Wind power outage early warning method, device and equipment and storage medium

Abstract

This application relates to a method, apparatus, equipment, and storage medium for wind power outage early warning. The method includes: first, acquiring data from ground meteorological observation stations and wind farm data; then, calculating the annual maximum wind power outage capacity sequence based on the acquired data; next, calculating the wind power outage capacity recurrence level under different return periods based on the annual maximum wind power outage capacity sequence; and finally, determining the wind power outage early warning level based on the predicted low-temperature wind power outage capacity and the recurrence level. This method can determine the wind power outage early warning level and obtain a quantitative value for the early warning level, facilitating grid dispatching departments in preparing emergency plans based on the early warning level.

Description

Technical Field

[0001] This application relates to the field of power system dispatching and operation technology, and in particular to a wind power outage early warning method, device, equipment and storage medium. Background Technology

[0002] With the global energy structure shifting towards low-carbon development and the continuous optimization of energy consumption patterns, wind power, due to its abundant resources, environmental friendliness, and high degree of automation in operation and management, has become one of the most widely developed and applied renewable energy sources. However, in recent years, several regional power grids in northern China have experienced several large-scale outages and grid disconnections of wind power equipment due to extreme cold waves and low temperatures, putting enormous pressure on power supply.

[0003] Currently, wind power grid dispatch lacks a corresponding early warning mechanism for low temperatures, making it impossible to quantitatively assess the severity of wind power outages caused by low temperatures. Summary of the Invention

[0004] Therefore, it is necessary to provide a wind power outage early warning method, device, equipment, and storage medium that can quantitatively assess the early warning level, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a wind power outage early warning method. The method includes: acquiring data from ground meteorological observation stations and wind farm data; calculating the annual maximum wind power outage capacity sequence based on the ground meteorological observation station data and wind farm data; calculating the wind power outage capacity recurrence level under different return periods based on the annual maximum wind power outage capacity sequence; and determining the wind power outage early warning level based on the predicted wind power outage capacity at low temperatures and the recurrence level.

[0006] In one embodiment, the ground meteorological station data includes the geographical location of the ground meteorological station and the daily minimum temperature data of the ground meteorological station. The wind farm data includes the geographical location of the wind farm, the rated capacity of each wind turbine in the wind farm, and the low temperature protection setting of each wind turbine. Based on the ground meteorological station data and the wind farm data, the annual maximum wind power outage capacity sequence is calculated, including: modeling based on Thiessen polygons; obtaining the daily minimum temperature data of each wind turbine based on the geographical location of the ground meteorological station, the daily minimum temperature data of the ground meteorological station, and the geographical location of the wind farm; and calculating the annual maximum wind power outage capacity sequence based on the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine, and the daily minimum temperature data of each wind turbine.

[0007] In one embodiment, the wind power outage capacity recurrence level under different return periods is calculated based on the annual maximum wind power outage capacity sequence, including: obtaining a distribution parameter sample based on the annual maximum wind power outage capacity sequence using the Markov chain Monte Carlo method; and calculating the wind power outage capacity recurrence level under different return periods based on the distribution parameter sample.

[0008] In one embodiment, based on the Markov chain Monte Carlo method, a distribution parameter sample is obtained according to the annual maximum wind power outage capacity sequence, including: obtaining the input parameters of the Markov chain Monte Carlo method, including the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations; and performing iterative calculations based on the input parameters and the annual maximum wind power outage capacity sequence to obtain the distribution parameter sample.

[0009] In one embodiment, the wind power outage capacity recurrence level is calculated based on the distribution parameter sample, including: calculating a sample set of wind power outage capacity recurrence levels for a preset recurrence period based on the distribution parameter sample; and determining different quantiles of the recurrence level for the preset recurrence period based on the sample set of recurrence levels.

[0010] In one embodiment, the early warning level for wind power outage is determined based on the predicted value of wind power outage capacity at low temperatures and the recurrence level, including: determining the first quantile of the recurrence level for early warning based on a preset judgment criterion; and determining the early warning level for wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0011] Secondly, this application also provides a wind power outage early warning device. The device includes:

[0012] The acquisition module is used to acquire data from ground meteorological observation stations and wind farms;

[0013] The first calculation module is used to calculate the annual maximum wind power outage capacity sequence based on ground meteorological observation station data and wind farm data;

[0014] The second calculation module is used to calculate the wind power outage capacity recurrence level under different recurrence periods based on the annual maximum wind power outage capacity sequence.

[0015] The determination module is used to determine the early warning level of wind power outage based on the predicted value and recurrence level of wind power outage capacity at low temperatures.

[0016] In one embodiment, the ground meteorological observation station data includes the geographical location of the ground meteorological observation station and the daily minimum temperature data of the ground meteorological observation station; the wind farm data includes the geographical location of the wind farm, the rated capacity of each wind turbine in the wind farm, and the low temperature protection setting of each wind turbine; the first calculation module is specifically used to perform modeling based on Thiessen polygons, and obtain the daily minimum temperature data of each wind turbine according to the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station, and the geographical location of the wind farm; and calculate the annual maximum wind power outage capacity sequence according to the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine, and the daily minimum temperature data of each wind turbine.

[0017] In one embodiment, the second calculation module is specifically used to obtain a distribution parameter sample based on the annual maximum wind power outage capacity sequence using the Markov chain Monte Carlo method; and to calculate the wind power outage capacity recurrence level under different return periods based on the distribution parameter sample.

[0018] In one embodiment, the second calculation module is specifically used to obtain the input parameters of the Markov chain Monte Carlo method. The input parameters include the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations. Based on the input parameters and the annual maximum wind power outage capacity sequence, iterative calculations are performed to obtain a distribution parameter sample.

[0019] In one embodiment, the second calculation module is specifically used to calculate the recurrence level sample set of wind power outage capacity with a preset recurrence period based on the distribution parameter sample; and to determine the different quantiles of the recurrence level with the preset recurrence period based on the recurrence level sample set.

[0020] In one embodiment, the determining module is specifically used to determine the first quantile of the recurrence level for early warning based on a preset judgment criterion; and to determine the early warning level of wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0021] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the aforementioned wind power outage early warning method.

[0022] Fourthly, this application also provides a computer-readable storage medium. This computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the aforementioned wind power outage early warning method.

[0023] Fifthly, this application also provides a computer program product. This computer program product includes a computer program that, when executed by a processor, provides the aforementioned wind power outage early warning method.

[0024] The aforementioned wind power outage early warning method, device, equipment, and storage medium first acquire data from ground meteorological observation stations and wind farms. Then, based on the acquired data, they calculate the annual maximum wind power outage capacity sequence. Next, they calculate the recurrence level of wind power outage capacity under different return periods based on the annual maximum wind power outage capacity sequence. Finally, based on the predicted value and recurrence level of wind power outage capacity at low temperatures, they determine the wind power outage early warning level. This method, by using ground meteorological observation data and wind farm data, can obtain the recurrence level of wind power outage capacity under different return periods. Then, based on the predicted value and recurrence level of wind power outage capacity at low temperatures, the early warning level of wind power outage can be determined. Therefore, a quantitative early warning level can be obtained, facilitating the grid dispatching department to prepare emergency plans based on the early warning level. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a wind power outage early warning method in one embodiment;

[0026] Figure 2 This is a flowchart illustrating the steps for calculating the annual maximum wind power outage capacity sequence in another embodiment;

[0027] Figure 3 This is a flowchart illustrating the horizontal calculation steps in another embodiment;

[0028] Figure 4 This is a flowchart illustrating the horizontal calculation steps in another embodiment;

[0029] Figure 5 This is a flowchart illustrating the horizontal calculation steps in another embodiment;

[0030] Figure 6 This is a flowchart illustrating the warning level determination step in another embodiment;

[0031] Figure 7 This is a flowchart illustrating the wind power outage early warning method in another embodiment;

[0032] Figure 8 This is a diagram showing the result of Thiessen polygon partitioning in another embodiment;

[0033] Figure 9 This is a graph showing the results of the maximum wind power outage capacity during low temperatures in another embodiment.

[0034] Figure 10 This is a structural block diagram of a wind power outage early warning device in one embodiment;

[0035] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0037] In one embodiment, such as Figure 1 As shown, a wind power outage early warning method is provided. The method is illustrated using a terminal as an example. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The method includes the following steps:

[0038] Step 101: The terminal acquires data from ground meteorological observation stations and wind farm data.

[0039] The data from ground-based meteorological observation stations can include their geographical location and daily minimum temperature data. Wind farms can include multiple wind turbines, and their data can include the wind farm's geographical location, the rated capacity of each wind turbine, and the low-temperature protection settings for each turbine. All wind turbines in the wind farm are located at the same geographical location as the wind farm itself. The low-temperature protection settings are used to protect the wind turbines from low temperatures; when the ambient temperature is detected to be below the low-temperature protection setting, the wind turbine is shut down.

[0040] Step 102: The terminal calculates the annual maximum wind power outage capacity sequence based on ground meteorological observation station data and wind farm data.

[0041] In this sequence, each data point represents the maximum annual wind power outage capacity. For example, over a 5-year period, the maximum annual wind power outage sequence could be {10, 30, 23, 18, 9}. This means that in the first year, the maximum low-temperature outage capacity is 10GW, in the second year it is 30GW, and so on. Based on the ground meteorological station data and wind farm data obtained in the previous step, the daily minimum temperature data for each wind turbine in the wind farm can be obtained, thus yielding the low-temperature outage capacity for each wind turbine. Summing the low-temperature outage capacities of all wind turbines in a given region gives the daily wind power outage capacity sequence for that region. Extracting the maximum value from this sequence yields the annual maximum wind power outage capacity for that region.

[0042] Step 103: The terminal calculates the wind power outage capacity recurrence level under different recurrence periods based on the annual maximum wind power outage capacity sequence.

[0043] Here, "recurrence" means the recurrence of something, and different recurrence periods refer to different times when it will recur. For example, a recurrence period of 5 means "once in 5 years". The annual maximum wind power outage capacity of a certain region obtained above is fitted. Optionally, a generalized extreme value distribution model is used for fitting. Based on the parameter samples obtained from the generalized extreme value distribution, the recurrence level of wind power outage capacity under different recurrence periods can be calculated.

[0044] Step 104: The terminal determines the early warning level of wind power outage based on the predicted value and recurrence level of wind power outage capacity at low temperatures.

[0045] The wind power low-temperature outage capacity forecast is the capacity of wind turbines that will be shut down due to low temperatures, obtained from the forecast of future cold waves and low temperatures. Based on this wind power low-temperature outage capacity forecast and the recurrence level, the warning level of the impact of cold waves and low temperatures on wind power outages can be determined. If it is a "once-in-a-few-years" event, a quantitative warning level can be obtained.

[0046] The aforementioned wind power outage early warning method first acquires data from ground meteorological observation stations and wind farms. Then, based on this data, it calculates the annual maximum wind power outage capacity sequence. Next, it calculates the recurrence level of wind power outage capacity under different return periods based on the annual maximum wind power outage capacity sequence. Finally, it determines the wind power outage early warning level based on the predicted value and recurrence level of wind power outage capacity at low temperatures. This method, by using ground meteorological observation data and wind farm data to obtain the recurrence level of wind power outage capacity under different return periods, and then determining the wind power outage early warning level based on the predicted value and recurrence level of wind power outage capacity at low temperatures, provides a quantitative early warning level, facilitating grid dispatching departments in preparing emergency plans accordingly.

[0047] In one embodiment, the ground meteorological station data includes the geographical location of the ground meteorological station and the daily minimum temperature data of the ground meteorological station; the wind farm data includes the geographical location of the wind farm, the rated capacity of each wind turbine in the wind farm, and the low-temperature protection setting of each wind turbine. The steps for calculating the annual maximum wind power outage capacity sequence based on the acquired data are as follows: Figure 2 As shown, it includes:

[0048] Step 201: The terminal performs modeling based on Thiessen polygons, and obtains the daily minimum temperature data of each wind turbine unit according to the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station, and the geographical location of the wind farm.

[0049] A wind farm can include multiple wind turbines, and the geographical location of all wind turbines in the wind farm is the same as the geographical location of the wind farm. A Thiessen polygon is a partition of a spatial plane, characterized by each Thiessen polygon containing only one discrete point. Points within a Thiessen polygon are closest to other discrete points within the same Thiessen polygon, and points on the edges of a Thiessen polygon are equidistant from the discrete points on either side of them.

[0050] Optionally, this application uses the geographical locations of ground meteorological observation stations as discrete points to divide the national region based on Thiessen polygons. Wind turbines falling within a certain Thiessen polygon s meet the modeling requirement of being closest to a ground meteorological observation station within Thiessen polygon s, as shown in the following formula:

[0051] dis(x s ,y s ) <dis(x s ,y k k≠s (1)

[0052] Where k and s represent two different Thiessen polygons, x s y represents the geographical location of the wind turbine that falls within the Thiessen polygon s. s y represents the geographical location of a ground meteorological observation station within the Thiessen polygon s. k This represents the geographical location of a ground meteorological observation station within the Thiessen polygon k, and dis() calculates the distance between the two parameters.

[0053] Therefore, the daily minimum temperature at the hub height of the wind turbine falling within the Thiessen polygon s can be calculated from the daily minimum temperature data recorded by the ground meteorological observation stations within the Thiessen polygon s, as shown in the following formula:

[0054]

[0055] Where, θ j (x s θ(y) represents the daily minimum temperature at the hub height of the j-th wind turbine falling within the Thiessen polygon s, where θ(y) s ) represents the daily minimum temperature at a ground-based meteorological station within the Thiessen polygon s, h j (x s ) represents the elevation difference between the hub of the j-th wind turbine falling within the Thiessen polygon s and the ground meteorological observation station within the Thiessen polygon s.

[0056] The above formula (2) holds true for any Thiessen polygon, from which the daily minimum temperature data of each wind turbine can be obtained.

[0057] Step 202: The terminal calculates the annual maximum wind power outage capacity sequence based on the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine, and the daily minimum temperature data of each wind turbine.

[0058] Currently, most wind turbine manufacturers have implemented low-temperature protection. When the ambient temperature is detected to be lower than the wind turbine's low-temperature protection setting, the wind turbine is shut down. The low-temperature protection action function for wind turbines can be expressed as follows:

[0059]

[0060] in, C represents the low-temperature outage capacity of the i-th wind turbine in the t-th time period. i Let θ represent the rated capacity of the i-th wind turbine, ε(·) represent the step function, and θ represent the step function. i,t This represents the hub height temperature of the i-th wind turbine in the t-th time period. This represents the low-temperature protection setting value for the i-th wind turbine unit.

[0061] Optionally, for example, the wind power outage capacity sequence for calculation area A can be calculated using the following formula:

[0062]

[0063] Where S(A) represents the set of wind turbine units contained in region A.

[0064] Therefore, based on the daily minimum temperature data of each wind turbine obtained in the previous step, the calculated values ​​are... The sequence is also calculated with daily precision. Then, by extracting the maximum value for each year, the annual maximum wind power outage capacity sequence can be obtained. As shown in the following formula:

[0065]

[0066] Where Y(y) represents the set of time period t corresponding to year y.

[0067] In the embodiments of this application, the annual maximum wind power outage capacity sequence of the region to be calculated is used as input. The distribution parameters of the annual maximum wind power outage capacity are estimated using the Markov chain Monte Carlo method. Then, based on the estimated distribution parameters, the recurrence level of wind power outage capacity under different return periods is calculated. The specific steps are as follows: Figure 3 As shown, it includes:

[0068] Step 301: The terminal obtains distribution parameter samples based on the annual maximum wind power outage capacity sequence using the Markov chain Monte Carlo method.

[0069] Generalized extreme value distributions (GEPs) are a common choice for fitting extreme value data. Methods for estimating GEP parameters include maximum likelihood estimation, moment estimation, and Bayesian estimation. However, the uncertainty intervals obtained by maximum likelihood estimation and moment estimation methods depend on asymptotic normality. In contrast, Bayesian estimation based on Markov chain Monte Carlo methods can directly calculate the confidence intervals of parameters from a large number of parameter samples obtained from simulated data, avoiding the asymptotic problem. Therefore, this application adopts the Markov chain Monte Carlo method to obtain distribution parameter samples based on the annual maximum wind power outage capacity sequence. The specific steps are as follows: Figure 4 As shown, it includes:

[0070] Step 401: The terminal obtains the input parameters of the Markov chain Monte Carlo method. The input parameters include the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations.

[0071] The number of Markov chains represents the number of initial samples generated. Input parameters also include the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations.

[0072] Step 402: The terminal performs iterative calculations based on the input parameters and the annual maximum wind power outage capacity sequence to obtain a sample of distribution parameters.

[0073] Based on the input parameters from the previous step, the annual maximum wind power outage capacity sequence is fitted using the Markov chain Monte Carlo method to obtain the location parameters, scale parameters, and shape parameters of the generalized extreme value distribution, i.e., the distribution parameter sample. Specifically, this includes the following steps.

[0074] Step 1: Generate initial samples for N Markov chains based on the prior distribution of the input. Let time t = 1.

[0075] Step 2: Construct the transition distribution based on the differential evolution algorithm. In the t-th iteration, for the n-th (n = 1, 2, ..., N) chain, calculate the conditional distribution vector.

[0076]

[0077] Where the superscripts r1 and r2 represent randomly selected Markov chain indices, γ is a constant randomly drawn from [0, 4, 1], and ψ is a value drawn from a normal distribution N(0, 10). -6 ) 3 The vector group extracted from it.

[0078] Step 3: Select a possible transition from the transition distribution. From the conditional distribution vector... Randomly select a candidate transition

[0079] Step 4: Generate a random number u to determine the next transition. Calculate the acceptance probability.

[0080]

[0081] Where x is the annual maximum wind power outage capacity sequence, π(·) represents the prior distribution, and f(·) represents the likelihood function.

[0082] Randomly generate u from [0,1] to determine the next transition:

[0083]

[0084] Step 5: Determine if the Markov chain is stationary. Calculate the scaling factor S:

[0085]

[0086] Where t is the generation number of each Markov chain; D is the number of Markov chains used for evaluation, and D≤N; B / t is the variance of the average value of D Markov chains; and W is the average variance of D Markov chains.

[0087] When S < 1.2, it indicates that the sample begins to stabilize.

[0088] Step 6: Repeat steps 2 through 5 until the maximum number of iterations T is reached.

[0089] Step 7: Output all generalized extreme value distribution parameter samples {μ,σ,ξ} during the stationary period of the population.

[0090] Step 302: The terminal calculates the wind power outage capacity recurrence level under different return periods based on the distributed parameter samples.

[0091] The specific steps for calculating the recurrence level of wind power outage capacity under different return periods are as follows: Figure 5 As shown, it includes:

[0092] Step 501: The terminal calculates the recurrence level sample set of wind power outage capacity with a preset recurrence period based on the distributed parameter sample.

[0093] The preset return period is the number of years of recurrence level to be calculated. The formula below uses T years as an example; T can be selected as needed, and different values ​​of T yield different return periods and recurrence levels. For all the generalized extreme value distribution parameter samples obtained in the previous step, given a set of generalized extreme value distribution parameters {μ... i ,σ i ,ξ i Then, a sample of the recurrence level in year T can be obtained by the following formula:

[0094]

[0095] in, The i-th sample represents the recurrence level in year T.

[0096] For the parameter samples {μ,σ,ξ} of all generalized extreme value distributions obtained in step 301, calculate the corresponding T-year recurrence level to obtain the sample set {R} of the T-year recurrence level. T}

[0097] Step 502: The terminal determines the different quantiles of the reproduction level for the preset reproduction period based on the reproduction level sample set.

[0098] Based on the sample set {R} of the recurrence level in year T T Then, the 5th percentile of the recurrence level in year T can be obtained. median and 95th percentile

[0099] In the above embodiments, by calculating the recurrence level of different recurrence periods, a basis is provided for quantitatively judging the severity of wind power low-temperature outage events.

[0100] In one embodiment, the process for determining the warning level for wind power outage is as follows: Figure 6 As shown, it includes:

[0101] Step 601: The terminal determines the first quantile of the recurrence level for early warning based on preset judgment criteria.

[0102] The judgment criteria include the 5th percentile of the recurrence level in year T. The standard for this is the "strongly conservative judgment criterion," which is based on the 50th percentile of the recurrence level in year T. The standard for this is the “moderately conservative judgment criterion,” which is based on the 95th percentile of the recurrence level in year T. The standard constitutes a "weakly conservative judgment criterion." The preset judgment criterion is a criterion selected by the power grid dispatching department in practical applications, and the first quantile is the quantile corresponding to the selected preset judgment criterion. For example, if the preset judgment criterion is a "weakly conservative judgment criterion," then the first quantile is 95%. If the preset judgment criterion is a "moderately conservative judgment criterion," then the first quantile is 50%.

[0103] Step 602: The terminal determines the early warning level of wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0104] Optional, forecast of wind power outage capacity during low temperatures If the preset judgment criterion is "strongly conservative judgment criterion", then the first quantile is 5%, if the following conditions are met:

[0105]

[0106] Where R in the formula T Pick The value indicates that the warning level for this cold wave is "once a year (T)".

[0107] In the embodiments of this application, please refer to Figure 7 The document illustrates a flowchart of a wind power outage early warning method provided in an embodiment of this application. The wind power outage early warning method includes the following steps:

[0108] Step 701: The terminal acquires data from ground meteorological observation stations and wind farm data.

[0109] Step 702: The terminal performs modeling based on Thiessen polygons, and obtains the daily minimum temperature data of each wind turbine unit according to the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station, and the geographical location of the wind farm.

[0110] Step 703: The terminal calculates the annual maximum wind power outage capacity sequence based on the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine, and the daily minimum temperature data of each wind turbine.

[0111] Step 704: The terminal obtains the input parameters of the Markov chain Monte Carlo method. The input parameters include the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations.

[0112] Step 705: The terminal performs iterative calculations based on the input parameters and the annual maximum wind power outage capacity sequence to obtain a sample of distribution parameters.

[0113] Step 706: The terminal calculates the recurrence level sample set of wind power outage capacity with a preset recurrence period based on the distributed parameter sample.

[0114] Step 707: The terminal determines the different quantiles of the reproduction level for the preset reproduction period based on the reproduction level sample set.

[0115] Step 708: The terminal determines the first quantile of the recurrence level for early warning based on preset judgment criteria.

[0116] Step 709: The terminal determines the early warning level of wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0117] To facilitate readers' understanding of the technical solutions provided in the embodiments of this application, the wind power outage early warning method of this application will be illustrated below by applying it to wind turbine units within a certain power grid area. Daily minimum temperature data from 2481 ground meteorological observation stations within a certain area from 1970 to 2017 were collected, along with the geographical location and rated capacity information of all wind farms within the power grid area in 2020. Calculations were performed on a wind farm-by-farm basis. Considering that low-temperature wind turbine units are the most widely used type, and that the vast majority of low-temperature wind turbine units use -30℃ as the low-temperature protection setting, -30℃ was used as the basis for judging the low-temperature protection action of the wind turbine unit.

[0118] (1) Thiessen polygon division results

[0119] In this scenario, the Thiessen polygon partitioning results based on ground-based meteorological observation stations, and the wind turbine capacity associated with each Thiessen polygon, are as follows: Figure 8 As shown.

[0120] (2) Calculation results of the annual maximum wind power outage capacity sequence within a certain power grid area

[0121] The calculated sequence of annual maximum wind power outage capacity over 48 years is as follows: Figure 9 As shown.

[0122] (3) Reproducibility of horizontal results

[0123] The recurrence level results of wind power outage capacity at different return periods are shown in Table 1.

[0124] Table 1. Recurrence Levels of Wind Power Low-Temperature Outage Capacity at Different Return Periods

[0125] Recurrence period (years) 2 5 10 20 30 40 50 5th percentile (GW) 15.08 22.52 26.56 30.17 32.08 33.15 34.00 50th percentile (GW) 18.06 24.65 29.53 33.57 36.12 37.40 38.67 95th percentile (GW) 18.91 28.26 33.78 39.95 43.98 46.75 48.87

[0126] (4) Early warning level evaluation

[0127] Suppose that the predicted wind power outage capacity due to low temperature is 31GW. If the "strong conservative judgment criterion" is applied, it belongs to the "once in 20 years" warning level. If the "medium conservative judgment criterion" is applied, it belongs to the "once in 10 years" warning level. If the "weak conservative judgment criterion" is applied, it belongs to the "once in 5 years" warning level.

[0128] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0129] Based on the same inventive concept, this application also provides a wind power outage early warning device for implementing the wind power outage early warning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more wind power outage early warning device embodiments provided below can be found in the limitations of the wind power outage early warning method described above, and will not be repeated here.

[0130] In one embodiment, such as Figure 10 As shown, a wind power outage early warning device 1000 is provided, including: an acquisition module 1001, a first calculation module 1002, a second calculation module 1003, and a determination module 1004, wherein:

[0131] The acquisition module 1001 is used to acquire data from ground meteorological observation stations and wind farms.

[0132] The first calculation module 1002 is used to calculate the annual maximum wind power outage capacity sequence based on ground meteorological observation station data and wind farm data.

[0133] The second calculation module 1003 is used to calculate the wind power outage capacity recurrence level under different recurrence periods based on the annual maximum wind power outage capacity sequence.

[0134] The determination module 1004 is used to determine the early warning level of wind power outage based on the predicted value and recurrence level of wind power low-temperature outage capacity.

[0135] In the embodiments of this application, the ground meteorological observation station data includes the geographical location of the ground meteorological observation station and the daily minimum temperature data of the ground meteorological observation station. The wind farm data includes the geographical location of the wind farm, the rated capacity of each wind turbine in the wind farm, and the low temperature protection setting of each wind turbine. The first calculation module 1002 is specifically used for modeling based on Thiessen polygons. According to the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station, and the geographical location of the wind farm, the daily minimum temperature data of each wind turbine is obtained. According to the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine, and the daily minimum temperature data of each wind turbine, the annual maximum wind power outage capacity sequence is calculated.

[0136] In the embodiments of this application, the second calculation module 1003 is specifically used to obtain a distribution parameter sample based on the annual maximum wind power outage capacity sequence using the Markov chain Monte Carlo method; and to calculate the wind power outage capacity recurrence level under different return periods based on the distribution parameter sample.

[0137] In the embodiments of this application, the second calculation module 1003 is specifically used to obtain the input parameters of the Markov chain Monte Carlo method. The input parameters include the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations. Based on the input parameters and the annual maximum wind power outage capacity sequence, iterative calculations are performed to obtain a distribution parameter sample.

[0138] In the embodiments of this application, the second calculation module 1003 is specifically used to calculate the recurrence level sample set of wind power outage capacity with a preset recurrence period based on the distribution parameter sample; and to determine the different quantiles of the recurrence level with the preset recurrence period based on the recurrence level sample set.

[0139] In the embodiments of this application, the determining module 1004 is specifically used to determine the first quantile of the recurrence level for early warning based on a preset judgment criterion; and to determine the early warning level of wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0140] Each module in the aforementioned wind power outage early warning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0141] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a wind power outage early warning method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0142] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0143] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0144] Acquire data from ground meteorological observation stations and wind farms; calculate the annual maximum wind power outage capacity sequence based on the ground meteorological observation station data and wind farm data; calculate the wind power outage capacity recurrence level under different recurrence periods based on the annual maximum wind power outage capacity sequence; determine the early warning level of wind power outage based on the predicted value and recurrence level of wind power outage capacity at low temperatures.

[0145] In one embodiment, when the processor executes the computer program, it also performs the following steps: modeling based on Thiessen polygons, obtaining the daily minimum temperature data of each wind turbine based on the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station and the geographical location of the wind farm; and calculating the annual maximum wind power outage capacity sequence based on the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine and the daily minimum temperature data of each wind turbine.

[0146] In one embodiment, when the processor executes the computer program, it also performs the following steps: obtaining a distribution parameter sample based on the annual maximum wind power outage capacity sequence using the Markov chain Monte Carlo method; and calculating the wind power outage capacity recurrence level under different return periods based on the distribution parameter sample.

[0147] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining the input parameters of the Markov chain Monte Carlo method, including the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations; and performing iterative calculations based on the input parameters and the annual maximum wind power outage capacity sequence to obtain a distribution parameter sample.

[0148] In one embodiment, when the processor executes the computer program, it further performs the following steps: calculating a sample set of recurrence levels of wind power outage capacity for a preset recurrence period based on the distribution parameter sample; and determining different quantiles of the recurrence level for the preset recurrence period based on the sample set of recurrence levels.

[0149] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the first quantile of the reproducibility level for early warning based on a preset judgment criterion; and determining the early warning level for wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0150] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0151] Acquire data from ground meteorological observation stations and wind farms; calculate the annual maximum wind power outage capacity sequence based on the ground meteorological observation station data and wind farm data; calculate the wind power outage capacity recurrence level under different recurrence periods based on the annual maximum wind power outage capacity sequence; determine the early warning level of wind power outage based on the predicted value and recurrence level of wind power outage capacity at low temperatures.

[0152] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: modeling based on Thiessen polygons, obtaining the daily minimum temperature data of each wind turbine based on the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station and the geographical location of the wind farm; and calculating the annual maximum wind power outage capacity sequence based on the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine and the daily minimum temperature data of each wind turbine.

[0153] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining a distribution parameter sample based on the annual maximum wind power outage capacity sequence using the Markov chain Monte Carlo method; and calculating the wind power outage capacity recurrence level under different return periods based on the distribution parameter sample.

[0154] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the input parameters of the Markov chain Monte Carlo method, including the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations; and performing iterative calculations based on the input parameters and the annual maximum wind power outage capacity sequence to obtain a distribution parameter sample.

[0155] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: calculating a sample set of the recurrence level of wind power outage capacity for a preset recurrence period based on the distribution parameter sample; and determining the different quantiles of the recurrence level for the preset recurrence period based on the sample set of the recurrence level.

[0156] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the first quantile of the reproducibility level for early warning based on a preset judgment criterion; and determining the early warning level for wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0157] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0158] Acquire data from ground meteorological observation stations and wind farms; calculate the annual maximum wind power outage capacity sequence based on the ground meteorological observation station data and wind farm data; calculate the wind power outage capacity recurrence level under different recurrence periods based on the annual maximum wind power outage capacity sequence; determine the early warning level of wind power outage based on the predicted value and recurrence level of wind power outage capacity at low temperatures.

[0159] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: modeling based on Thiessen polygons, obtaining the daily minimum temperature data of each wind turbine based on the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station and the geographical location of the wind farm; and calculating the annual maximum wind power outage capacity sequence based on the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine and the daily minimum temperature data of each wind turbine.

[0160] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining a distribution parameter sample based on the annual maximum wind power outage capacity sequence using the Markov chain Monte Carlo method; and calculating the wind power outage capacity recurrence level under different return periods based on the distribution parameter sample.

[0161] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the input parameters of the Markov chain Monte Carlo method, including the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations; and performing iterative calculations based on the input parameters and the annual maximum wind power outage capacity sequence to obtain a distribution parameter sample.

[0162] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: calculating a sample set of the recurrence level of wind power outage capacity for a preset recurrence period based on the distribution parameter sample; and determining the different quantiles of the recurrence level for the preset recurrence period based on the sample set of the recurrence level.

[0163] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the first quantile of the reproducibility level for early warning based on a preset judgment criterion; and determining the early warning level for wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0165] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0166] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0167] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A wind power outage early warning method, characterized in that, The method includes: Data from ground meteorological observation stations and wind farms are acquired. The ground meteorological observation station data includes the geographical location of the station and the daily minimum temperature data. The wind farm data includes the geographical location of the wind farm, the rated capacity of each wind turbine in the wind farm, and the low-temperature protection setting of each wind turbine. Modeling is performed based on Thiessen polygons. The daily minimum temperature data of each wind turbine is obtained according to the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station, and the geographical location of the wind farm. The annual maximum wind power outage capacity sequence is calculated according to the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine, and the daily minimum temperature data of each wind turbine. Based on the Markov chain Monte Carlo method, a distribution parameter sample is obtained according to the annual maximum wind power outage capacity sequence; the distribution parameter sample includes the location parameter, scale parameter, and shape parameter of the generalized extreme value distribution; based on the distribution parameter sample, the wind power outage capacity recurrence level under different return periods is calculated; The early warning level for wind power outages is determined based on the predicted capacity for wind power outages due to low temperatures and the recurrence level.

2. The method according to claim 1, characterized in that, The Markov chain Monte Carlo method, based on the annual maximum wind power outage capacity sequence, obtains a sample of distribution parameters, including: Obtain the input parameters of the Markov chain Monte Carlo method, which include the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations; The distribution parameter sample is obtained by iterative calculation based on the input parameters and the annual maximum wind power outage capacity sequence.

3. The method according to claim 2, characterized in that, The step of calculating the wind power outage capacity recurrence level under different return periods based on the distribution parameter sample includes: Based on the distribution parameter sample, calculate the recurrence level sample set of wind power outage capacity with a preset recurrence period; Based on the sample set of the recurrence level, determine the different quantiles of the recurrence level for the preset recurrence period.

4. The method according to claim 1, characterized in that, The step of determining the early warning level for wind power outages based on the predicted wind power outage capacity at low temperatures and the recurrence level includes: According to the preset judgment criteria, the first quantile of the recurrence level used for early warning is determined; The warning level for wind power outage is determined based on the predicted wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

5. A wind power outage early warning device, characterized in that, The device includes: The acquisition module is used to acquire data from ground meteorological observation stations and wind farms. The ground meteorological observation station data includes the geographical location of the ground meteorological observation station and the daily minimum temperature data of the ground meteorological observation station. The wind farm data includes the geographical location of the wind farm, the rated capacity of each wind turbine in the wind farm, and the low temperature protection setting of each wind turbine. The first calculation module is used for modeling based on Thiessen polygons. It obtains the daily minimum temperature data of each wind turbine based on the geographical location of the ground meteorological observation station, the daily minimum temperature data of the ground meteorological observation station, and the geographical location of the wind farm. It calculates the annual maximum wind power outage capacity sequence based on the rated capacity of each wind turbine, the low temperature protection setting of each wind turbine, and the daily minimum temperature data of each wind turbine. The second calculation module is used to obtain distribution parameter samples based on the Markov chain Monte Carlo method and the annual maximum wind power outage capacity sequence; the distribution parameter samples include the location parameters, scale parameters, and shape parameters of the generalized extreme value distribution; and to calculate the wind power outage capacity recurrence level under different return periods based on the distribution parameter samples. The determination module is used to determine the early warning level of the wind power outage based on the predicted value of the wind power outage capacity at low temperatures and the recurrence level.

6. The apparatus according to claim 5, characterized in that, The second calculation module is specifically used to obtain the input parameters of the Markov chain Monte Carlo method. The input parameters include the number of Markov chains, the prior distribution of the generalized extreme value distribution parameters, the number of Markov chains used for evaluation, and the number of iterations. Based on the input parameters and the annual maximum wind power outage capacity sequence, iterative calculations are performed to obtain the distribution parameter sample.

7. The apparatus according to claim 6, characterized in that, The second calculation module is specifically used to calculate the recurrence level sample set of wind power outage capacity with a preset recurrence period based on the distribution parameter sample; and to determine the different quantiles of the recurrence level with the preset recurrence period based on the recurrence level sample set.

8. The apparatus according to claim 5, characterized in that, The determining module is specifically used to determine the first quantile of the recurrence level for early warning based on a preset judgment criterion; and to determine the early warning level of wind power outage based on the predicted value of wind power outage capacity at low temperatures and the wind power outage capacity corresponding to the first quantile.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images