] The present invention provides a method for configuring the energy storage capacity based on the unbalanced power of wind power to solve the above-mentioned technical problems.

[0006] The present invention provides a method for configuring the energy storage capacity based on the unbalanced power of wind power, including: Step 1: Collect the historical wind power data of the target area, and preprocess the historical wind power data according to the historical meteorological data of the target area, where the historical wind power data includes the wind power output under different seasons and different weather conditions; Step 2: Divide the preprocessed data according to the time scale, and obtain the dual analysis algorithms for each time scale from the scale - algorithm comparison table, and decompose and analyze the corresponding divided data respectively to obtain the unbalanced power arrays corresponding to the time scales, where the unbalanced power arrays include N1 unbalanced power components obtained based on the first analysis algorithm and N2 unbalanced power components obtained based on the second analysis algorithm; Step 3: Establish an energy storage capacity configuration model with the constraint condition of meeting the requirement of suppressing the fluctuation of wind power by the power system and the objective function of maximizing the overall life - cycle operation efficiency of the energy storage system; Step 4: Determine the imbalance characteristics at the corresponding time scale based on the imbalance power array, optimize the energy storage capacity configuration model, and determine the capacity configuration plan depending on the current energy storage demand and the current actual energy storage situation in the target area.

[0007] Preferably, preprocess the historical wind power data according to the historical meteorological data of the target area, including: Sort the historical wind power at each historical collection moment in sequence, and determine whether there is missing power; If there is, obtain the historical meteorological data at the missing moment for analysis to obtain the initial filling power; Obtain the first reference power and the first meteorological data at the first non-missing moment closest to the missing moment. At the same time, obtain the second reference power and the second meteorological data at the second non-missing moment second closest to the missing moment; Obtain the first predicted power depending on the first meteorological data and the operation mode of the wind power system at the first non-missing moment. At the same time, obtain the second predicted power depending on the second meteorological data and the operation mode of the wind power system at the second non-missing moment; Perform a first correction on the initial filling power according to the first reference power, the second reference power, the first predicted power, and the second predicted power;

[0008]

[0009]

[0010] Wherein, represents a fine-tuning function; represents the number of similar moments where the similarity between the historical meteorological data Q at the missing moment and the historical meteorological data at each remaining historical collection moment is greater than or equal to 0.9; represents the historical wind power at the jth similar moment; represents a positive and negative function; , represent the first reference power and the first predicted power respectively; represent the second reference power and the second predicted power respectively; represents the power after the first correction; represents the initial filling power; represents the similarity function between the historical meteorological data Q at the missing moment and the first meteorological data at the first non-missing moment; represents the historical meteorological data Q at the missing moment and the second meteorological data Similarity function

[0011] Preferably, after the initial filling power is corrected once, it further includes: Lock continuous time segments according to the time distribution of all similar moments, draw a power curve based on the continuous time segments, and intercept the power curve with the power after the first correction as a straight line to obtain the excess increment of the upper intercepted part and the proportion of the upper intercepted time, the excess decay of the lower intercepted part and the proportion of the lower intercepted time, and perform secondary correction and supplementation on the power after the first correction;

[0012]

[0013]

[0014] Wherein Represents the power after secondary correction; 、 Respectively represent the maximum absolute difference between the upper intercepted part and And the maximum absolute difference between the lower intercepted part and ; 、 Respectively represent the enclosed areas of the upper intercepted part and the lower intercepted part; Represents the total number of historical acquisition moments; Represents the positive and negative function; Is a constant with a value of 1; 、 Respectively represent the proportion of the upper intercepted time and the proportion of the lower intercepted time; Respectively represent the excess decay and the excess increment.

[0015] Preferably, the unbalanced power component of each analysis algorithm is set in advance.

[0016] Preferably, determining the unbalanced characteristics under the corresponding time scale based on the unbalanced power array includes: Randomly shuffle and split the order of the unbalanced power in each unbalanced power array to obtain several new arrays, and extract time domain features from the new arrays; Perform a fast Fourier transform on the new arrays, analyze the main frequency components and assign values to obtain the dominant frequency, quantify the energy distribution of the dominant frequency components, and extract frequency feature parameters; Decompose the new arrays into sub-signals of different frequency bands based on the wavelet basis function and the decomposition level, and obtain the change characteristics of the unbalanced power in time and frequency by analyzing the time-frequency diagram; Fuse the time-domain features, frequency-domain features, and time-frequency domain features, and perform dimensionality reduction processing to obtain feature vectors; Use a clustering algorithm to perform clustering analysis on the clustering vectors to divide the unbalanced power arrays at different time scales into different categories, and determine the unbalanced features of each category by analyzing the feature means and distribution conditions of each category.

[0017] Preferably, optimize the energy storage capacity configuration model, including: Integrate the unbalanced features at different time scales to construct a multi-dimensional feature matrix; Use the grey relational analysis algorithm to calculate the correlation degrees between the features at each time scale, mine the potential connections between the unbalanced features at different time scales, and introduce influence factors reflecting the unbalanced features at each time scale; Refine the constraints in the energy storage capacity configuration model based on the influence factors to achieve optimization.

[0018] Preferably, determine the capacity configuration scheme depending on the current energy storage demand and the current actual energy storage situation in the target area, including: Analyze the current energy storage demand to obtain the power difference between the output power and the electrical load. At the same time, based on several consecutive demands before the current energy storage demand, predict the demand trend after the current energy storage demand; Determine the state of the energy storage system and the charge and discharge capacity according to the current actual energy storage situation; Use the power difference, demand trend, energy storage system state, and charge and discharge capacity as inputs, continuously adjust the values of the energy storage capacity and power, search for the optimal solution that satisfies the constraint conditions and minimizes the objective function, and obtain the current optimal capacity configuration scheme.

[0019] Preferably, the time scales include: ultra-short-term time scale, short-term time scale, and medium- and long-term time scale.

[0020] Compared with the prior art, the beneficial effects of the present application are as follows: After preprocessing, accurate, complete, and standardized historical wind power data can be obtained, which can truly reflect the wind power output of the target area under different seasons and weather conditions. By processing data on different time scales through a dual-analysis algorithm, the unbalance characteristics of wind power within different time ranges can be deeply explored from multiple perspectives, obtaining a comprehensive and detailed unbalanced power array. The established energy storage capacity configuration model is based on the actual power system requirements and the performance of the energy storage system. By optimizing the objective function and following the constraints, a configuration plan can be calculated that maximizes the overall life cycle operation efficiency of the energy storage system while meeting the requirements for suppressing wind power fluctuations. By determining the unbalance characteristics based on the unbalanced power array and optimizing the model, the energy storage capacity configuration model can more accurately reflect the unbalance characteristics of wind power, improving the adaptability and accuracy of the model. Then, combined with the current energy storage demand and actual situation, the capacity configuration plan is determined, realizing the dynamic and accurate configuration of the energy storage capacity, ensuring that the energy storage system can effectively suppress wind power fluctuations at any time and meet the power system requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a flowchart of a method for configuring the energy storage capacity based on the unbalanced wind power in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0024] The present invention provides a method for configuring the energy storage capacity based on the unbalanced wind power, as Figure 1 shown, including: Step 1: Collect historical wind power data of the target area and preprocess the historical wind power data according to the historical meteorological data of the target area, where the historical wind power data includes the wind power output under different seasons and different weather conditions; Step 2: Divide the preprocessed data according to the time scale, and obtain the dual analysis algorithms for each time scale from the scale-algorithm comparison table, and decompose and analyze the corresponding divided data respectively to obtain the unbalanced power array corresponding to the time scale. Among them, the unbalanced power array includes N1 unbalanced power components obtained based on the first analysis algorithm and N2 unbalanced power components obtained based on the second analysis algorithm; Step 3: Establish a energy storage capacity configuration model with the constraint of meeting the requirement of suppressing the fluctuation of wind power in the power system and the objective function of maximizing the overall life cycle operation efficiency of the energy storage system; Step 4: Determine the unbalanced characteristics corresponding to the time scale based on the unbalanced power array, optimize the energy storage capacity configuration model, and determine the capacity configuration plan depending on the current energy storage demand and the current actual energy storage situation in the target area.

[0025] Preferably, the unbalanced power components of each analysis algorithm are set in advance. Preferably, the time scale includes: ultra-short-term time scale, short-term time scale, and medium- and long-term time scale.

[0026] In this embodiment, the target area: a specific wind farm and its surrounding power coverage area, for example, a large wind farm and the regional power grid it is connected to.

[0027] In this embodiment, the historical wind power data refers to the records of the wind power output values at different times of this wind farm in the past period (such as the past 3 years), such as the wind power output at 0:00 on January 1, 2022 is 1000 kW, and the wind power output at 12:00 on July 15, 2022 is 3500 kW, etc., covering power data under various weather conditions such as spring, summer, autumn, winter, sunny days, rainy days, windy days, and thunderstorm days. The meteorological observation data of the target area during the same time period as the historical wind power data, including wind speed (such as the wind speed at 15:00 on March 20, 2022 is 8 m / s), wind direction (such as the wind direction at 9:00 on October 5, 2022 is northwest), temperature (such as the temperature at 0:00 on January 10, 2023 is -20 °C), humidity (such as the humidity at 14:00 on June 25, 2023 is 60%), etc.

[0028] The preprocessing is to fill in the missing data to meet the requirements of subsequent analysis.

[0029] In this embodiment, the ultra-short-term time scale (0 - 4 hours), the short-term time scale (4 - 24 hours), and the medium- and long-term time scale (1 - several days).

[0030] In this embodiment, the scale-algorithm correspondence table is a pre-established table that records the applicable analysis algorithms corresponding to each time scale. For example, the ultra-short-term time scale corresponds to the variational mode decomposition (VMD) algorithm and the improved empirical mode decomposition (EEMD) algorithm; the short-term time scale corresponds to the seasonal decomposition method based on Fourier transform (STL) and the gated recurrent unit-autoregressive integrated moving average model (GRU-ARIMA) hybrid algorithm; the medium- and long-term time scale corresponds to the long short-term memory network-gray prediction model (LSTM-GM) fusion algorithm and the time series analysis method based on wavelet transform. There are two algorithms for analyzing data at each time scale. The array containing multiple unbalanced power components obtained through algorithm analysis is a quantitative representation of the wind power imbalance characteristics.

[0031] In this embodiment, the power change parts that can reflect different frequencies or characteristics obtained after decomposing the wind power data, each component represents a certain characteristic of the wind power imbalance, and its quantity (N1, N2) is determined according to the algorithm and data characteristics and is set in advance.

[0032] In this embodiment, the requirement for suppressing the wind power fluctuation by the power system is the limit standard set for the wind power fluctuation range, fluctuation frequency, etc. to ensure the stable operation of the power system. For example, it is required that the wind power volatility does not exceed 10% within a certain time period, or the power change rate does not exceed a certain value (such as 50 kW / min).

[0033] In this embodiment, the full-life cycle operation efficiency of the energy storage system is an index to measure the comprehensive performance of the energy storage system in the entire usage cycle, including energy storage and release efficiency, operation stability, maintenance cost, etc. The maximum operation efficiency means that on the premise of meeting the requirements of the power system, the energy storage system achieves the highest energy utilization rate, the lowest cost, and the best benefit in the full-life cycle.

[0034] In this embodiment, the energy storage capacity configuration model is a mathematical model established based on the objective function and constraint conditions, and is used to calculate and determine the optimal capacity and power configuration scheme of the energy storage system.

[0035] In this embodiment, the imbalance characteristics are parameters or patterns extracted from the unbalanced power array that can reflect the essential imbalance characteristics of wind power at different time scales, such as the high-frequency fluctuation intensity in the ultra-short term, the periodic change law in the short term, and the trend in the medium- and long-term. Adjust and improve the structure, parameters, objective function, etc. of the energy storage capacity configuration model to make it more in line with the actual needs and improve the accuracy and practicality of the model.

[0036] In this embodiment, the capacity configuration scheme is a scheme for determining specific configuration parameters such as the capacity size (e.g., 1000 kWh) and power parameters (e.g., 500 kW) of the energy storage system, and is used to guide the construction and operation of the energy storage system.

[0037] The beneficial effects of the above technical solution are as follows: After preprocessing, accurate, complete, and standardized historical wind power data is obtained, which can truly reflect the wind power output of the target area under different seasons and weather conditions. By processing data on different time scales through a dual analysis algorithm, the unbalance characteristics of wind power within different time ranges can be deeply explored from multiple perspectives, and a comprehensive and detailed unbalanced power array can be obtained. The established energy storage capacity configuration model is based on the actual power system requirements and the performance of the energy storage system. By optimizing the objective function and following the constraints, a configuration scheme that maximizes the full-life cycle operation efficiency of the energy storage system under the requirement of suppressing wind power fluctuations can be calculated. By determining the unbalance characteristics based on the unbalanced power array and optimizing the model, the energy storage capacity configuration model can more accurately reflect the unbalance characteristics of wind power, improving the adaptability and accuracy of the model. Combining with the current energy storage demand and actual situation to determine the capacity configuration scheme realizes the dynamic and accurate configuration of the energy storage capacity, ensuring that the energy storage system can effectively suppress wind power fluctuations at any time and meet the power system requirements.

[0038] The present invention provides a method for configuring the energy storage capacity based on wind power unbalance power. The historical wind power data is preprocessed according to the historical meteorological data of the target area, including: Sorting the historical wind power at each historical collection moment in sequence, and determining whether there is missing power; If there is, obtaining the historical meteorological data at the missing moment for analysis to obtain the initial filling power; Obtaining the first reference power and the first meteorological data at the first non-missing moment closest to the missing moment, and at the same time, obtaining the second reference power and the second meteorological data at the second non-missing moment second closest to the missing moment; Depending on the first meteorological data and the operation mode of the wind power system at the first non-missing moment to obtain the first predicted power, and at the same time, depending on the second meteorological data and the operation mode of the wind power system at the second non-missing moment to obtain the second predicted power; Performing a first correction on the initial filling power according to the first reference power, the second reference power, the first predicted power, and the second predicted power;

[0039]

[0040]

[0041] Among them, represents the fine-tuning function; represents the number of similar moments where the similarity between the historical meteorological data Q at the missing moment and the historical meteorological data at each remaining historical collection moment is greater than or equal to 0.9; represents the historical wind power at the j-th similar moment; represents the positive and negative function; , respectively represent the first reference power and the first predicted power; respectively represent the second reference power and the second predicted power; represents the power after the first correction; represents the initial filling power; represents the similarity function between the historical meteorological data Q at the missing moment and the first meteorological data at the first non-missing moment ; represents the similarity function between the historical meteorological data Q at the missing moment and the second meteorological data at the second non-missing moment ;

[0042] In this embodiment, by introducing multiple variables related to similar historical meteorological data, the influence of power reference values and predicted power values at different moments is comprehensively considered. is based on the principle that wind power is similar under similar meteorological conditions. By statistically analyzing the power under similar conditions, it provides a basis for correction. Divide by is to calculate the average value of the power at these similar moments, making the result more representative. After adding C (the initial filling power) and then dividing by 2, it comprehensively considers the power situation at similar moments on the basis of the initial filling power, balancing the relationship between the initial estimate and the statistical situation of similar cases.

[0043] Calculates the average value of the absolute values of the differences between the two reference powers and the corresponding predicted powers, reflecting the deviation degree between the reference power and the predicted power. Multiply by is to use the minimum value of the similarities between the meteorological data at the missing moment and the meteorological data at two adjacent non-missing moments to weight the deviation degree. The lower the similarity, the greater the difference in meteorological conditions. Even if the deviation between the reference power and the predicted power is large, this deviation cannot be overly relied on for correction. Through this weighting method, the fine-tuning is made more reasonable.

[0044] The beneficial effects of the above technical solution are as follows: filling and correcting the missing wind power data can effectively improve the integrity of the historical wind power data. By reasonably correcting the missing power data, the unbalanced power array and unbalanced characteristics determined based on these data subsequently are more accurate. Furthermore, when optimizing the energy storage capacity configuration model, it can more accurately reflect the actual fluctuations of wind power, making the constraint conditions and objective function of the configuration model more in line with the actual situation.

[0045] The present invention provides a method for configuring the energy storage capacity based on the wind power imbalance power. After performing a first correction on the initial filled power, it further includes: Locking a continuous time segment according to the time distribution of all similar moments, plotting a power curve based on the continuous time segment, and intercepting the power curve with the power after the first correction as a straight line to obtain the excess increment of the upper intercepted part and the proportion of the upper intercepted moment, the excess decay of the lower intercepted part and the proportion of the lower intercepted moment, and performing a second correction and supplementation on the power after the first correction;

[0046]

[0047]

[0048] Wherein, represents the power after the second correction; and respectively represent the maximum absolute difference between the upper intercepted part and , and the maximum absolute difference between the lower intercepted part and ; and respectively represent the enclosed areas of the upper intercepted part and the lower intercepted part; represents the total number of historical acquisition moments; represents the positive and negative function; is a constant with a value of 1; and respectively represent the proportion of the upper intercepted moment and the proportion of the lower intercepted moment; respectively represent the excess decay and the excess increment.

[0049] In this embodiment, the excess increment refers to the average value of the absolute values of the differences between the power values at each moment in the upper intercepted part and the power after the first correction.

[0050] The excess decay refers to the average value of the absolute values of the differences between the power values at each moment in the lower intercepted part and the power after the first correction.

[0051] In this embodiment, the time proportion is the number of moments involved in the corresponding intercepted part / the total number of moments.

[0052] In this embodiment, Taking into comprehensive consideration the time proportions of the upper intercepted part and the lower intercepted part, as well as the excess increment and the excess decay, reflecting the difference in the time proportions of the upper and lower intercepted moments, multiplying by is the difference in the excess power of the upper and lower parts combined, used to measure the power amplitude that needs to be further adjusted.

[0053] According to the positive or negative value to determine the value, accurately judging the adjustment direction, and ensuring that the secondary correction can reasonably determine whether to adjust the power value in the positive or negative direction according to the area difference between the upper and lower parts of the power curve and other situations.

[0054] The beneficial effects of the above technical solution are: Through secondary correction, combining information such as the time proportions, excess increments, and decays of the upper and lower intercepted parts of the power curve, the power value can be adjusted more meticulously, making the filled power data more in line with the actual power change trend and improving the accuracy of the power data.

[0055] The present invention provides a method for configuring the energy storage capacity based on the unbalanced power of wind power. Based on the unbalanced power array, the unbalanced characteristics under the corresponding time scale are determined, including: Randomly shuffling and splitting the order of the unbalanced power in each unbalanced power array to obtain several new arrays, and extracting time domain features from the new arrays; Performing a fast Fourier transform on the new arrays, analyzing the main frequency components and assigning values to obtain the dominant frequency, quantifying the energy distribution of the dominant frequency components, and extracting frequency feature parameters; Based on the wavelet basis function and the decomposition level, decomposing the new arrays into sub-signals of different frequency bands, and obtaining the change characteristics of the unbalanced power in terms of time and frequency by analyzing the time-frequency diagram; Fusing the time domain features, frequency domain features, and time-frequency domain features, and performing dimensionality reduction processing to obtain feature vectors; Using a clustering algorithm to perform clustering analysis on the clustering vectors to divide the unbalanced power arrays under different time scales into different categories, and determining the unbalanced characteristics of each category by analyzing the feature means and distribution situations of each category.

[0056] In this embodiment, an unbalanced array, for example: [10kW, 15kW, 8kW, 12kW, 9kW], after the order is randomly changed to [12kW, 9kW, 15kW, 8kW, 10kW], can be split into [12kW, 9kW], [15kW, 8kW], [10kW] to obtain several new arrays. Using a random function in a computer programming language, such as the random.shuffle() function in Python, randomly rearrange the order of elements in the unbalanced power array.

[0057] In this embodiment, the numpy.fft.fft() function in Python performs a fast Fourier transform on the new array to obtain frequency-domain data, analyzes the magnitude of each frequency component in the frequency-domain data, finds the main frequency components with larger magnitudes, determines the dominant frequency with the largest magnitude among them, and calculates frequency characteristic parameters according to the dominant frequency and the energy values of other frequency components. For example, the proportion of the main frequency energy is obtained by dividing the main frequency energy by the total energy.

[0058] In this embodiment, signals in different frequency bands obtained after wavelet transform decomposition. For example, the new array [12kW, 9kW, 15kW, 8kW, 10kW] is decomposed based on the db4 wavelet basis function with a decomposition level of 3 to obtain a low-frequency sub-signal [10kW, 11kW], a mid-frequency sub-signal [3kW, 2kW], and a high-frequency sub-signal [1kW, 0.5kW].

[0059] In this embodiment, the time-frequency diagram uses time as the horizontal axis and frequency as the vertical axis to display the energy distribution image of the signal at different times and frequencies. It can be seen from the time-frequency diagram which frequency components are dominant at a certain moment.

[0060] In this embodiment, assume that the time-domain characteristics are a mean of 10kW and a variance of 2kW². Frequency-domain characteristics: such as the proportion of the main frequency energy is 40%, and the proportion of the high-frequency energy is 10%, etc. Time-frequency domain characteristics: for example, the energy density value in a specific area of the time-frequency diagram, etc.

[0061] In this embodiment, after combining the mean and variance of the time-domain characteristics, the proportion of the main frequency energy and the proportion of the high-frequency energy of the frequency-domain characteristics, the energy density value of the time-frequency domain characteristics, etc., reduce the dimension through an algorithm. For example, use the principal component analysis (PCA) algorithm to convert the high-dimensional features into low-dimensional feature vectors. For example, the two-dimensional vector [0.5, 0.3] which synthesizes the key information of the time domain, frequency domain, and time-frequency domain.

[0062] In this embodiment, the clustering algorithm uses the K-means clustering algorithm, and different groups are divided through the clustering algorithm. Assume that the K-means clustering algorithm is used to divide the feature vectors into 3 categories, namely category A, category B, and category C.

[0063] In this embodiment, for the feature vectors in each category, the mean value of each dimension is calculated. For example, if the values of the feature vectors in category A on the first dimension are 0.4, 0.5, and 0.6, then the feature mean of this dimension is (0.4 + 0.5 + 0.6) ÷ 3 = 0.5. The distribution describes the distribution pattern of the feature vectors in the feature space, such as whether they are concentrated or discrete. Category A may represent unbalanced features with high-frequency fluctuations and large fluctuation amplitudes.

[0064] The beneficial effects of the above technical solution are as follows: Random shuffling and splitting can break the sequential correlation of the original data, increase the randomness and diversity of the data, and help to more comprehensively mine data features. Through fast Fourier transform and correlation analysis, the characteristics of unbalanced power can be revealed from the frequency dimension, and the frequency components that play a major role in power fluctuations can be found. Wavelet transform can analyze unbalanced power simultaneously in both the time and frequency dimensions. Compared with pure time-domain or frequency-domain analysis, it can capture the local characteristics of the signal more comprehensively. Feature fusion can comprehensively utilize feature information in different dimensions to comprehensively describe the characteristics of unbalanced power. Cluster analysis can divide unbalanced power arrays with similar unbalanced characteristics into the same category to achieve classification management and analysis of unbalanced power. The unbalanced features determined by analyzing the feature means and distribution of each category help to more clearly understand different types of wind power unbalance situations.

[0065] The present invention provides a method for configuring the energy storage capacity based on wind power unbalance power, and optimizes the energy storage capacity configuration model, including: Integrate unbalanced features at different time scales to construct a multi-dimensional feature matrix; Use the grey relational analysis algorithm to calculate the correlation degree between the features at each time scale, mine the potential relationship between unbalanced features at different time scales, and introduce influence factors reflecting the unbalanced features at each time scale; Based on the influence factors, refine the constraints in the energy storage capacity configuration model to achieve optimization.

[0066] In this embodiment, the value measuring the degree of tight correlation between two or more features generally ranges from 0 to 1. For example, the calculation result of the correlation degree between the ultra-short-term high-frequency fluctuation intensity and the short-term periodic fluctuation amplitude is 0.6, indicating that there is a certain correlation between the two.

[0067] The hidden and not easily directly observable relationship between unbalanced features at different time scales. For example, ultra-short-term high-frequency fluctuations may affect the short-term power fluctuation period to a certain extent, and this influence relationship is the potential connection.

[0068] The coefficient determined based on the correlation degree and potential connection between the characteristics of each time scale is used to measure the influence degree of a certain time scale characteristic on the energy storage capacity configuration model. For example, the influence factor of the ultra-short-term characteristic may be 0.3, indicating its relative importance in the model.

[0069] In this embodiment, the formula for the correlation coefficient is as follows:

[0070] Among them, x0(k) is the value of the reference sequence at time k, xi(k) is the value of the comparison sequence at time k, ρ is the resolution coefficient (generally taken as 0.5), and the average value of the correlation coefficients is calculated to obtain the correlation degree.

[0071] Based on the calculated correlation degree, combined with professional knowledge and practical experience, analyze the potential connection between different time scale characteristics. For example, it is found that the correlation degree between the ultra-short-term high-frequency fluctuation intensity and the short-term periodic fluctuation amplitude is relatively high, which may mean that the ultra-short-term high-frequency fluctuation will affect the short-term fluctuation period. Then, according to the size of the correlation degree and the importance of the potential connection, determine the influence factor of each time scale characteristic. The characteristic with a high correlation degree and a large impact on energy storage configuration has a relatively large influence factor.

[0072] In this embodiment, the influence factor of the ultra-short-term characteristic is 0.3, the influence factor of the short-term characteristic is 0.2, and the influence factor of the medium- and long-term characteristic is 0.5.

[0073] In this embodiment, according to the influence factor of the ultra-short-term characteristic, adjust the instantaneous power change rate limit in the power constraint; according to the influence factor of the medium- and long-term characteristic, modify the long-term capacity adjustment range in the capacity constraint, which is the refinement process. The relatively high influence factor of the ultra-short-term characteristic indicates that the ultra-short-term imbalance characteristic has a high requirement for the power response speed of the energy storage system. Then, it is necessary to focus on adjusting the instantaneous power change rate limit in the power constraint; the relatively large influence factor of the medium- and long-term characteristic means that the medium- and long-term imbalance characteristic has a great impact on the long-term planning of the energy storage capacity, and attention should be paid to the adjustment of the capacity constraint. If the influence factor of the ultra-short-term characteristic is large, reduce the instantaneous power change rate limit value, such as adjusting it from the original 50kW / min to 30kW / min to better adapt to the power change requirements of ultra-short-term high-frequency fluctuations; if the influence factor of the medium- and long-term characteristic is large, appropriately expand the capacity adjustment range in the capacity constraint according to the medium- and long-term trend changes, such as increasing the capacity upper limit from 80% of the rated capacity to 90%.

[0074] The beneficial effects of the above technical solution are as follows: By integrating and constructing a multi-dimensional feature matrix, the unbalanced features at different time scales can be systematically sorted out and presented, making this feature information clearer and more organized. Using the grey relational analysis algorithm can quantitatively analyze the correlation degree between the unbalanced features at different time scales, and potential connections can be mined. By refining the constraints on the energy storage capacity configuration model based on the influencing factors, the constraint conditions of the model can be more in line with the actual situation of the unbalanced features at different time scales.

[0075] The present invention provides a method for configuring the energy storage capacity based on the unbalanced power of wind power. Depending on the current energy storage demand and the current actual energy storage situation in the target area, a capacity configuration plan is determined, including: Analyze the current energy storage demand to obtain the power difference between the output power and the electricity load. At the same time, based on several consecutive demands before the current energy storage demand, predict the demand trend after the current energy storage demand; Determine the energy storage system state and the charge and discharge capacity according to the current actual energy storage situation; Taking the power difference, demand trend, energy storage system state, and charge and discharge capacity as inputs, continuously adjust the values of the energy storage capacity and power, search for the optimal solution that satisfies the constraint conditions and minimizes the objective function, and obtain the current optimal capacity configuration plan.

[0076] In this embodiment, for demand trend prediction: Time series prediction algorithms are used, such as exponential smoothing method, long short-term memory network (LSTM), etc. Taking LSTM as an example, first normalize several consecutive demand data before the current energy storage demand, and then use it as the input of the LSTM network. The LSTM model that has been trained is used to predict the demand in the short term in the future. When training the model, historical data is used for training, and the model parameters are adjusted to minimize the prediction error.

[0077] In this embodiment, the energy storage system state: mainly refers to indicators such as the SOC and SOH of the battery that reflect the health and available state of the energy storage system. The charge and discharge capacity: The maximum charge power, maximum discharge power, and continuous charge and discharge time that the energy storage system can achieve safely and efficiently in the current state. For example, in the current state of this energy storage system, the maximum charge power is 150kW, which means that under other conditions, up to 150kWh of electricity can be charged per hour; the maximum discharge power is 200kW, and the continuous discharge time is 2 hours, indicating that when discharging at a power of 200kW, it can last for up to 2 hours.

[0078] In this embodiment, the optimal solution: The combination of the values of the energy storage capacity and power that satisfies all the constraint conditions and minimizes the objective function. For example, when the energy storage capacity is 1200kWh and the power is 180kW, the value of the objective function is the smallest, and this combination is the optimal solution.

[0079] The beneficial effects of the above technical solution are as follows: By taking multiple key factors as inputs for optimization calculation, an optimal capacity configuration solution that comprehensively considers current requirements, system status, and future trends can be obtained. While meeting the requirements of the power system for suppressing wind power fluctuations, this solution minimizes the total life cycle cost of the energy storage system, improving the economy and operating efficiency of the energy storage system.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. However, such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for configuring the energy storage capacity based on the unbalanced power of wind power, characterized in that Including: Step 1: Collect historical wind power data of the target area, and preprocess the historical wind power data according to the historical meteorological data of the target area. Among them, the historical wind power data includes wind power output under different seasons and different weather conditions; Step 2: Divide the preprocessed data according to the time scale, and obtain the double analysis algorithms at each time scale from the scale - algorithm comparison table, and decompose and analyze the corresponding divided data respectively to obtain the unbalanced power array corresponding to the time scale. Among them, the unbalanced power array contains N1 unbalanced power components obtained based on the first analysis algorithm and N2 unbalanced power components obtained based on the second analysis algorithm; Step 3: Establish a storage capacity configuration model with the constraint of meeting the requirement of suppressing the fluctuation of wind power by the power system and the objective function of maximizing the full - life - cycle operation efficiency of the energy storage system; Step 4: Determine the unbalanced characteristics corresponding to the time scale based on the unbalanced power array, optimize the storage capacity configuration model, and determine the capacity configuration scheme depending on the current energy storage demand and the current actual energy storage situation of the target area.

2. The configuration method of the energy storage capacity based on the unbalanced power of wind power according to claim 1, characterized in that Preprocessing the historical wind power data according to the historical meteorological data of the target area includes: Sequentially sort the historical wind power at each historical collection moment, and judge whether there is missing power; If there is, obtain the historical meteorological data at the missing moment for analysis to obtain the initial filling power; Obtain the first reference power and the first meteorological data at the first non - missing moment closest to the missing moment, and at the same time, obtain the second reference power and the second meteorological data at the second non - missing moment second - closest to the missing moment; Depend on the first meteorological data and the operation mode of the wind power system at the first non - missing moment to obtain the first predicted power, and at the same time, depend on the second meteorological data and the operation mode of the wind power system at the second non - missing moment to obtain the second predicted power; According to the first reference power, the second reference power, the first predicted power and the second predicted power, perform a first correction on the initial filling power; Among them, represents the fine-tuning function; represents the number of similar moments where the similarity between the historical meteorological data Q at the missing moment and the historical meteorological data at each remaining historical collection moment is greater than or equal to 0.9; represents the historical wind power at the j-th similar moment; represents the positive and negative function; , respectively represent the first reference power and the first predicted power; respectively represent the second reference power and the second predicted power; represents the power after the first correction; represents the initial filling power; represents the similarity function between the historical meteorological data Q at the missing moment and the first meteorological data at the first non-missing moment ; represents the similarity function between the historical meteorological data Q at the missing moment and the second meteorological data at the second non-missing moment ; 3. The configuration method of the energy storage capacity based on the unbalanced power of wind power according to claim 2, wherein, After performing a first correction on the initial filling power, it further includes: Lock the continuous time segment according to the time distribution of all similar moments, draw the power curve based on the continuous time segment, and intercept the power curve with the power after the first correction as a straight line to obtain the excess increment of the upper - intercepted part and the proportion of the upper - intercepted moment, the excess decay of the lower - intercepted part and the proportion of the lower - intercepted moment, and perform a second correction and filling on the power after the first correction; Among them, represents the power after the second correction; , respectively represent the maximum absolute difference existing in the upper intercepted part and and the maximum absolute difference existing in the lower intercepted part and ; , respectively represent the enclosed areas of the upper intercepted part and the lower intercepted part; represents the total number of historical acquisition moments; represents the positive and negative function; is a constant with a value of 1; , respectively represent the proportion of the upper intercepted moment and the proportion of the lower intercepted moment; respectively represent the redundant attenuation and the redundant increment.

4. The configuration method of the energy storage capacity based on the unbalanced power of wind power according to claim 1, characterized in that The unbalanced power components of each analysis algorithm are set in advance.

5. The configuration method of the energy storage capacity based on the unbalanced power of wind power according to claim 1, wherein, Determining the unbalanced characteristics corresponding to the time scale based on the unbalanced power array includes: Randomly shuffle and split the order of the unbalanced power in each unbalanced power array to obtain several new arrays, and extract the time - domain characteristics of the new arrays; Perform a fast Fourier transform on the new array, analyze the main frequency components and assign values to obtain the dominant frequency, quantify the energy distribution of the dominant frequency components, and extract frequency characteristic parameters; Decompose the new array into sub-signals of different frequency bands based on the wavelet basis function and the decomposition level, and obtain the change characteristics of the unbalanced power in terms of time and frequency by analyzing the time-frequency diagram; Fuse the time domain characteristics, frequency domain characteristics, and time-frequency domain characteristics, and perform dimensionality reduction processing to obtain feature vectors; Use a clustering algorithm to perform clustering analysis on the clustering vectors to divide the unbalanced power arrays at different time scales into different categories, and determine the unbalanced characteristics of each category by analyzing the characteristic means and distribution of each category; 6. The method for configuring the energy storage capacity based on the unbalanced power of wind power according to claim 1, wherein Optimize the energy storage capacity configuration model, including: Integrate the unbalanced characteristics at different time scales to construct a multi-dimensional feature matrix; Apply the grey relational analysis algorithm to calculate the correlation degrees between the characteristics at different time scales, explore the potential relationships between the unbalanced characteristics at different time scales, and introduce influence factors reflecting the unbalanced characteristics at each time scale; Refine the constraints in the energy storage capacity configuration model based on the influence factors to achieve optimization; 7. The configuration method of the energy storage capacity based on the unbalanced power of wind power according to claim 1, characterized in that Depend on the current energy storage demand and the current actual energy storage situation in the target area to determine the capacity configuration plan, including: Analyze the current energy storage demand to obtain the power difference between the output power and the electricity load. At the same time, based on several consecutive demands before the current energy storage demand, predict the demand trend after the current energy storage demand; Determine the energy storage system state and charge-discharge capacity according to the current actual energy storage situation; Take the power difference, demand trend, energy storage system state, and charge-discharge capacity as inputs, continuously adjust the values of the energy storage capacity and power, search for the optimal solution that satisfies the constraint conditions and minimizes the objective function, and obtain the current optimal capacity configuration plan; 8. The method for configuring the energy storage capacity based on the unbalanced power of wind power according to claim 1, wherein, The time scales include: ultra-short-term time scale, short-term time scale, and medium- and long-term time scale.

Images