Regional wind resource evaluation and prediction method and system based on interpolation method and SARIMA, storage medium and processor

Abstract

The invention relates to the technical field of wind resource assessment and prediction, in particular to a regional wind resource assessment and prediction method and system based on an interpolation method and SARIMA, a storage medium and a processor, and the method comprises the steps: obtaining regional wind speed data; performing interpolation processing on the data to obtain interpolated wind speed data; according to the interpolated wind speed data, calculating the annual available hours of the wind resources in each space region, and selecting the region with the maximum utilization potential of the wind resources as a target region for wind speed prediction; establishing and training an SARIMA wind speed prediction model; and performing wind speed prediction on the selected region with the maximum wind resource utilization potential by adopting the trained SARIMA prediction model region to obtain wind speed prediction data of the region. According to the method, the plane interpolation method and the SARIMA model are combined, spatial data are reasonably filled through the plane interpolation method, the utilization potential of wind resources is evaluated, the SARIMA model is combined to dynamically predict the time sequence, and the limitation of a traditional method can be overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of wind resource assessment and prediction, and in particular to a regional wind resource assessment and prediction method, system, storage medium and processor based on interpolation method and SARIMA. Background Art

[0002] With the vigorous development of the renewable energy industry, the proportion of renewable energy in the energy structure has increased significantly. Among them, the proportion of wind power generation in the total electricity consumption of the society has increased year by year. Taking 2023 as an example, my country's new wind power installed capacity will reach 75 GW, accounting for about 65% of the world's new wind power installed capacity. Among them, offshore wind power will increase by 6.3 GW, accounting for 71% of the world's new offshore wind power. With the rapid development of the wind power industry and the planned establishment of a large number of wind farms in the future, how to obtain a large amount of high-resolution wind speed data to assist in wind farm site selection is very critical for the efficient use of wind energy.

[0003] Traditional wind resource assessment methods, such as field measurements and assessments based on numerical weather prediction (NWP) models, often have problems with difficult data acquisition, high costs, and insufficient spatial coverage. Planar interpolation can geographically expand the scope of wind resource assessment by interpolating multiple observation points in a region. It is suitable for areas with sparse data, especially in complex terrain conditions, and has good spatial adaptability. As a time series prediction model, the SARIMA model can capture the seasonality and trend of wind speed data and is suitable for dynamic prediction of historical wind speed data.

[0004] In view of this, it is necessary to study a regional wind resource assessment and prediction method based on interpolation and SARIMA to solve the current problems of wind resource assessment, such as difficulty in data acquisition, high cost and insufficient spatial coverage. Summary of the invention

[0005] In view of the problems in the prior art, the present invention provides a regional wind resource assessment and prediction method, system, storage medium and processor based on interpolation method and SARIMA. The specific technical solution is as follows:

[0006] A regional wind resource assessment and prediction method based on interpolation method and SARIMA includes the following steps:

[0007] Step S1, obtaining regional wind speed data, classifying the obtained data according to time series and space series, and preprocessing the obtained original wind speed data to eliminate obviously abnormal data;

[0008] Step S2, retaining the original time resolution, interpolating the classified spatial sequence data to obtain an interpolated spatial sequence, dividing the wind speed data into various spatial regions, arranging the interpolated wind speed data according to the time series, and obtaining the interpolated wind speed data;

[0009] Step S3, calculating the annual available hours of wind resources in each spatial area according to the interpolated wind speed data, and selecting the area with the greatest potential for wind resource utilization as the target area for wind speed prediction;

[0010] Step S4, establishing and training a SARIMA wind speed prediction model;

[0011] Step S5, using the trained SARIMA prediction model area to predict the wind speed of the selected area with the greatest wind resource utilization potential, to obtain wind speed prediction data for the area.

[0012] Preferably, the interpolation processing of the classified spatial sequence data in step S2 specifically includes interpolation of the longitude direction of the spatial sequence data and interpolation of the latitude direction of the spatial sequence data.

[0013] Preferably, the longitude direction of the spatial sequence data is interpolated by using the following formula:

[0014] f(x)=a(x i ) 3 +b(xx i ) 2 +c(xx i )+d

[0015] Among them, x is the longitude of the desired position, x i is the longitude and azimuth of the ith area near the target location, a, b, c, d are coefficients, which are calculated by the following formula:

[0016]

[0017] Among them, f(x i ) is the wind speed value of the i-th area with respect to the longitude, f'(x i ) is the partial derivative of the wind speed in the ith region with respect to the longitude direction; f(x i+1 ) is the wind speed value of the i+1th area with respect to the longitude, f'(x i+1 ) is the partial derivative of the wind speed in the i+1th region with respect to the longitude direction.

[0018] Preferably, the interpolation of the spatial sequence data in the latitude direction is performed by using the following formula:

[0019]

[0020] Among them, f(y) is the wind speed value of the target position at latitude y, y is the latitude of the target point, y1 is the wind speed value of the area with a latitude lower than the area where y is located, and y2 is the wind speed value of the area with a latitude higher than the area where y is located.

[0021] Preferably, the calculation of the annual available hours of wind resources in each spatial area according to the interpolated data in step S3 is as follows:

[0022]

[0023] Among them, H a W is the annual available hours of the fan; y is the annual power generation of the region; P r is the rated power of a single fan.

[0024] Preferably, the step S4 specifically includes the following steps:

[0025] First, data is selected from the interpolated wind speed data and divided into a test set and a training set;

[0026] Determine the data volume of the training set. When the data volume of the training set is 10 times larger than that of the test set, directly perform model training; otherwise, interpolate the time series to expand the data volume of the training set.

[0027] The SARIMA wind speed prediction model is established as follows:

[0028]

[0029] θ(B)=1-θ1B-…-θqB q

[0030] Φ(B s )=1-ΦB s -…-Φ p B Ps

[0031] Θ(B s )=1-Θ1B-…-Θ Q B Qs ;

[0032] Among them, Y t represents the time series of wind speed data in the target area, and d represents the time series of the sequence Y t The number of ordinary differences is used to eliminate non-seasonal trends; D represents the number of seasonal differences of the time series to eliminate seasonal costs; (1-B) d (1-B s ) D Yt is the stationary time series after difference; B represents the lag operator, (1-B) represents the difference operator, (1-B s ) indicates that the lag operator B shifts the time series backward by one time step s; is a seasonal autoregressive model, represents the p-order autoregressive polynomial, is the non-seasonal autoregressive parameter; Φ(B s ) represents the p-order seasonal autoregressive polynomial, Φ1, Φ2, …, Φ p is the p-order seasonal autoregressive parameter; θ(B)Θ(B s ) represents the seasonal moving average model, where θ(B) represents the q-order moving average polynomial, θ1, θ2, …, θ q is the non-seasonal moving average parameter, Θ(B s ) represents the seasonal moving average polynomial, Θ1,Θ1,…,Θ Q is the Q-order seasonal moving average parameter, ε t is Gaussian noise, and the s parameter represents the seasonal period;

[0033] Perform a stationarity test on the wind speed data of the test set to determine whether the wind speed data of the test set is a stationary sequence. If not, perform differential processing on the wind speed data of the test set;

[0034] After the wind speed data of the test set is stabilized, the SARIMA wind speed prediction model is identified and the parameters are determined based on the autocorrelation coefficient graph ACF and the partial autocorrelation coefficient graph PACF.

[0035] Preferably,

[0036] Model identification and parameter order determination are performed based on the autocorrelation coefficient graph ACF and the partial autocorrelation coefficient graph PACF. Specifically, the value range of parameters p and q is first determined based on the autocorrelation coefficient graph ACF and the partial autocorrelation coefficient graph PACF, and then the values ​​of model parameters p, d, q, P, D, and Q are screened and determined based on the Akaike information criterion.

[0037] A regional wind resource assessment and prediction system based on interpolation method and SARIMA, applied to the method described, comprising:

[0038] The data acquisition and processing module is used to obtain regional wind speed data, classify the obtained data according to time series and spatial series, and pre-process the obtained original wind speed data to eliminate obviously abnormal data;

[0039] The data interpolation module is used to retain the original time resolution, interpolate the classified spatial sequence data, obtain the interpolated spatial sequence, divide the wind speed data into various spatial regions, arrange the interpolated wind speed data according to the time series, and obtain the interpolated wind speed data;

[0040] The target area selection module is used to calculate the annual available hours of wind resources in each spatial area based on the interpolated wind speed data, and select the area with the greatest potential for wind resource utilization as the target area for wind speed prediction;

[0041] Model building module, used to build and train the SARIMA wind speed prediction model;

[0042] The wind speed prediction module is used to use the trained SARIMA prediction model area to predict the wind speed of the selected area with the greatest potential for wind resource utilization, and obtain the wind speed prediction data for the area.

[0043] A computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the regional wind resource assessment and prediction method based on interpolation method and SARIMA.

[0044] A processor is used to run a program, wherein the program executes the regional wind resource assessment and prediction method based on interpolation method and SARIMA when running.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention combines the plane interpolation method with the SARIMA (Seasonal Autoregressive Integrated Moving Average) model, reasonably fills in the spatial data through the plane interpolation method, evaluates the utilization potential of wind resources, and dynamically predicts the time series in combination with the SARIMA model, which can overcome the limitations of traditional methods. The method can improve the accuracy and timeliness of wind resource assessment without increasing additional measurement costs, and is particularly suitable for wind resource assessment and wind power generation potential prediction in areas with sparse wind speed measurement points or complex terrain. This method can improve the scientific nature of wind farm site selection and significantly reduce the cost of wind resource assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0048] Figure 1 The figure is a flow chart of the method of the present invention.

[0049] Figure 2 This is the wind speed-wind power curve.

[0050] Figure 3 It is the annual wind speed curve of the embodiment area.

[0051] Figure 4 It is the annual power curve diagram of the embodiment area.

[0052] Figure 5 ACF and PACF plots.

[0053] Figure 6 This is the wind speed data chart for January 1, 2023.

[0054] Figure 7 It is a system principle diagram of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0057] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0058] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0059] Embodiment 1:

[0060] like Figure 1 As shown, this embodiment provides a regional wind resource assessment and prediction method based on interpolation method and SARIMA, including the following steps:

[0061] Step S1, obtain regional wind speed data, classify the obtained data according to time series and space series, and pre-process the obtained original wind speed data to eliminate obviously abnormal data.

[0062] The obtained data are classified according to time series and space series, so as to facilitate the extraction of required data according to the requirements of interpolation when performing the interpolation algorithm later.

[0063] This embodiment selects the hourly wind speed data for the South China Sea region of my country (3° to 23° north latitude, 109° to 121° east longitude) from 2012 to 2023, with a spatial resolution of 31km×31km.

[0064] Step S2, retaining the original time resolution, interpolating the classified spatial sequence data to obtain the interpolated spatial sequence, dividing the wind speed data into various spatial regions, arranging the interpolated wind speed data according to the time series, and obtaining the interpolated wind speed data. The interpolation processing of the classified spatial sequence data specifically includes interpolating the longitude direction of the spatial sequence data and interpolating the latitude direction of the spatial sequence data.

[0065] The classified data are interpolated to retain the original temporal resolution while improving its spatial resolution to obtain more spatial wind speed data.

[0066] Bicubic and Cubic interpolation methods are used for plane interpolation processing. The interpolation method with higher accuracy for the area is selected through MSE comparison to avoid overfitting or insufficient fitting in the interpolation processing. By comparing two different interpolation methods, this embodiment finds that the Cubic interpolation method is more effective in processing the selected original data in the South China Sea.

[0067] Cubic interpolation is an extension of one-dimensional cubic polynomial interpolation. In this embodiment, the longitude direction of the spatial sequence data is interpolated using the following formula:

[0068] f(x)=a(x i ) 3 +b(xx i ) 2 +c(xx i )+d

[0069] Among them, x is the longitude of the desired position, x i is the longitude and azimuth of the ith area near the target location, a, b, c, d are coefficients, which are calculated by the following formula:

[0070]

[0071] Among them, f(x i ) is the wind speed value of the i-th area with respect to the longitude, f'(x i ) is the partial derivative of the wind speed in the ith region with respect to the longitude direction; f(x i+1 ) is the wind speed value of the i+1th area with respect to the longitude, f'(x i+1 ) is the partial derivative of the wind speed in the i+1th region with respect to the longitude direction.

[0072] The following formula is used to interpolate the latitude direction of spatial series data:

[0073]

[0074] Among them, f(y) is the wind speed value of the target position at the latitude y, y is the latitude of the target point, y1 is the wind speed value of the area with a latitude lower than the area where y is located, and y2 is the wind speed value of the area with a latitude higher than the area where y is located. The latitude area is the area in the latitude direction of the spatial area divided previously.

[0075] This embodiment improves the spatial resolution of the original wind speed data in the South my country Sea by two times, to 15km×15km. The interpolated wind speed data is arranged in a time series, and all wind speed data of the South China Sea at a given time point are included. Since this embodiment improves the original spatial resolution by two times, the original one spatial region containing wind speed is increased to four spatial regions containing wind speed, the amount of wind speed data in the spatial range is expanded, and the obtained wind speed has a higher spatial resolution.

[0076] Step S3, calculating the annual available hours of wind resources in each spatial area based on the interpolated wind speed data, and selecting the area with the greatest potential for wind resource utilization as the target area for wind speed prediction.

[0077] First, select the wind turbine model to be calculated, and draw the wind turbine power curve through the relevant parameters of the wind turbine and the relationship between wind speed and power. Combine the annual wind speed change curve of each small area with the wind turbine power curve to calculate the annual power generation of the wind turbine in the area. Calculate the annual available hours of wind resources in each spatial area based on the interpolated data as follows:

[0078]

[0079] Among them, H a W is the annual available hours of the fan; y is the annual power generation of the region; P r is the rated power of a single fan.

[0080] In step S2, the spatial interpolation method is used to improve the spatial resolution of the selected area and generate more small areas. By calculating the annual available hours of wind resources in small areas, the distribution of wind resources in the entire large area can be evaluated, and the areas with annual available hours greater than 3000 hours can be found for further analysis, avoiding wind speed prediction for all areas, which can significantly reduce the amount of calculation of the subsequent SARIMA algorithm.

[0081] The wind speed data selected in this embodiment is the wind speed data of 2023 after interpolation in the South my country Sea. The 8MW Vestes V 164-8.0 wind turbine is selected for the calculation of the regional annual available hours. The specific power calculation can be performed according to the following algorithm:

[0082] When v <v i When the wind speed is less than the starting wind speed of the wind turbine, the wind turbine will not start, P = 0;

[0083] When v i ≤v≤v r When the wind speed increases, the output power gradually increases. At this time, the relationship between the output power and the wind speed is as shown in the attached figure. Figure 2 As shown;

[0084] When v r <v<v t When the output power remains stable, P = P r ;

[0085] When v ≥ v t In order to protect the fan, the fan stops running, P = 0

[0086] Among them, v i is the wind turbine cut-in wind speed, v r is the rated wind speed of the fan, v t is the cut-out wind speed of the fan, P r is the rated power of the wind turbine. The above algorithm can be used to obtain the output power of the wind turbine at each moment, and the annual cumulative power generation can be obtained by adding up all the moments of the year. In this example, the area with the greatest potential for wind resource utilization, 18.93°N and 120.52°E, was selected for detailed evaluation of wind resources and prediction of future wind speeds. The annual wind speed curve of this area is shown in the attached figure. Figure 3 The annual power curve is shown in the attached Figure 4 As shown, it can be seen that the overall wind speed in the area with the greatest potential for wind resource utilization is in the range of 5-15m / s, and the wind speed can reach the rated wind speed of the wind turbine for a large part of the time, so the capacity factor of the wind turbine can be better improved.

[0087] Step S4, establishing and training the SARIMA wind speed prediction model. Specifically, the following steps are included:

[0088] Step S41, firstly, data are selected from the interpolated wind speed data to be divided into a test set and a training set; specifically, data with relatively stable time intervals and spatial intervals can be selected from the interpolated wind speed data to be divided into a test set and a training set.

[0089] Step S42, determine the data volume of the training set. When the data volume of the training set is 10 times greater than the data volume of the test set, directly perform model training; otherwise, interpolate the time series to expand the data volume of the training set.

[0090] Step S43, establishing a SARIMA wind speed prediction model, specifically as follows:

[0091]

[0092] θ(B)=1-θ1B-…-θqB q

[0093] Φ(B s )=1-ΦB s -…-Φ p B Ps

[0094] Θ(B s )=1-Θ1B-…-Θ Q B Qs ;

[0095] Among them, Y t represents the time series of wind speed data in the target area, and d represents the time series of the sequence Y t The number of ordinary differences is used to eliminate non-seasonal trends; D represents the number of seasonal differences of the time series to eliminate seasonal costs; (1-B) d (1-B s ) D Y t is the stationary time series after difference; B represents the lag operator, (1-B) represents the difference operator, (1-B s ) indicates that the lag operator B shifts the time series backward by one time step s; is a seasonal autoregressive model, represents the p-order autoregressive polynomial, is the non-seasonal autoregressive parameter; Φ(B s ) represents the p-order seasonal autoregressive polynomial, Φ1, Φ2, …, Φ p is the p-order seasonal autoregressive parameter; θ(B)Θ(B s) represents the seasonal moving average model, where θ(B) represents the q-order moving average polynomial, θ1, θ2, …, θ q is the non-seasonal moving average parameter, Θ(B s ) represents the seasonal moving average polynomial, Θ1,Θ1,…,Θ Q is the Q-order seasonal moving average parameter, ε t is Gaussian noise, and the s parameter represents the seasonal period.

[0096] Step S44, perform a stationarity test on the wind speed data of the test set to determine whether the wind speed data of the test set is a stationary sequence. If not, perform differential processing on the wind speed data of the test set. Specifically, use ADF to test whether the input time series is a stationary sequence. When the p value is <0.05, it can be determined that the sequence is a stationary sequence. The formula for performing differential processing is specifically D-order differential processing as follows:

[0097]

[0098] in Represents the time series Y t The result after d times of non-seasonal differencing is: Represents the time series Y t The result after d-1 times of non-seasonal difference is: Represents Y t-1 Results after d-2 non-seasonal differencing.

[0099] Step S45, after the wind speed data of the test set is stabilized, the SARIMA wind speed prediction model is identified and the parameters are determined according to the autocorrelation coefficient graph ACF and the partial autocorrelation coefficient graph PACF.

[0100] Furthermore, model identification and parameter order determination are performed based on the autocorrelation coefficient diagram ACF and the partial autocorrelation coefficient diagram PACF. By observing the changing trends of the two curves in the partial autocorrelation diagram and the autocorrelation diagram, such as tailing and truncation, it is determined whether the input time series data has an obvious seasonal trend, and the value range of the SARIMA model parameters p and q is preliminarily determined. Then, the Akaike information criterion is used to screen and determine the model's p, d, q, P, D, and Q parameters.

[0101] The calculation formula of Akaike's information criterion is as follows:

[0102] AIC = -2ln(L) + 2k;

[0103] Among them, L is the maximum likelihood estimate of the input time series, and k is the number of variables in the SARIMA model.

[0104] In this embodiment, the interpolated wind speed data of the area with the greatest potential for wind resource utilization in the South my country Sea from 2012 to 2022 on January 1st of each year is used as the training set, and the wind speed data on January 1st, 2023 is used as the test set. The amount of training set data is much larger than that of the test set data, so there is no need to use secondary interpolation processing. Its ACF and PACF are shown in the attached figure. Figure 5 As shown in the figure, both the ACF graph and the PACF graph have a certain tailing state, indicating that they have a certain seasonality. The wind speed data predicted by the SARIMA model on January 1, 2023 is shown in the attached figure. Figure 6 As shown, the predicted wind speed data has a similar trend to the actual wind speed data, and the average daily error between the predicted wind speed and the actual wind speed is less than 15%, which has good accuracy in regional wind speed prediction and can participate in wind resource assessment in larger areas. The parameters in the embodiment are p=1, d=0, q=2, P=0, D=0, Q=2, s=24, and the AIC under this model is 526.977, which shows that this model has a good balance between fitting error and complexity, indicating that the model performs well in explaining data. AIC is around 500, which means that the selected data volume is moderate and will not lead to higher complexity to increase the difficulty of calculation during calculation, and no overfitting phenomenon is found.

[0105] Step S5, using the trained SARIMA prediction model area to predict the wind speed of the selected area with the greatest wind resource utilization potential, to obtain wind speed prediction data for the area.

[0106] The more original wind speed data the method of the present invention obtains, the higher the accuracy of the predicted wind speed after interpolation and SARIMA model training. For different geographical areas, it is necessary to select a suitable interpolation method according to the MSE value. For the case of less data, the data set can also be expanded according to the interpolation algorithm to facilitate the training of the SARIMA model.

[0107] The present invention combines the interpolation method with the SARIMA model prediction method, and processes missing or noisy data through the interpolation method, so that the wind speed data is smoother and more complete, and can more accurately describe the wind speed change. After this high-precision data is input into the SARIMA model, the future wind speed can be predicted more accurately, and the reliability of wind resource assessment can be improved, thereby effectively supporting the scientific planning and layout of the wind farm. The SARIMA model is fitted based on stable and complete time series data, and has a strong ability to capture the trend and periodic changes of wind speed. After the accuracy of the predicted power output is improved, it can better support the load management of the power grid and reduce the uncertainty caused by wind power grid connection. Accurate wind speed prediction can also help wind farms make flexible power generation decisions, especially when the market electricity price fluctuates, it can increase output during the peak wind speed period, reduce costs, and increase revenue. Combining the interpolation method and SARIMA wind speed prediction can greatly reduce the cost of high-resolution wind speed acquisition. Predicting future wind speed changes through interpolation and SARIMA models can also help the operation and maintenance team to judge the wind speed peaks and valleys in advance and optimize the power generation scheduling and unit operation strategies of the wind farm.

[0108] Embodiment 2:

[0109] like Figure 7 As shown, based on the same inventive concept as that of Example 1, this embodiment provides a regional wind resource assessment and prediction system based on interpolation method and SARIMA, which is applied to the method described, including:

[0110] The data acquisition and processing module is used to obtain regional wind speed data, classify the obtained data according to time series and spatial series, and pre-process the obtained original wind speed data to eliminate obviously abnormal data;

[0111] The data interpolation module is used to retain the original time resolution, interpolate the classified spatial sequence data, obtain the interpolated spatial sequence, divide the wind speed data into various spatial regions, arrange the interpolated wind speed data according to the time series, and obtain the interpolated wind speed data;

[0112] The target area selection module is used to calculate the annual available hours of wind resources in each spatial area based on the interpolated wind speed data, and select the area with the greatest potential for wind resource utilization as the target area for wind speed prediction;

[0113] Model building module, used to build and train the SARIMA wind speed prediction model;

[0114] The wind speed prediction module is used to use the trained SARIMA prediction model area to predict the wind speed of the selected area with the greatest potential for wind resource utilization, and obtain the wind speed prediction data for the area.

[0115] Embodiment 3:

[0116] Based on the same inventive concept as Example 1, this embodiment provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the regional wind resource assessment and prediction method based on interpolation method and SARIMA.

[0117] Embodiment 4:

[0118] Based on the same inventive concept as that of Example 1, this embodiment provides a processor, which is used to run a program, wherein the program executes the regional wind resource assessment and prediction method based on interpolation and SARIMA when running.

[0119] Those of ordinary skill in the art will appreciate that the modules of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0120] In the embodiments provided by the present invention, it should be understood that the division of modules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple modules can be combined into one module, one module can be split into multiple modules, or some features can be ignored, etc.

[0121] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0122] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., various media that can store program codes.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A regional wind resource assessment and prediction method based on interpolation and SARIMA, characterized in that: The following steps are involved: Step S1, obtaining regional wind speed data, classifying the obtained data according to time series and space series, and preprocessing the obtained original wind speed data to eliminate obviously abnormal data; Step S2, retaining the original time resolution, interpolating the classified spatial sequence data to obtain an interpolated spatial sequence, dividing the wind speed data into various spatial regions, arranging the interpolated wind speed data according to the time series, and obtaining the interpolated wind speed data; Step S3, calculating the annual available hours of wind resources in each spatial area according to the interpolated wind speed data, and selecting the area with the greatest potential for wind resource utilization as the target area for wind speed prediction; Step S4, establishing and training a SARIMA wind speed prediction model; Step S5, using the trained SARIMA prediction model area to predict the wind speed of the selected area with the greatest wind resource utilization potential, to obtain wind speed prediction data for the area.

2. The regional wind resource assessment and prediction method based on interpolation method and SARIMA according to claim 1 is characterized in that: The interpolation processing of the classified spatial sequence data in step S2 specifically includes interpolation of the longitude direction of the spatial sequence data and interpolation of the latitude direction of the spatial sequence data.

3. The regional wind resource assessment and prediction method based on interpolation and SARIMA according to claim 2 is characterized in that: The following formula is used to interpolate the longitude direction of spatial series data: f(x)=a(x-x i ) 3 +b(x-x i ) 2 +c(x-x i )+d Among them, x is the longitude of the desired position, x i is the longitude and azimuth of the ith area near the target location, a, b, c, d are coefficients, which are calculated by the following formula: Among them, f(x i ) is the wind speed value of the i-th area with respect to the longitude, f'(x i ) is the partial derivative of the wind speed in the ith region with respect to the longitude direction; f(x i+1 ) is the wind speed value of the i+1th area with respect to the longitude, f'(x i+1 ) is the partial derivative of the wind speed in the i+1th region with respect to the longitude direction.

4. The regional wind resource assessment and prediction method based on interpolation and SARIMA according to claim 2 is characterized in that: The following formula is used to interpolate the latitude direction of spatial series data: Among them, f(y) is the wind speed value of the target position at latitude y, y is the latitude of the target point, y1 is the wind speed value of the area with a latitude lower than the area where y is located, and y2 is the wind speed value of the area with a latitude higher than the area where y is located.

5. The regional wind resource assessment and prediction method based on interpolation and SARIMA according to claim 1, characterized in that: The calculation of the annual available hours of wind resources in each spatial area according to the interpolated data in step S3 is as follows: Among them, H a W is the annual available hours of the fan; y is the annual power generation of the region; P r is the rated power of a single fan.

6. The regional wind resource assessment and prediction method based on interpolation and SARIMA according to claim 1, characterized in that: The step S4 specifically comprises the following steps: First, data is selected from the interpolated wind speed data and divided into a test set and a training set; Determine the data volume of the training set. When the data volume of the training set is 10 times larger than that of the test set, directly perform model training; otherwise, interpolate the time series to expand the data volume of the training set. The SARIMA wind speed prediction model is established as follows: θ(B)=1-θ1B-…-θqB q Among them, Y t represents the time series of wind speed data in the target area, and d represents the time series of the sequence Y t The number of ordinary differences is used to eliminate non-seasonal trends; D represents the number of seasonal differences of the time series to eliminate seasonal costs; (1-B) d (1-B s ) D Y t is the stationary time series after difference; B represents the lag operator, (1-B) represents the difference operator, (1-B s ) indicates that the lag operator B shifts the time series backward by one time step s; is a seasonal autoregressive model, represents the p-order autoregressive polynomial, is the non-seasonal autoregressive parameter; Φ(B s ) represents the p-order seasonal autoregressive polynomial, Φ1, Φ2, …, Φ p is the p-order seasonal autoregressive parameter; θ(B)Θ(B s ) represents the seasonal moving average model, where θ(B) represents the q-order moving average polynomial, θ1, θ2, …, θ q is the non-seasonal moving average parameter, Θ(B s ) represents the seasonal moving average polynomial, Θ1,Θ1,…,Θ Q is the Q-order seasonal moving average parameter, ε t is Gaussian noise, and the s parameter represents the seasonal period; Perform a stationarity test on the wind speed data of the test set to determine whether the wind speed data of the test set is a stationary sequence. If not, perform differential processing on the wind speed data of the test set; After the wind speed data of the test set is stabilized, the SARIMA wind speed prediction model is identified and the parameters are determined based on the autocorrelation coefficient graph ACF and the partial autocorrelation coefficient graph PACF.

7. The regional wind resource assessment and prediction method based on interpolation and SARIMA according to claim 6 is characterized in that: Model identification and parameter order determination are performed based on the autocorrelation coefficient graph ACF and the partial autocorrelation coefficient graph PACF. Specifically, the value range of parameters p and q is first determined based on the autocorrelation coefficient graph ACF and the partial autocorrelation coefficient graph PACF, and then the values ​​of model parameters p, d, q, P, D, and Q are screened and determined based on the Akaike information criterion.

8. A regional wind resource assessment and prediction system based on interpolation method and SARIMA, characterized in that: The method applied to any one of claims 1 to 7, comprising: The data acquisition and processing module is used to obtain regional wind speed data, classify the obtained data according to time series and spatial series, and pre-process the obtained original wind speed data to eliminate obviously abnormal data; The data interpolation module is used to retain the original time resolution, interpolate the classified spatial sequence data, obtain the interpolated spatial sequence, divide the wind speed data into various spatial regions, arrange the interpolated wind speed data according to the time series, and obtain the interpolated wind speed data; The target area selection module is used to calculate the annual available hours of wind resources in each spatial area based on the interpolated wind speed data, and select the area with the greatest potential for wind resource utilization as the target area for wind speed prediction; Model building module, used to build and train the SARIMA wind speed prediction model; The wind speed prediction module is used to use the trained SARIMA prediction model area to predict the wind speed of the selected area with the greatest potential for wind resource utilization, and obtain the wind speed prediction data of the area.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the regional wind resource assessment and prediction method based on interpolation method and SARIMA as described in any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the regional wind resource assessment and prediction method based on interpolation method and SARIMA as described in any one of claims 1 to 7.

Images