Coordinated optimization method for microclimate data fusion and new energy power prediction

Abstract

The application provides a micro-meteorological data fusion and new energy power prediction collaborative optimization method, and relates to the technical field of new energy power prediction. The method comprises the following steps: collecting historical meteorological data, and performing regional micro-meteorological feature extraction based on a time dimension to form regional historical micro-meteorological feature data; collecting historical new energy production data, and performing power production information extraction based on a time dimension to form historical power production data; performing collaborative influence analysis according to the regional historical micro-meteorological feature data and the historical power production data to form micro-meteorological-power collaborative feature data; obtaining meteorological prediction data, and performing power prediction analysis in combination with the micro-meteorological-power collaborative feature data to form collaborative power prediction result data. The method can realize accurate and effective prediction of new energy power through more detailed meteorological analysis.

Description

Technical Field

[0001] This invention relates to the field of new energy power prediction technology, and more specifically, to a collaborative optimization method for micro-meteorological data fusion and new energy power prediction. Background Technology

[0002] The development of new energy technologies is progressing rapidly, gradually becoming an important part of energy supply. However, because the production of new energy is greatly affected by meteorological and environmental conditions, its production power fluctuates significantly, and its impact on the power grid during grid connection is also substantial. If its power output cannot be effectively predicted and processed, the grid connection efficiency will be affected.

[0003] Currently, the prediction of new energy power is mainly achieved through simple meteorological records and analysis. This method is simplistic and crude, and the power prediction results obtained are not very accurate, failing to meet the needs of power prediction.

[0004] Therefore, designing a collaborative optimization method for micro-meteorological data fusion and new energy power prediction, which can achieve accurate and effective prediction of new energy power through more detailed meteorological analysis, is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide a collaborative optimization method for micro-meteorological data fusion and new energy power prediction. By using historical meteorological data and new energy power production data that match the meteorological data in the time dimension, micro-meteorological features are extracted in the new energy production area and power production data of new energy equipment are analyzed. Then, by using micro-meteorological feature data and power conversion data of new energy production equipment, a collaborative data on the impact of micro-meteorology on new energy power production is established. This provides an important and accurate analytical model for subsequent prediction of new energy power production based on meteorological forecast data. Compared with simple meteorological analysis to determine power conditions, this method greatly improves the accuracy and real-time performance of new energy production power prediction.

[0006] In a first aspect, the present invention provides a collaborative optimization method for micro-meteorological data fusion and new energy power prediction, comprising: collecting historical meteorological data and extracting regional micro-meteorological features based on the time dimension to form regional historical micro-meteorological feature data; collecting historical new energy production data and extracting power production information based on the time dimension to form historical power production data; performing collaborative impact analysis based on regional historical micro-meteorological feature data and historical power production data to form micro-meteorological-power collaborative feature data; acquiring meteorological forecast data and performing power prediction analysis in conjunction with the micro-meteorological-power collaborative feature data to form collaborative power prediction result data.

[0007] In this invention, the method extracts micro-meteorological features and analyzes the power production data of new energy equipment within the new energy production area based on historical meteorological data and new energy power production data that match the meteorological data in the time dimension. Then, it uses the micro-meteorological feature data and the power conversion data of new energy production equipment to establish collaborative data on the impact of micro-meteorology on new energy power production. This provides an important and accurate analytical model for subsequent prediction of new energy power production based on meteorological forecast data. Compared with simple meteorological analysis to determine the power situation, it greatly improves the accuracy and real-time performance of new energy production power prediction.

[0008] One possible approach is to collect historical meteorological data and extract regional micro-meteorological features based on the time dimension to form regional historical micro-meteorological feature data. This includes: extracting regional historical micro-meteorological data in new energy production areas based on historical meteorological data; extracting different micro-meteorological parameter data from the regional historical micro-meteorological data in the time dimension to form regional historical micro-meteorological parameter change data; and combining historical data on changes in micro-meteorological parameters in different regions to form regional historical micro-meteorological feature data.

[0009] In this invention, to conduct a reasonable impact analysis on the production of new energy power using historical meteorological data, two aspects need to be considered. The first aspect is the need to refine the historical meteorological data. This refinement mainly involves mapping the meteorological data to the areas where new energy is produced. It's understandable that refining the meteorological data to these areas represents the most accurate data mining approach, since meteorological data acquisition is based on data collection from designated meteorological observation points. Therefore, refining the meteorological data to map it to each individual new energy production unit would lead to inaccuracies due to the precision limitations of meteorological data fitting. The analysis and fitting of meteorological data inherently consider precision to avoid wasting resources on excessive data volume. For relatively low-precision meteorological data, the accuracy, measured by area, might only be accurate to areas of tens or hundreds of square meters. Therefore, mapping to the new energy production area is sufficient, as established new energy production areas are typically hundreds of square meters or even larger. Of course, refining the mapping to each individual new energy production unit would also increase the difficulty of analysis and the amount of data, which is unnecessary, since new energy power is considered to be integrated into the grid in clusters. Secondly, there are many types of meteorological parameters. The parameters that affect the production of different types of new energy are not entirely the same. For example, for wind energy, the main meteorological factors are wind speed, wind direction, and rainfall, while for photovoltaic energy, the main factors are sunlight intensity, sunshine duration, and rainfall. Therefore, it is necessary to extract the meteorological parameters that affect the power of new energy according to its type to ensure that the parameter analysis is reasonable and accurate.

[0010] As one possible approach, historical micro-meteorological data of the region is used to extract different micro-meteorological parameters over time to form historical data on changes in regional micro-meteorological parameters. This includes: identifying meteorological parameters affecting new energy power production; and extracting the changes in different meteorological parameters over time based on the historical micro-meteorological data of the region, thus forming historical change functions for the meteorological parameters. Where n represents the number of different meteorological parameters; the set contains the historical variation functions of different meteorological parameters. This generates historical data on regional micrometeorological parameter changes.

[0011] In this invention, to establish reasonable micro-meteorological data affecting new energy power production, it is necessary to first determine the meteorological parameters affecting new energy power production. Of course, it is not necessary to directly confirm the meteorological parameters, because even if meteorological parameters that do not affect new energy power production are subsequently introduced into the data analysis, they will not generate correlation characteristics in the data analysis due to their lack of influence on new energy power. However, such analysis will produce a large amount of invalid data. Therefore, to further improve and optimize the efficiency and accuracy of data analysis, it is necessary to first confirm the meteorological parameters affecting new energy power production when extracting meteorological parameters. This confirmation can be accomplished through manual calibration or big data analysis. For meteorological parameter data, since new energy power is a time-dimensional information quantity, for the sake of reasonable subsequent analysis, the impact of meteorological parameters on new energy power is also obtained in chronological order when extracting meteorological parameters, establishing data based on time-dimensional changes that match new energy power.

[0012] One possible approach is to collect historical renewable energy production data and extract time-based power production information to form historical power production data. This includes: determining power variation data within the same analysis period as historical meteorological data based on the historical renewable energy production data; and determining energy input variation data matching the power variation data within the analysis period based on the power variation data and renewable energy power production equipment information, thus forming a historical energy input variation function. .

[0013] In this invention, the power production of new energy sources is also data that changes sequentially over time. Therefore, to determine the influence of meteorological parameters on the power production of new energy sources, historical power data must be extracted to form power change data that matches the changes in meteorological parameters over time. Of course, power data is the result of converting natural energy acquired by new energy production equipment. Therefore, to establish a direct influence relationship between power data and meteorological parameters, the power data needs to be converted into energy input data directly influenced by meteorological information. The form of energy input is determined according to the type of new energy source. For example, for wind energy, it is the energy in the wind utilized by the equipment, such as the windmill's rotation speed; for photovoltaics, it is the light energy collected by the equipment, such as the total photon energy generated. After conversion, using the input energy data as direct data for analyzing the influence of meteorological factors on power can effectively avoid the influence of the operating status of the new energy production equipment itself on power, greatly improving the accuracy of the analysis.

[0014] As one possible approach, a synergistic impact analysis is conducted based on historical micro-meteorological characteristic data and historical power production data of the region to form micro-meteorological-power synergistic characteristic data. This includes: extracting feature values ​​from historical micro-meteorological characteristic data of the region to form a historical micro-meteorological characteristic information set of the region; extracting corresponding historical energy input features from historical power production data based on the historical micro-meteorological characteristic information set of the region to form a historical energy input feature information set; and conducting a synergistic impact analysis based on the historical micro-meteorological characteristic information set of the region and the historical energy input feature information set to form micro-meteorological-power synergistic characteristic data.

[0015] In this invention, if we directly use the time-dimensional function change data of meteorological parameters to analyze the synergistic relationship with the energy input change function, the resulting synergistic data will have two shortcomings. First, because the analysis introduces the time parameter, the influence of meteorological parameters on energy input data is time-dependent. However, for meteorological data, time-dependent data does not necessarily have strong regularity. For example, there will be differences between meteorological data from the same period this year and last year. The larger the time span, the smaller the regularity. Therefore, the introduction of the time parameter will reduce the accuracy of the analysis results. Moreover, the time parameter truly affects the process of how changes in the service life of new energy equipment affect the success rate of input energy conversion. This application uses energy input as direct data for the analysis of the influence of meteorological parameters, thus eliminating the influence of the time parameter. Therefore, it is unnecessary to introduce the time parameter again. Secondly, if data containing time parameters is used for synergy analysis, the influence of these time parameters must be considered, and the analysis must also be conducted over a certain time span. Therefore, the synergy analysis results are not a point-to-point representation of synergistic relationships, but rather a representation of relationships over a specific time period. This can lead to a decrease in accuracy because the analysis requires matching data over a certain time period. After all, the analyzed synergistic relationships cannot accurately express the impact of large fluctuations in certain meteorological parameters over a short period. Therefore, this application considers excluding time parameters. After excluding them, it is necessary to consider how to extract reasonable feature data for synergy analysis to ensure the accuracy of the analysis results.

[0016] As one possible approach, feature value extraction is performed on historical micro-meteorological characteristic data of the region to form a set of historical micro-meteorological characteristic information for the region, including: based on the historical variation functions of different meteorological parameters in the historical micro-meteorological characteristic data of the region. Feature value extraction is performed in the following manner: using time parameters as a reference, the historical variation functions of different meteorological parameters are analyzed. Mapping these coordinates into the same coordinate system forms parameter feature extraction coordinate data; time point calibration is performed on the parameter feature extraction coordinate data for feature extraction; for each determined time point, historical variation functions of all meteorological parameters corresponding to that time point are extracted. Meteorological parameter values ​​are used to form corresponding micro-meteorological historical feature groups. k represents the number of different time points; the historical micro-meteorological feature groups corresponding to all time points are collected to form a regional historical micro-meteorological feature information set. .

[0017] In this invention, feature data extraction mainly involves acquiring representative feature values ​​as input data for collaborative analysis to ensure that the collaborative analysis can reasonably and accurately demonstrate the collaborative relationship. It is understood that the meteorological parameters affecting energy input values ​​are diverse, and each meteorological parameter requires feature extraction. However, it is necessary to consider that the extracted feature values ​​have data matching properties between different meteorological parameters. Therefore, extracting features based on time parameters can effectively ensure the data matching properties between different meteorological parameters.

[0018] As one possible implementation, time point calibration for feature extraction in the parameter feature extraction coordinate data includes: calibrating different time points in the parameter feature extraction coordinate data, and the calibrated time points satisfy the following condition: the calibrated time points cover the historical variation function of each meteorological parameter. The maximum and minimum values; the total number of time points identified, excluding any historical variation function of meteorological parameters. After determining the number of time points at which the maximum or minimum value is reached, the interval between any two adjacent time points at the remaining time points is... and Between, among them, M represents the total duration of the analysis period, and M is a function that excludes historical variations of any meteorological parameters. The total number of time points remaining after the number of time points of the maximum or minimum value, where i represents the interval adjustment value and i is a natural number greater than 1.

[0019] In this invention, time point calibration needs to consider two aspects. First, the characteristic values ​​of the meteorological parameters corresponding to the calibrated time points must be representative. Here, representativeness is defined by the maximum and minimum values ​​within the analysis period. Of course, to further improve the accuracy and rationality of data extraction, representativeness can also consider the point of minimum rate of change, the point of maximum rate of change, and points where the rate of change changes positively or negatively. Second, simply extracting representative points is insufficient; it also requires a larger number of normal data points to support the representative data. Therefore, this is achieved by reasonably setting the quantity and the span of normal data point extraction. M and i can be determined based on the actual situation.

[0020] As one possible implementation, based on the regional historical micro-meteorological characteristic information set, corresponding historical energy input features are extracted from historical power production data to form an energy input historical feature information set, including: based on the regional historical micro-meteorological characteristic information set... The time point determined in the energy input history variation function Position calibration is performed; historical energy input feature values ​​corresponding to all calibrated time points are extracted to form a historical energy input feature information set. ,in, , This represents the historical energy input feature value corresponding to time point k.

[0021] In this invention, the extraction of historical energy input feature values ​​mainly involves matching the time points with the time points of meteorological parameter feature value extraction to ensure the rationality of subsequent analysis.

[0022] As one possible approach, based on the historical micro-meteorological characteristic information set and the historical energy input characteristic information set of the region, a synergistic impact analysis is conducted to form micro-meteorological-power synergistic characteristic data, including: establishing synergistic relationships. ,in, This represents the input value for the meteorological parameter numbered n. Indicates energy input value; sets up regional historical micro-meteorological characteristic information. Micrometeorological historical characteristics at different time points Same energy input historical feature information set Different energy input historical eigenvalues After mapping the corresponding time points, the results are substituted into the collaborative relation. In the process, the synergistic relationship was determined. The parameter values ​​in the text.

[0023] In this invention, the analysis of synergistic relationships mainly involves determining these relationships. The determination of these synergistic relationships primarily relies on the mapping relationship between acquired micrometeorological characteristic values ​​and energy input characteristic values, employing a multi-factor simultaneous analysis. The specific methods for analyzing these relationships are diverse. One approach is to group the mapped characteristic value sets based on the number of quantities in the relationship, determining the parameter values ​​in each group's relationship, and then averaging the parameter values ​​in each group to obtain a comprehensive relationship. Alternatively, one can first extract features equal to the number of parameters, determine a relationship, and then sequentially substitute the remaining feature sets to adjust the parameters based on the deviation between the energy input value determined by the relationship and the actual energy input value at the corresponding time point, thereby improving the accuracy of the relationship.

[0024] One possible approach is to acquire meteorological forecast data and combine it with micro-meteorological-power synergistic feature data for power prediction analysis, forming synergistic power prediction results data. This includes: extracting real-time meteorological parameter values ​​for different meteorological parameters at different time points based on the meteorological forecast data; and combining the extracted real-time meteorological parameter values ​​for different meteorological parameters at different time points with the synergistic relationship. The process involves determining the real-time energy input value at the corresponding time point; determining the corresponding real-time power value based on the real-time energy input value at different time points; and performing fitting analysis on the determined real-time power values ​​at different time points in chronological order to form collaborative power prediction result data.

[0025] In this invention, after determining the cooperative relationship, it can be used to make reasonable predictions of real-time power. Considering that meteorological parameters are collected according to a preset time, the discrete meteorological parameter data obtained, after being combined with the cooperative relationship to determine the actual power, needs to be reasonably fitted in the time dimension to form a real-time power prediction result that is continuous in the time dimension. There are various methods for analysis, such as least squares fitting, or connecting the discrete power values ​​with a piecewise linear relationship in the time dimension and smoothing the points on the line. Any method that can form a smooth real-time power prediction curve is acceptable.

[0026] The beneficial effects of the synergistic optimization method for micro-meteorological data fusion and new energy power prediction provided by this invention are as follows:

[0027] This method extracts micro-meteorological features and analyzes the power production data of new energy equipment within the new energy production area by using historical meteorological data and new energy power production data that match the meteorological data in the time dimension. Then, it uses the micro-meteorological feature data and the power conversion data of new energy production equipment to establish a collaborative data on the impact of micro-meteorology on new energy power production. This provides an important and accurate analytical model for subsequent prediction of new energy power production based on meteorological forecast data. Compared with simple meteorological analysis to determine the power situation, it greatly improves the accuracy and real-time performance of new energy production power prediction. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1A flowchart illustrating the implementation steps of the collaborative optimization method for micro-meteorological data fusion and new energy power prediction provided in this embodiment of the invention;

[0030] Figure 2 This is a schematic diagram of the structure of the collaborative optimization method for micro-meteorological data fusion and new energy power prediction provided in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention.

[0032] The development of new energy technologies is progressing rapidly, gradually becoming an important part of energy supply. However, because the production of new energy is greatly affected by meteorological and environmental conditions, its production power fluctuates significantly, and its impact on the power grid during grid connection is also substantial. If its power output cannot be effectively predicted and processed, the grid connection efficiency will be affected.

[0033] Currently, the prediction of new energy power is mainly achieved through simple meteorological records and analysis. This method is simplistic and crude, and the power prediction results obtained are not very accurate, failing to meet the needs of power prediction.

[0034] refer to Figures 1-2 This invention provides a collaborative optimization method for micro-meteorological data fusion and new energy power prediction. This method extracts micro-meteorological features and analyzes the power production data of new energy equipment in the new energy production area based on historical meteorological data and new energy power production data that match the meteorological data in the time dimension. Then, it uses the micro-meteorological feature data and the power conversion data of new energy production equipment to establish collaborative data on the impact of micro-meteorology on new energy power production. This provides an important and accurate analytical model for subsequent prediction of new energy power production based on meteorological forecast data. Compared with simple meteorological analysis to determine the power situation, it greatly improves the accuracy and real-time performance of new energy production power prediction.

[0035] The synergistic optimization method for micro-meteorological data fusion and new energy power prediction is specifically configured as follows:

[0036] S1: Collect historical meteorological data and extract regional micro-meteorological features based on the time dimension to form regional historical micro-meteorological feature data.

[0037] Historical meteorological data is collected and regional micro-meteorological features are extracted based on the time dimension to form regional historical micro-meteorological feature data, including: extracting regional historical micro-meteorological data in new energy production areas based on historical meteorological data; extracting different micro-meteorological parameter data in the time dimension from the regional historical micro-meteorological data to form regional historical micro-meteorological parameter change data; and combining historical micro-meteorological parameter change data from different regions to form regional historical micro-meteorological feature data.

[0038] To conduct a reasonable impact analysis on renewable energy production using historical meteorological data, two aspects need to be considered. First, the historical meteorological data needs to be refined. This refinement mainly involves mapping the meteorological data to the regions where renewable energy is produced. It's understandable that refining the meteorological data to these regions represents the most accurate data mining approach, as meteorological data acquisition is based on data collection from designated meteorological observation points. Therefore, mapping the meteorological data to each individual renewable energy production unit would lead to inaccuracies due to the precision limitations of meteorological data fitting. The analysis and fitting of meteorological data inherently consider precision to avoid wasting resources on excessive data volume. For relatively low-precision meteorological data, the accuracy, measured by area, might only be accurate to areas of tens or hundreds of square meters. Mapping to the renewable energy production area is sufficient; typically, established renewable energy production areas are hundreds of square meters or even larger. Of course, refining the mapping to each individual renewable energy production unit would also increase the analysis difficulty and data volume, which is unnecessary, since renewable energy production is considered in clusters when connected to the grid. Secondly, there are many types of meteorological parameters. The parameters that affect the production of different types of new energy are not entirely the same. For example, for wind energy, the main meteorological factors are wind speed, wind direction, and rainfall, while for photovoltaic energy, the main factors are sunlight intensity, sunshine duration, and rainfall. Therefore, it is necessary to extract the meteorological parameters that affect the power of new energy according to its type to ensure that the parameter analysis is reasonable and accurate.

[0039] Different micro-meteorological parameters are extracted from historical micro-meteorological data of the region over time to form historical data on changes in regional micro-meteorological parameters. This includes: identifying meteorological parameters affecting new energy power production; and extracting the changes in different meteorological parameters over time based on the historical micro-meteorological data of the region, and forming historical change functions for the meteorological parameters. Where n represents the number of different meteorological parameters; the set contains the historical variation functions of different meteorological parameters. This generates historical data on regional micrometeorological parameter changes.

[0040] To establish reasonable micro-meteorological data affecting renewable energy power production, it is necessary to first identify the meteorological parameters that influence renewable energy power production. While it's not always necessary to directly confirm these parameters, even if meteorological parameters that don't affect renewable energy power production are subsequently included in the data analysis, they may still generate correlation characteristics in the analysis due to their lack of direct impact on renewable energy power. However, such analysis would produce a large amount of invalid data. Therefore, to further improve and optimize the efficiency and accuracy of data analysis, it is essential to first confirm the meteorological parameters affecting renewable energy power production during the extraction process. This confirmation can be accomplished through manual calibration or big data analysis. Since renewable energy power is a time-dependent information quantity, for the sake of reasonable subsequent analysis, the impact of meteorological parameters on renewable energy power is extracted sequentially along the time dimension, establishing data based on time-varying changes that match renewable energy power.

[0041] S2: Collect historical new energy production data and extract power production information based on the time dimension to form historical power production data.

[0042] Historical renewable energy production data is collected, and time-based power production information is extracted to form historical power production data. This includes: determining power change data within the same analysis period as historical meteorological data based on historical renewable energy production data; and determining energy input change data matching the power change data within the analysis period based on the power change data and renewable energy power production equipment information, thus forming a historical energy input change function. .

[0043] New energy power production is also data that changes sequentially over time. Therefore, to determine the impact of meteorological parameters on new energy power production, historical power data must be extracted to form power change data that matches the changes in meteorological parameters over time. Of course, power data is the result of converting natural energy acquired by new energy production equipment. Therefore, to establish a direct relationship between power data and meteorological parameters, the power data needs to be converted into energy input data directly influenced by meteorological information. The form of energy input is determined according to the type of new energy source. For example, for wind energy, it is the energy in the wind utilized by the equipment, such as the windmill's rotation speed; for photovoltaics, it is the light energy collected by the equipment, such as the total photon energy generated. After conversion, using the input energy data as direct data for analyzing the impact of meteorological factors on power can effectively avoid the influence of the operating status of the new energy production equipment itself on power, greatly improving the accuracy of the analysis.

[0044] S3: Based on historical micro-meteorological characteristic data and historical power production data of the region, conduct synergistic impact analysis to form micro-meteorological-power synergistic characteristic data.

[0045] Based on historical micro-meteorological characteristic data and historical power production data of the region, a synergistic impact analysis is conducted to form micro-meteorological-power synergistic characteristic data. This includes: extracting feature values ​​from historical micro-meteorological characteristic data of the region to form a historical micro-meteorological characteristic information set of the region; extracting corresponding historical energy input features from historical power production data based on the historical micro-meteorological characteristic information set of the region to form a historical energy input feature information set; and conducting a synergistic impact analysis based on the historical micro-meteorological characteristic information set of the region and the historical energy input feature information set to form micro-meteorological-power synergistic characteristic data.

[0046] If we directly use the time-dimensional variation data of meteorological parameters to analyze the synergistic relationship with the energy input variation function, the resulting synergistic data will have two shortcomings. First, because the analysis introduces the time parameter, the influence of meteorological parameters on energy input data is time-dependent. However, for meteorological data, time dependence does not necessarily have strong regularity. For example, there will be differences between meteorological data from this year and the same period last year. The larger the time span, the smaller the regularity. Therefore, the introduction of the time parameter will reduce the accuracy of the analysis results. Moreover, the time parameter truly affects the process of how changes in the service life of new energy equipment affect the success rate of input energy conversion. This application uses energy input as direct data for the analysis of the influence of meteorological parameters, thus eliminating the influence of the time parameter. Therefore, it is unnecessary to introduce the time parameter again. Secondly, if data containing time parameters is used for synergy analysis, the influence of these time parameters must be considered, and the analysis must also be conducted over a certain time span. Therefore, the synergy analysis results are not a point-to-point representation of synergistic relationships, but rather a representation of relationships over a specific time period. This can lead to a decrease in accuracy because the analysis requires matching data over a certain time period. After all, the analyzed synergistic relationships cannot accurately express the impact of large fluctuations in certain meteorological parameters over a short period. Therefore, this application considers excluding time parameters. After excluding them, it is necessary to consider how to extract reasonable feature data for synergy analysis to ensure the accuracy of the analysis results.

[0047] Feature values ​​are extracted from historical micro-meteorological characteristic data of the region to form a set of historical micro-meteorological characteristic information for the region, including: based on the historical variation functions of different meteorological parameters in the historical micro-meteorological characteristic data of the region. Feature value extraction is performed in the following manner: using time parameters as a reference, the historical variation functions of different meteorological parameters are analyzed. Mapping these coordinates into the same coordinate system forms parameter feature extraction coordinate data; time point calibration is performed on the parameter feature extraction coordinate data for feature extraction; for each determined time point, historical variation functions of all meteorological parameters corresponding to that time point are extracted. Meteorological parameter values ​​are used to form corresponding micro-meteorological historical feature groups. k represents the number of different time points; the historical micro-meteorological feature groups corresponding to all time points are collected to form a regional historical micro-meteorological feature information set. .

[0048] Feature data extraction primarily involves acquiring representative feature values ​​as input data for collaborative analysis to ensure that the analysis can accurately and reasonably represent collaborative relationships. It is understandable that the meteorological parameters influencing energy input are diverse, and each parameter requires feature extraction. However, it is necessary to consider the data matching between different meteorological parameters. Therefore, extracting features based on time parameters can effectively guarantee the data matching between different meteorological parameters.

[0049] The time point calibration for feature extraction in the parameter feature extraction coordinate data includes: calibrating different time points in the parameter feature extraction coordinate data, and the calibrated time points meet the following condition: the calibrated time points cover the historical variation function of each meteorological parameter. The maximum and minimum values; the total number of time points identified, excluding any historical variation function of meteorological parameters. After determining the number of time points at which the maximum or minimum value is reached, the interval between any two adjacent time points at the remaining time points is... and Between, among them, M represents the total duration of the analysis period, and M is a function that excludes historical variations of any meteorological parameters. The total number of time points remaining after the number of time points of the maximum or minimum value, where i represents the interval adjustment value and i is a natural number greater than 1.

[0050] Time point calibration needs to consider two aspects. First, the characteristic values ​​of the meteorological parameters corresponding to the calibrated time points must be representative. Here, representativeness is defined by the maximum and minimum values ​​within the analysis period. Of course, to further improve the accuracy and rationality of data extraction, representativeness can also consider the points of minimum and maximum rate of change, points where the rate of change changes positively or negatively, etc. Second, simply extracting representative points is insufficient; it also requires a larger number of normal data points to support the representative data. Therefore, this is achieved by reasonably setting the quantity and the span of normal data point extraction. M and i can be determined based on the actual situation.

[0051] Based on the regional historical micro-meteorological characteristic information set, corresponding historical energy input characteristics are extracted from historical power production data to form an energy input historical characteristic information set, including: based on the regional historical micro-meteorological characteristic information set. The time point determined in the energy input history variation function Position calibration is performed; historical energy input feature values ​​corresponding to all calibrated time points are extracted to form a historical energy input feature information set. ,in, , This represents the historical energy input feature value corresponding to time point k.

[0052] The extraction of historical characteristic values ​​of energy input mainly requires matching the time points with the time points of meteorological parameter characteristic value extraction to ensure the rationality of subsequent analysis.

[0053] Based on the historical micro-meteorological and energy input characteristic information sets of the region, a synergistic impact analysis is conducted to generate micro-meteorological-power synergistic characteristic data, including: establishing synergistic relationships. ,in, This represents the input value for the meteorological parameter numbered n. Indicates energy input value; sets up regional historical micro-meteorological characteristic information. Micrometeorological historical characteristics at different time points Same energy input historical feature information set Different energy input historical eigenvalues After mapping the corresponding time points, the results are substituted into the collaborative relation. In the process, the synergistic relationship was determined. The parameter values ​​in the text.

[0054] The analysis of synergistic relationships primarily involves determining these relationships. The determination of these synergistic relationships mainly relies on the mapping relationship between acquired micrometeorological characteristic values ​​and energy input characteristic values, employing a multi-factor analysis. The specific methods for analyzing these relationships are diverse. One approach is to group the mapped characteristic values ​​based on the number of quantities in the relationship, determining the parameter values ​​in each group, and then averaging the parameter values ​​in each group to obtain a comprehensive relationship. Another approach is to first extract features equal to the number of parameters, determine a relationship, and then sequentially substitute the remaining feature groups to adjust the parameters based on the deviation between the energy input value determined by the relationship and the actual energy input value at the corresponding time point, thereby improving the accuracy of the relationship.

[0055] S4: Acquire meteorological forecast data and combine it with micro-meteorological-power synergistic characteristic data to perform power prediction analysis and form synergistic power prediction result data.

[0056] Acquire meteorological forecast data and combine it with micrometeorological-power synergistic feature data to perform power prediction analysis, forming synergistic power prediction results data, including: extracting real-time meteorological parameter values ​​for different meteorological parameters at different time points based on the meteorological forecast data; and combining the extracted real-time meteorological parameter values ​​for different meteorological parameters at different time points with the synergistic relationship formula. The process involves determining the real-time energy input value at the corresponding time point; determining the corresponding real-time power value based on the real-time energy input value at different time points; and performing fitting analysis on the determined real-time power values ​​at different time points in chronological order to form collaborative power prediction result data.

[0057] Once the coordination relationship is established, it can be used to make reasonable predictions of real-time power. Considering that meteorological parameters are collected according to a preset time frame, the discrete meteorological parameter data obtained, after being combined with the coordination relationship to determine the actual power, needs to be reasonably fitted in the time dimension to form a continuous real-time power prediction result. There are various analysis methods, such as least squares fitting, or connecting the discrete power values ​​along a broken line in the time dimension and smoothing the points on the line. Any method that can form a smooth real-time power prediction curve is acceptable.

[0058] This application also provides the specific components of the system. It includes a data acquisition unit for collecting historical meteorological data, historical new energy production data, and meteorological forecast data; a feature analysis unit for extracting regional micro-meteorological features from the historical meteorological data collected by the data acquisition unit based on the time dimension, forming regional historical micro-meteorological feature data, extracting power production information from the historical new energy production data based on the time dimension, forming historical power production data, and combining the regional historical micro-meteorological feature data and historical power production data to perform synergistic impact analysis, forming micro-meteorological-power synergistic feature data; and a prediction analysis unit for performing prediction analysis on the micro-meteorological-power synergistic feature data formed by the feature analysis unit from the meteorological forecast data collected by the data acquisition unit, forming synergistic power prediction result data.

[0059] In summary, the beneficial effects of the synergistic optimization method for micro-meteorological data fusion and new energy power prediction provided in this embodiment of the invention are as follows:

[0060] This method extracts micro-meteorological features and analyzes the power production data of new energy equipment within the new energy production area by using historical meteorological data and new energy power production data that match the meteorological data in the time dimension. Then, it uses the micro-meteorological feature data and the power conversion data of new energy production equipment to establish a collaborative data on the impact of micro-meteorology on new energy power production. This provides an important and accurate analytical model for subsequent prediction of new energy power production based on meteorological forecast data. Compared with simple meteorological analysis to determine the power situation, it greatly improves the accuracy and real-time performance of new energy production power prediction.

[0061] In the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In the specific implementation process, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0062] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0063] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this application embodiment. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0064] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This application does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0065] The “protocol” mentioned in the embodiments of this application may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to future communication systems. The embodiments of this application do not specifically limit this.

[0066] In the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0067] In the description of the embodiments of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0068] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0069] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0070] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0071] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0072] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0073] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0074] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0075] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0077] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0079] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A synergistic optimization method for micro-meteorological data fusion and new energy power prediction, characterized in that, include: Historical meteorological data is collected, and regional micro-meteorological features are extracted based on the time dimension to form regional historical micro-meteorological feature data; Historical new energy production data is collected, and power production information is extracted based on the time dimension to form historical power production data; Based on the historical micro-meteorological characteristic data and the historical power production data of the region, a synergistic impact analysis is performed to form micro-meteorological-power synergistic characteristic data; Meteorological forecast data is acquired and combined with the micro-meteorological-power synergistic feature data to perform power prediction analysis, thereby forming synergistic power prediction result data; Specifically, based on the historical micro-meteorological characteristic data and the historical power production data of the region, a synergistic impact analysis is performed to form micro-meteorological-power synergistic characteristic data, including: Feature values ​​are extracted from the historical micro-meteorological characteristic data of the region to form a set of historical micro-meteorological characteristic information for the region; Based on the historical micro-meteorological feature information set of the region, the corresponding historical energy input features are extracted from the historical power production data to form a historical energy input feature information set. Based on the historical micro-meteorological feature information set of the region and the historical energy input feature information set, a synergistic impact analysis is performed to form the micro-meteorological-power synergistic feature data; Feature values ​​are extracted from the historical micro-meteorological characteristic data of the region to form a set of historical micro-meteorological characteristic information for the region, including: Based on the historical variation functions of different meteorological parameters in the historical micrometeorological characteristic data of the region Feature value extraction is performed in the following ways: Using time parameters as a reference, the historical variation functions of different meteorological parameters are... Mapped in the same coordinate system, forming coordinate data for parametric feature extraction; Time point calibration for feature extraction in the parameter feature extraction coordinate data; For each determined time point, extract the historical variation function of all meteorological parameters corresponding to that time point. Meteorological parameter values ​​are used to form corresponding micro-meteorological historical feature groups. k represents the number of different time points; The historical micro-meteorological feature sets corresponding to all time points are collected to form the historical micro-meteorological feature information set of the region. ; The time point calibration for feature extraction in the parameter feature extraction coordinate data includes: The coordinate data extracted from the parameter features are calibrated at different time points, and the calibrated time points meet the following conditions: The calibrated time points cover the historical variation function of each of the meteorological parameters. The maximum and minimum values ​​on; The total number of calibrated time points excludes those with any of the historical variation functions of the meteorological parameters mentioned. After determining the number of time points at which the maximum or minimum value is reached, the interval between any two adjacent time points at the remaining time points is... and Between, among them, M represents the total duration of the analysis period, and M is a function to exclude any historical variations of the meteorological parameters mentioned above. The total number of time points remaining after the number of time points of the maximum or minimum value, where i represents the interval adjustment value and i is a natural number greater than 1.

2. The synergistic optimization method for micro-meteorological data fusion and new energy power prediction according to claim 1, characterized in that, The process involves collecting historical meteorological data and extracting regional micro-meteorological features based on the time dimension to form regional historical micro-meteorological feature data, including: Based on the historical meteorological data, extract the regional historical micro-meteorological data for the new energy production area; The historical micro-meteorological data of the region are used to extract different micro-meteorological parameters in the time dimension to form historical data on changes in regional micro-meteorological parameters; Historical micrometeorological parameter change data of different regions are collected to form historical micrometeorological characteristic data of the region.

3. The synergistic optimization method for micro-meteorological data fusion and new energy power prediction according to claim 2, characterized in that, The step of extracting different micrometeorological parameters from the historical micrometeorological data of the region over time to form historical data on changes in regional micrometeorological parameters includes: Determine the meteorological parameters that affect the production of new energy power; Based on the historical micro-meteorological data of the region, the variation data of different meteorological parameters over time are extracted, and historical variation functions of meteorological parameters are formed. , where n represents the number of different meteorological parameters; The set of historical variation functions of the meteorological parameters corresponding to different meteorological parameters This generates historical data on the changes in micrometeorological parameters in the region.

4. The synergistic optimization method for micro-meteorological data fusion and new energy power prediction according to claim 3, characterized in that, The process of collecting historical new energy production data and extracting power production information based on the time dimension to form historical power production data includes: Based on the historical new energy production data, power change data within the same analysis period as the historical meteorological data were determined; Based on the power change data and information on new energy power production equipment, energy input change data matching the power change data within the analysis period is determined, forming a historical energy input change function. .

5. The synergistic optimization method for micro-meteorological data fusion and new energy power prediction according to claim 4, characterized in that, The step involves extracting corresponding historical energy input features from the historical power production data based on the historical micro-meteorological feature information set of the region, forming a historical energy input feature information set, including: Based on the historical micrometeorological characteristics information set of the region At the time point determined in the energy input history variation function Position calibration is performed during this process; Extract the historical energy input feature values ​​corresponding to all calibrated time points to form the historical energy input feature information set. ,in, , This represents the historical energy input feature value corresponding to time point k.

6. The synergistic optimization method for micro-meteorological data fusion and new energy power prediction according to claim 5, characterized in that, The step involves performing a synergistic impact analysis based on the historical micro-meteorological characteristic information set of the region and the historical energy input characteristic information set to form the micro-meteorological-power synergistic characteristic data, including: Establish collaborative relationships ,in, This represents the input value for the meteorological parameter numbered n. Indicates the energy input value; The historical micro-meteorological feature information set of the region The micrometeorological historical characteristics group at different time points The same as the energy input historical feature information set Different energy input historical eigenvalues After mapping the corresponding time points, the corresponding collaborative relationship is substituted into the formula. In the process, the collaborative relationship is determined. The parameter values ​​in the text.

7. The synergistic optimization method for micro-meteorological data fusion and new energy power prediction according to claim 6, characterized in that, The acquisition of meteorological forecast data, combined with the micro-meteorological-power synergistic feature data, to perform power prediction analysis and form synergistic power prediction result data includes: Based on the meteorological forecast data, extract the real-time meteorological parameter values ​​for different meteorological parameters at different time points; The real-time meteorological parameter values ​​extracted at different time points are combined with the synergistic relationship. Determine the real-time energy input value at the corresponding time point; Based on the real-time energy input values ​​at different points in time, the corresponding real-time power values ​​are determined. The real-time power values ​​determined at different time points are fitted and analyzed in chronological order to form the collaborative power prediction result data.

Images