Distributed new energy meteorological data management method and system

Abstract

The invention provides a distributed new energy meteorological data management method and system, and relates to the technical field of data management, and the method comprises the steps: receiving a new energy meteorological data management request through a user side; determining an associated meteorological index according to the distributed new energy type; according to the associated meteorological indexes, a communication intelligent acquisition terminal obtains future time zone meteorological monitoring information of the distributed new energy deployment position; and predicting future time zone generating capacity of the distributed new energy according to the generating capacity predictor, and sending the future time zone generating capacity to the user side. The technical problem that in the prior art, a new energy meteorological station lacks an intelligent analysis means, the power generation rate cannot be quantitatively predicted in advance, and new energy meteorological data management is poor is solved. The technical effects that the meteorological mode is automatically recognized by building the model, the new energy power generation potential is predicted, and efficient, fine and intelligent management of the new energy meteorological data is ensured are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a distributed new energy meteorological data management method and system. Background Art

[0002] With the rapid development of the new energy industry, especially the widespread application of renewable energy such as solar energy and wind energy, the accurate acquisition and management of new energy meteorological data has become a crucial link. Traditionally, new energy meteorological stations usually have basic monitoring and data recording functions, and transmit the collected data to a centralized data center for processing and storage. However, although traditional new energy meteorological stations play an important role in data collection, their data processing mode and analysis framework are relatively basic and single, limited to data collection and simple processing, lacking intelligent analysis methods, and unable to make accurate quantitative predictions of future new energy power generation, resulting in poor management of new energy meteorological data, uneven energy distribution, resource waste or supply shortages.

[0003] The existing technology has the technical problem that new energy meteorological stations lack intelligent analysis methods and cannot quantitatively predict power generation rates in advance, resulting in poor management of new energy meteorological data. Summary of the invention

[0004] The present application provides a distributed new energy meteorological data management method and system, which is used to solve the technical problem in the prior art that new energy meteorological stations lack intelligent analysis methods and cannot quantitatively predict power generation rates in advance, resulting in poor management of new energy meteorological data.

[0005] In view of the above problems, the present application provides a distributed new energy meteorological data management method and system.

[0006] The first aspect of the present application provides a distributed new energy meteorological data management method, the method comprising: receiving a new energy meteorological data management request through a user end, wherein the new energy meteorological data management request includes a distributed new energy type and a distributed new energy deployment location; determining associated meteorological indicators based on the distributed new energy type; based on the associated meteorological indicators, a communication intelligent collection terminal obtains future time zone meteorological monitoring information of the distributed new energy deployment location; predicting the future time zone power generation of the distributed new energy based on a power generation predictor, and sending the information to the user end.

[0007] The second aspect of the present application provides a distributed new energy meteorological data management system, the system comprising: a management request receiving module, the management request receiving module is used to receive a new energy meteorological data management request through a user end, wherein the new energy meteorological data management request includes a distributed new energy type and a distributed new energy deployment location; an associated meteorological indicator determination module, the associated meteorological indicator determination module is used to determine associated meteorological indicators according to the distributed new energy type; a meteorological monitoring information acquisition module, the meteorological monitoring information acquisition module is used to obtain future time zone meteorological monitoring information of the distributed new energy deployment location according to the associated meteorological indicators by a communication intelligent collection terminal; a power generation prediction module, the power generation prediction module is used to predict the future time zone power generation of the distributed new energy according to the power generation predictor, and send it to the user end.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The method provided in the embodiment of the present application receives a new energy meteorological data management request through the user end; determines the associated meteorological index according to the type of distributed new energy; according to the associated meteorological index, the communication intelligent acquisition terminal obtains the future time zone meteorological monitoring information of the distributed new energy deployment location; and predicts the future time zone power generation of the distributed new energy according to the power generation predictor, and sends it to the user end. The technical effect of automatically identifying meteorological patterns by building a model, predicting the power generation potential of new energy, and ensuring efficient, precise, and intelligent management of new energy meteorological data is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flow chart of a distributed new energy meteorological data management method provided in this application;

[0012] Figure 2 A structural diagram of a distributed new energy meteorological data management system provided for this application.

[0013] Description of the reference numerals: management request receiving module 11 , associated meteorological index determining module 12 , meteorological monitoring information obtaining module 13 , power generation prediction module 14 . DETAILED DESCRIPTION

[0014] This application provides a distributed new energy meteorological data management method and system, which is used to solve the technical problem that new energy meteorological stations in the prior art lack intelligent analysis methods and cannot quantitatively predict power generation rates in advance, resulting in poor management of new energy meteorological data. The method achieves the technical effect of automatically identifying meteorological patterns by building models, predicting new energy power generation potential, and ensuring efficient, precise, and intelligent management of new energy meteorological data.

[0015] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. 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. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a distributed new energy meteorological data management method, the method comprising:

[0017] A new energy meteorological data management request is received through a user terminal, wherein the new energy meteorological data management request includes a distributed new energy type and a distributed new energy deployment location.

[0018] Specifically, the user initiates a new energy meteorological data management request through the user terminal, and the user terminal refers to the interface or device through which the user interacts with the meteorological data management service platform, such as a mobile application, a web page, or a dedicated management terminal. The meteorological data management service platform receives the new energy meteorological data management request through the user terminal, and the meteorological data management request contains two key information: the type of distributed new energy and the deployment location of the distributed new energy, wherein the distributed new energy type refers to the type of new energy using a distributed layout, such as distributed solar power generation, distributed wind power generation, etc., and the distributed new energy deployment location refers to the specific geographical location where the distributed new energy power generation equipment is installed, which is used to obtain accurate meteorological data.

[0019] According to the type of distributed renewable energy, associated meteorological indicators are determined.

[0020] Specifically, based on the type information of distributed renewable energy, determine the meteorological indicators that are closely related to the power generation of this type of renewable energy. For example, for solar power generation, the key meteorological indicators include solar irradiance, temperature, humidity, etc., and for wind power generation, they may be wind speed, wind direction, temperature, etc.

[0021] Furthermore, according to the distributed new energy type, the associated meteorological indicators are determined, including: obtaining an initial meteorological indicator set; collecting a new energy storage quantity record data set and an initial meteorological indicator characteristic value record data set with the initial meteorological indicator set and the distributed new energy type as constraints; performing correlation analysis based on the new energy storage quantity record data set and the initial meteorological indicator characteristic value record data set to obtain a correlation degree set, wherein the initial meteorological indicator set corresponds one-to-one to the correlation degree set; according to the correlation degree set, selecting the associated meteorological indicators that are greater than or equal to the correlation degree threshold from the initial meteorological indicator set.

[0022] Specifically, according to the type of distributed renewable energy, an initial meteorological index set is obtained, which includes all meteorological parameters that may be related to renewable energy power generation, including wind speed, wind direction, temperature, humidity, irradiance, etc. The initial meteorological index set corresponding to each type of distributed renewable energy is obtained based on the power generation characteristics of this type and historical practical experience, and is used to cover all meteorological factors that may affect power generation.

[0023] Then, the initial meteorological indicator set and the distributed new energy type are used as constraints to perform data collection. Data collection includes collecting new energy storage quantity record data sets and initial meteorological indicator characteristic value record data sets. The new energy storage quantity record data sets refer to the storage quantity data of various distributed new energy sources, such as solar energy and wind energy, in different time periods, which are used to reflect the actual power generation situation in different time periods. The initial meteorological indicator characteristic value record data sets refer to the characteristic values ​​of various meteorological indicators in the same time period, including key meteorological parameters such as wind speed, wind direction, temperature, humidity, and irradiance. Then, the collected new energy storage quantity record data sets and the initial meteorological indicator characteristic value record data sets are subjected to correlation analysis, and the correlation between each initial meteorological indicator and the new energy storage quantity is calculated to obtain a correlation degree set. In the correlation degree set, each initial meteorological indicator corresponds to a correlation degree value, which reflects the closeness of the relationship between each meteorological indicator and the power generation. The higher the correlation degree, the greater the impact of the meteorological indicator on the power generation.

[0024] Finally, based on actual needs and expert experience, a correlation threshold is set according to the correlation set, that is, the correlation threshold is a preset value, which is used to determine which meteorological indicators have a high enough correlation to ensure that the selected associated meteorological indicators have practical significance. Then, the meteorological indicators with a correlation greater than or equal to the preset threshold are screened out from the initial meteorological indicator set as the final associated meteorological indicators. Through correlation analysis and screening, meteorological indicators closely related to distributed renewable energy types can be accurately determined, which reduces unnecessary data redundancy, optimizes the efficiency and accuracy of data collection, and significantly improves the accuracy and reliability of subsequent power generation forecasts.

[0025] According to the associated meteorological indicators, the communication intelligent collection terminal obtains the future time zone meteorological monitoring information of the distributed new energy deployment location.

[0026] Specifically, according to the associated meteorological indicators that have been determined, a connection is established with the intelligent collection terminal through a preset communication protocol, and the intelligent collection terminal is instructed to perform meteorological monitoring for a certain time period in the future for the distributed new energy deployment location. The meteorological monitoring information includes the associated meteorological indicator data for the specified future time zone. The communication intelligent collection terminal refers to the equipment deployed at the edge of the distributed new energy site. The intelligent collection terminal has a variety of high-precision sensors and real-time data transmission capabilities, which are used to collect and record multiple meteorological parameters in the specified area in real time, including wind speed, wind direction, temperature, humidity, irradiance and other key meteorological parameters. By clarifying the associated meteorological indicators through prior communication, the transmission of irrelevant data is effectively reduced. Accurate future time zone meteorological data closely related to power generation is obtained through the intelligent collection terminal, providing accurate and reliable data support for subsequent new energy power generation forecast results.

[0027] The future time zone power generation of distributed renewable energy is predicted based on the power generation predictor and sent to the user end.

[0028] Furthermore, predicting the future time zone power generation of distributed new energy according to the power generation predictor includes: obtaining historical operation data of distributed new energy, wherein the historical operation data includes a new energy control mode historical data set, a meteorological indicator historical data set, a storage capacity historical data set and a power generation historical data set; using the new energy control mode historical data set and the meteorological indicator historical data set as input data of the neural network, and using the storage capacity historical data set as supervision data, to configure the storage capacity predictor; performing conversion rate identification according to the storage capacity historical data set and the power generation historical data set to obtain power utilization; weighting the output layer of the storage capacity predictor according to the power utilization to obtain the power generation predictor.

[0029] Specifically, based on the renewable energy statistical database, comprehensive historical operation data of distributed new energy is obtained, wherein the historical operation data of distributed new energy includes a new energy control mode historical data set, a meteorological indicator historical data set, a power storage historical data set and a power generation historical data set. The new energy control mode historical data set includes the historical operation status of new energy equipment under different control modes, the meteorological indicator historical data set includes historical data of historical meteorological conditions, such as wind speed, irradiance, etc., the power storage historical data set includes the power storage status of new energy equipment in different time periods, and the power generation historical data set includes historical power generation and the corresponding energy storage utilization ratio.

[0030] Then, by using the powerful learning ability of the neural network, the new energy control mode historical data set and the meteorological index historical data set are used as input data and input into the neural network, and the power storage historical data set is used as supervision data. Through the training process, the neural network can learn the complex relationship between the input data new energy control mode, meteorological index and power storage change, thereby configuring a power storage predictor. The power storage predictor can predict the power storage in a certain period of time in the future based on the current control mode and meteorological conditions.

[0031] In order to further improve the accuracy of the prediction of the power storage predictor, the power storage historical data set and the power generation historical data set are used for conversion rate identification, and the power utilization rate is calculated, that is, the proportion of the electric energy stored in the energy storage device that is effectively utilized. By calculating the power utilization rate, the efficiency of the energy storage device and the actual availability of the power generation can be reflected. Optionally, first ensure that the power storage historical data set and the power generation historical data set are aligned in time, that is, the power storage and power generation data at each time point are corresponding, and then for each time point (such as every hour, every day, etc.), calculate the ratio between the power generation at that time point and the change in power storage (the power storage at the end minus the power storage at the beginning). This ratio reflects the efficiency of the power stored in the energy storage device being converted into actual power generation during the time period, that is, the power utilization rate. Then, the power utilization rate is used as a weight factor to perform weighted adjustment on the output layer of the power storage predictor to obtain the final power generation predictor. The predictor is based on a neural network model and integrates multi-dimensional information such as new energy control mode, meteorological indicators, and power storage prediction after weighted adjustment of power utilization rate, ensuring the accuracy and reliability of the prediction results of the power storage predictor model.

[0032] Finally, the power generation predictor is used to automatically identify meteorological patterns and predict the power generation of distributed renewable energy in a specific time zone in the future based on the relevant meteorological indicators and historical operation data obtained in real time. The power generation predictor takes into account a variety of factors, including meteorological conditions, historical data of storage capacity, and power generation efficiency, to generate accurate power generation prediction results. After the prediction is completed, the prediction results are sent to the user end, so that the user can understand the future power generation situation in advance, thereby optimizing energy scheduling and management strategies, ensuring efficient, precise, and intelligent management of renewable energy meteorological data, and improving the efficiency and reliability of renewable energy utilization.

[0033] Further, a correlation analysis is performed on the new energy storage quantity record data set and the initial meteorological indicator characteristic value record data set to obtain a correlation degree set, including: the new energy storage quantity record data set has a new energy power station scale label and a new energy power station control mode label; according to the new energy power station scale label and the new energy power station control mode label, the new energy storage quantity record data set and the initial meteorological indicator characteristic value record data set are clustered to obtain a first group of new energy storage quantity record data sets and a first group of initial meteorological indicator characteristic value record data sets, a second group of new energy storage quantity record data sets and a second group of initial meteorological indicator characteristic value record data sets, until the Nth group of new energy storage quantity record data sets and the Nth group of initial meteorological indicator characteristic value record data sets; the first group of new energy storage quantity record data sets and the first group of initial meteorological indicator characteristic value record data sets, the second group of new energy storage quantity record data sets and the second group of initial meteorological indicator characteristic value record data sets are traversed, until the Nth group of new energy storage quantity record data sets and the Nth group of initial meteorological indicator characteristic value record data sets are subjected to correlation analysis to obtain the correlation degree set.

[0034] Specifically, the new energy power storage record data set contains two labels: the new energy power station scale label and the new energy power station control mode label. The new energy power station scale label refers to the scale parameter of the power station, with the maximum power generation per unit time as the measurement indicator. The new energy power station control mode label refers to the specific control parameters of the power station, such as the number of activated energy storage units. The new energy storage amount record data set and the initial meteorological indicator characteristic value record data set are clustered by using a clustering algorithm, such as K-means clustering, DBSCAN clustering, etc., through the new energy power station scale label and the new energy power station control mode label of the new energy storage amount record data set, and the new energy storage amount record data set and the initial meteorological indicator characteristic value record data set are divided into multiple groups, including a first group of new energy storage amount record data set and a first group of initial meteorological indicator characteristic value record data set, a second group of new energy storage amount record data set and a second group of initial meteorological indicator characteristic value record data set, until the Nth group of new energy storage amount record data set and the Nth group of initial meteorological indicator characteristic value record data set, each group of new energy storage amount record data set and initial meteorological indicator characteristic value record data set represents the power generation situation and corresponding meteorological conditions under different scales and control modes.

[0035] Next, these grouped data are traversed, and correlation analysis is performed on each group (the first group of new energy storage quantity record data set and the first group of initial meteorological indicator characteristic value record data set, the second group of new energy storage quantity record data set and the second group of initial meteorological indicator characteristic value record data set, until the Nth group of new energy storage quantity record data set and the Nth group of initial meteorological indicator characteristic value record data set). The correlation analysis is a process for evaluating the relationship between meteorological indicators and storage quantity. By traversing and analyzing these grouped data, the correlation between each meteorological indicator and storage quantity in each group is calculated. Finally, the analysis results of all groups will be summarized to form a correlation set, which reflects the degree of influence of different meteorological indicators on storage quantity under different power station scales and control modes. By clustering and correlation analysis of new energy power generation data of different scales and control modes, the relationship between meteorological indicators and storage quantity is refined, providing a more accurate data basis for subsequent power generation forecasts, and further improving the accuracy of the forecast.

[0036] Further, the first group of new energy storage quantity record data sets and the first group of initial meteorological indicator characteristic value record data sets, the second group of new energy storage quantity record data sets and the second group of initial meteorological indicator characteristic value record data sets are traversed until the Nth group of new energy storage quantity record data sets and the Nth group of initial meteorological indicator characteristic value record data sets are subjected to correlation analysis to obtain the correlation degree set, including: constructing a first benchmark sequence according to the first group of new energy storage quantity record data sets, and constructing a first comparison sequence according to the first group of initial meteorological indicator characteristic value record data sets; performing grey correlation analysis according to the first benchmark sequence and the first comparison sequence to obtain a first group of correlation degrees, wherein the first group of correlation degrees corresponds one-to-one to the initial meteorological indicator set; and performing grey correlation analysis according to the second group of new energy storage quantity record data sets. A source electricity storage quantity record data set is constructed, a second benchmark sequence is constructed, and a second comparison sequence is constructed according to the second group of initial meteorological indicator characteristic value record data sets; a grey correlation analysis is performed according to the second benchmark sequence and the second comparison sequence to obtain a second group of correlations, wherein the second group of correlations corresponds one-to-one with the initial meteorological indicator set; until an Nth benchmark sequence is constructed according to the Nth group of new energy storage quantity record data sets, and an Nth comparison sequence is constructed according to the Nth group of initial meteorological indicator characteristic value record data sets; a grey correlation analysis is performed according to the Nth benchmark sequence and the Nth comparison sequence to obtain an Nth group of correlations, wherein the Nth group of correlations corresponds one-to-one with the initial meteorological indicator set; and the mean values ​​of the N correlations of the initial meteorological indicator set are calculated to obtain the correlation set.

[0037] Specifically, before the correlation analysis, a corresponding benchmark sequence is first constructed for each group of new energy storage quantity record data sets. The benchmark sequence refers to the change in the new energy storage quantity during that period of time. At the same time, a comparison sequence is constructed for each group of corresponding initial meteorological indicator characteristic value record data sets. The comparison sequence contains the change in meteorological indicator values ​​corresponding to the benchmark sequence. For example, a first benchmark sequence is constructed based on the first group of new energy storage quantity record data sets. The first benchmark sequence represents the change in the new energy storage quantity during that period of time. At the same time, a first comparison sequence is constructed based on the first group of initial meteorological indicator characteristic value record data sets. The first comparison sequence contains the change in meteorological indicator values ​​corresponding to the first benchmark sequence, until the Nth benchmark sequence is constructed based on the Nth group of new energy storage quantity record data sets, and the Nth comparison sequence is constructed based on the Nth group of initial meteorological indicator characteristic value record data sets.

[0038] Next, the grey correlation analysis method is used to compare the reference sequence (representing the change in the amount of electricity stored) and the comparison sequence (representing the change in meteorological conditions) of each group. By calculating the correlation between the two, a set of correlation values ​​corresponding to the initial meteorological indicator set is obtained. These correlation values ​​reflect the degree of influence of different meteorological indicators on the change in the amount of electricity stored in new energy sources. For example, the first reference sequence and the first comparison sequence are subjected to grey correlation analysis. Grey correlation analysis is an analysis method used to evaluate the strength of the relationship between two sequences, which can reveal the dependency between variables when the data samples are small or incomplete. Through the grey correlation analysis, the first group of correlations is obtained. The correlation values ​​reflect the strength of the association between different meteorological indicators and the amount of electricity stored, and correspond one-to-one with the initial meteorological indicator set. This step is repeated until the Nth group. The Nth reference sequence and the Nth comparison sequence are subjected to grey correlation analysis, and finally the Nth group of correlations is obtained. The Nth group of correlations corresponds one-to-one with the initial meteorological indicator set.

[0039] After the correlation analysis of all groups is completed, the correlation mean of each meteorological indicator in all N groups of data is calculated through statistical and averaging processing to form the correlation set, where the correlation mean of each meteorological indicator reflects its overall correlation with the storage capacity under various conditions. By performing grey correlation analysis on multiple data groups and calculating the mean of the correlation, the correlation between the initial meteorological indicators and the storage capacity of new energy can be comprehensively and accurately evaluated. The final obtained correlation set provides a scientific basis for the subsequent power generation forecast, ensuring that the prediction model can capture the most critical meteorological influencing factors and improve the accuracy and reliability of the forecast.

[0040] Further, the new energy control mode historical data set and the meteorological index historical data set are used as input data of the neural network, and the storage power historical data set is used as the supervision data to configure the storage power predictor, including: segmenting the new energy control mode historical data set, the meteorological index historical data set, and the storage power historical data set to obtain a first group of new energy control mode historical data sets, a first group of meteorological index historical data sets, and a first group of storage power historical data sets; using the first group of new energy control mode historical data sets and the first group of meteorological index historical data sets as input data of the neural network, and using the first group of storage power historical data sets as the supervision data; The method comprises the steps of: configuring a first power storage predictor according to the Mth group of new energy control modal historical data sets, an Mth group of meteorological indicator historical data sets and an Mth group of power storage historical data sets, configuring a first power storage predictor according to the Mth group of new energy control modal historical data sets and the Mth group of meteorological indicator historical data sets, and configuring the first power storage predictor according to the Mth group of new energy control modal historical data sets and the Mth group of meteorological indicator historical data sets as the input data of the neural network, and configuring the Mth power storage predictor according to the Mth group of power storage historical data sets as the supervision data; fusing the first power storage predictor until the mode value of the Mth power storage predictor is obtained, and generating the power storage predictor.

[0041] Specifically, the new energy control mode historical data set, the meteorological index historical data set and the power storage historical data set are first segmented by time windows or specific conditions to form multiple data sets, each of which contains data in a continuous time period, which are marked as the first group to the Mth group. The first group of new energy control mode historical data sets and the first group of meteorological index historical data sets obtained by segmentation are used as input data of the neural network, and the first group of power storage historical data sets are used as supervision data. Based on this, a first power storage predictor is configured, and the first power storage predictor can predict future power storage based on given control modes and meteorological conditions. Similarly, the above process is repeated until the Mth group, and a power storage predictor is independently trained for each group of data. The multi-model strategy can capture the diversity and non-stationarity that may exist in the data set, thereby improving the robustness of the prediction system. Finally, the fusion technology is used to integrate the prediction results of the first to the Mth power storage predictor, and the final power storage predictor is generated by calculating the mode value (i.e. the prediction value with the highest frequency), which effectively improves the accuracy and generalization ability of power storage prediction and ensures the accuracy and reliability of the prediction results, thereby optimizing the scheduling and management strategies of new energy and ensuring efficient, precise and intelligent management of new energy meteorological data.

[0042] Furthermore, conversion rate identification is performed based on the power storage historical data set and the power generation historical data set to obtain power utilization, including: calculating the ratio of the power generation historical data set to the power storage historical data set to obtain an initial power utilization set; performing a central trend analysis on the initial power utilization set to obtain the power utilization.

[0043] Furthermore, performing a central tendency analysis on the initial power utilization rate set to obtain the power utilization rate includes: the central tendency analysis is a process of obtaining the mode, median or mean.

[0044] Specifically, first, the proportion of the power generation history data set and the power storage history data set is calculated to quantify the proportion of the total power generation in each time period that is effectively stored (i.e., power storage), directly reflecting the efficiency of the power system in the energy storage link, and obtaining the initial power utilization rate set. Then, in order to grasp the stability of the power utilization rate as a whole, the initial power utilization rate set is subjected to a central trend analysis. Central trend analysis is a statistical method used to describe the degree to which each value in the data set approaches a central value. Common methods include obtaining the mode, median, or mean. The mode represents the value that appears most frequently in the data, which can reflect the multitude of the data; the median is the number in the middle after the data is sorted, representing the central position of the data; the mean is the arithmetic mean of all the data, which can reflect the average level of the data. Based on this, in practice, according to the characteristics of the data and the analysis requirements, the central trend of the power utilization rate can be analyzed by calculating the mode (the utilization value with the highest frequency), the median (the middle value that divides the data set into two), or the mean (the average value of all utilization values), so as to obtain a representative power utilization value. By calculating the electricity utilization rate, we can better understand the energy conversion efficiency under various operating conditions, provide a key reference for subsequent power generation forecasts, and improve the overall efficiency of energy utilization.

[0045] Embodiment 2, based on the same inventive concept as a distributed new energy meteorological data management method in the above embodiment, Figure 2 As shown, the present application provides a distributed new energy meteorological data management system, wherein the system includes:

[0046] A management request receiving module 11, the management request receiving module 11 is used to receive a new energy meteorological data management request through a user terminal, wherein the new energy meteorological data management request includes a distributed new energy type and a distributed new energy deployment location; an associated meteorological indicator determination module 12, the associated meteorological indicator determination module 12 is used to determine associated meteorological indicators according to the distributed new energy type; a meteorological monitoring information acquisition module 13, the meteorological monitoring information acquisition module 13 is used to obtain future time zone meteorological monitoring information of the distributed new energy deployment location according to the associated meteorological indicators by a communication intelligent collection terminal; a power generation prediction module 14, the power generation prediction module 14 is used to predict the future time zone power generation of distributed new energy according to a power generation predictor, and send it to the user terminal.

[0047] Furthermore, the associated meteorological indicator determination module 12 is used to perform the following steps: obtain an initial meteorological indicator set; collect a new energy storage quantity record data set and an initial meteorological indicator characteristic value record data set based on the initial meteorological indicator set and the distributed new energy type as constraints; perform correlation analysis based on the new energy storage quantity record data set and the initial meteorological indicator characteristic value record data set to obtain a correlation degree set, wherein the initial meteorological indicator set corresponds one-to-one to the correlation degree set; and according to the correlation degree set, select the associated meteorological indicators that are greater than or equal to the correlation degree threshold from the initial meteorological indicator set.

[0048] Furthermore, the associated meteorological indicator determination module 12 is also used to perform the following steps: the new energy storage quantity record data set has a new energy power station scale label and a new energy power station control mode label; according to the new energy power station scale label and the new energy power station control mode label, the new energy storage quantity record data set and the initial meteorological indicator characteristic value record data set are clustered to obtain a first group of new energy storage quantity record data sets and a first group of initial meteorological indicator characteristic value record data sets, a second group of new energy storage quantity record data sets and a second group of initial meteorological indicator characteristic value record data sets, until the Nth group of new energy storage quantity record data sets and the Nth group of initial meteorological indicator characteristic value record data sets; traverse the first group of new energy storage quantity record data sets and the first group of initial meteorological indicator characteristic value record data sets, the second group of new energy storage quantity record data sets and the second group of initial meteorological indicator characteristic value record data sets, until the Nth group of new energy storage quantity record data sets and the Nth group of initial meteorological indicator characteristic value record data sets are performed for correlation analysis to obtain the correlation degree set.

[0049] Furthermore, the associated meteorological indicator determination module 12 is further configured to perform the following steps: construct a first reference sequence based on the first set of new energy storage quantity record data sets, and construct a first comparison sequence based on the first set of initial meteorological indicator characteristic value record data sets; perform grey correlation analysis based on the first reference sequence and the first comparison sequence to obtain a first group of correlations, wherein the first group of correlations corresponds one-to-one to the initial meteorological indicator set; construct a second reference sequence based on the second set of new energy storage quantity record data sets, and construct a second comparison sequence based on the second set of initial meteorological indicator characteristic value record data sets; and perform grey correlation analysis based on the first reference sequence and the first comparison sequence to obtain a first group of correlations, wherein the first group of correlations corresponds one-to-one to the initial meteorological indicator set. The benchmark sequence and the second comparison sequence are subjected to grey correlation analysis to obtain a second group of correlations, wherein the second group of correlations corresponds one-to-one to the initial meteorological indicator set; until an Nth benchmark sequence is constructed according to the Nth group of new energy storage power record data sets, and an Nth comparison sequence is constructed according to the Nth group of initial meteorological indicator characteristic value record data sets; a grey correlation analysis is performed according to the Nth benchmark sequence and the Nth comparison sequence to obtain an Nth group of correlations, wherein the Nth group of correlations corresponds one-to-one to the initial meteorological indicator set; and the mean values ​​of N correlations of the initial meteorological indicator set are calculated to obtain the correlation set.

[0050] Furthermore, the power generation prediction module 14 is used to perform the following steps: obtain historical operation data of distributed new energy, wherein the historical operation data includes a new energy control mode historical data set, a meteorological indicator historical data set, a storage capacity historical data set and a power generation historical data set; use the new energy control mode historical data set and the meteorological indicator historical data set as input data of the neural network, and use the storage capacity historical data set as supervision data to configure a storage capacity predictor; perform conversion rate identification based on the storage capacity historical data set and the power generation historical data set to obtain power utilization; weight the output layer of the storage capacity predictor according to the power utilization to obtain the power generation predictor.

[0051] Furthermore, the power generation prediction module 14 is also used to perform the following steps: segmenting the new energy control modal historical data set, the meteorological indicator historical data set, and the power storage historical data set to obtain a first group of new energy control modal historical data sets, a first group of meteorological indicator historical data sets, and a first group of power storage historical data sets, using the first group of new energy control modal historical data sets and the first group of meteorological indicator historical data sets as input data of the neural network, using the first group of power storage historical data sets as supervision data, and configuring a first power storage predictor; until the new energy control modal historical data set, the meteorological indicator historical data set, and the power storage historical data set are segmented to obtain the Mth group of new energy control modal historical data sets, the Mth group of meteorological indicator historical data sets, and the Mth group of power storage historical data sets, using the Mth group of new energy control modal historical data sets and the Mth group of meteorological indicator historical data sets as input data of the neural network, using the Mth group of power storage historical data sets as supervision data, and configuring the Mth power storage predictor; fusing the first power storage predictor until the mode value of the Mth power storage predictor is reached to generate the power storage predictor.

[0052] Furthermore, the power generation prediction module 14 is also used to perform the following steps: calculate the ratio of the power generation historical data set to the power storage historical data set to obtain an initial power utilization rate set; perform a central trend analysis on the initial power utilization rate set to obtain the power utilization rate.

[0053] Furthermore, the power generation prediction module 14 is also used to perform the following steps: the central tendency analysis is a process of obtaining the mode, median or mean.

[0054] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0055] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A distributed new energy meteorological data management method, characterized in that: include: Receiving, through a user terminal, a new energy meteorological data management request, wherein the new energy meteorological data management request includes a distributed new energy type and a distributed new energy deployment location; Determining associated meteorological indicators according to the type of distributed renewable energy; According to the associated meteorological indicators, the communication intelligent collection terminal obtains the future time zone meteorological monitoring information of the distributed new energy deployment location; The future time zone power generation of distributed renewable energy is predicted based on the power generation predictor and sent to the user end.

2. The method according to claim 1, characterized in that According to the type of distributed renewable energy, the associated meteorological indicators are determined, including: Obtain an initial set of meteorological indicators; Taking the initial meteorological indicator set and the distributed new energy type as constraints, collecting a new energy storage quantity record data set and an initial meteorological indicator characteristic value record data set; Performing a correlation analysis on the new energy storage quantity record data set and the initial meteorological index characteristic value record data set to obtain a correlation degree set, wherein the initial meteorological index set corresponds to the correlation degree set one by one; According to the correlation degree set, the associated meteorological indicators greater than or equal to a correlation degree threshold are sorted from the initial meteorological indicator set.

3. The method according to claim 2, characterized in that A correlation analysis is performed based on the new energy storage quantity record data set and the initial meteorological indicator characteristic value record data set to obtain a correlation degree set, including: The new energy storage quantity record data set has a new energy power station scale label and a new energy power station control mode label; Clustering the new energy storage quantity record data set and the initial meteorological indicator characteristic value record data set according to the new energy power station scale label and the new energy power station control mode label to obtain a first group of new energy storage quantity record data set and a first group of initial meteorological indicator characteristic value record data set, a second group of new energy storage quantity record data set and a second group of initial meteorological indicator characteristic value record data set, until an Nth group of new energy storage quantity record data set and an Nth group of initial meteorological indicator characteristic value record data set; The first group of new energy storage quantity record data sets and the first group of initial meteorological indicator characteristic value record data sets, the second group of new energy storage quantity record data sets and the second group of initial meteorological indicator characteristic value record data sets are traversed until the Nth group of new energy storage quantity record data sets and the Nth group of initial meteorological indicator characteristic value record data sets are subjected to correlation analysis to obtain the correlation degree set.

4. The method according to claim 3, characterized in that Traversing the first group of new energy storage quantity record data sets and the first group of initial meteorological indicator characteristic value record data sets, the second group of new energy storage quantity record data sets and the second group of initial meteorological indicator characteristic value record data sets, until the Nth group of new energy storage quantity record data sets and the Nth group of initial meteorological indicator characteristic value record data sets perform correlation analysis to obtain the correlation degree set, including: Constructing a first reference sequence based on the first set of new energy storage quantity record data sets, and constructing a first comparison sequence based on the first set of initial meteorological indicator characteristic value record data sets; Performing grey correlation analysis on the first reference sequence and the first comparison sequence to obtain a first group of correlations, wherein the first group of correlations corresponds one-to-one to the initial meteorological indicator set; constructing a second reference sequence according to the second set of new energy storage quantity record data sets, and constructing a second comparison sequence according to the second set of initial meteorological indicator characteristic value record data sets; Performing grey correlation analysis on the second reference sequence and the second comparison sequence to obtain a second group of correlations, wherein the second group of correlations corresponds one-to-one to the initial meteorological indicator set; Until an Nth reference sequence is constructed according to the Nth set of new energy storage quantity record data sets, and an Nth comparison sequence is constructed according to the Nth set of initial meteorological indicator characteristic value record data sets; Performing a grey correlation analysis on the Nth reference sequence and the Nth comparison sequence to obtain an Nth group of correlations, wherein the Nth group of correlations corresponds one-to-one to the initial meteorological indicator set; Calculate N correlation degree means of the initial meteorological indicator set to obtain the correlation degree set.

5. The method according to claim 1, characterized in that The future time zone power generation of distributed renewable energy is predicted based on the power generation forecaster, which previously included: Obtaining historical operation data of distributed renewable energy, wherein the historical operation data includes a renewable energy control mode historical data set, a meteorological index historical data set, a storage capacity historical data set, and a power generation capacity historical data set; The new energy control mode historical data set and the meteorological index historical data set are used as input data of the neural network, and the power storage historical data set is used as supervision data to configure a power storage predictor; Performing conversion rate identification according to the power storage historical data set and the power generation historical data set to obtain power utilization rate; The output layer of the power storage predictor is weighted according to the power utilization rate to obtain the power generation predictor.

6. The method according to claim 5, characterized in that The new energy control mode historical data set and the meteorological index historical data set are used as input data of the neural network, and the storage power historical data set is used as supervision data to configure the storage power predictor, including: Segmenting the new energy control mode historical data set, the meteorological index historical data set, and the power storage historical data set to obtain a first group of new energy control mode historical data sets, a first group of meteorological index historical data sets, and a first group of power storage historical data sets, using the first group of new energy control mode historical data sets and the first group of meteorological index historical data sets as input data of a neural network, using the first group of power storage historical data sets as supervision data, and configuring a first power storage predictor; Until the new energy control mode historical data set, the meteorological index historical data set, and the power storage historical data set are segmented to obtain the Mth group of new energy control mode historical data set, the Mth group of meteorological index historical data set, and the Mth group of power storage historical data set, and the Mth group of new energy control mode historical data set and the Mth group of meteorological index historical data set are used as input data of the neural network, and the Mth group of power storage historical data set is used as supervision data to configure the Mth power storage predictor; The first power storage amount predictor is integrated until the mode value of the Mth power storage amount predictor is generated.

7. The method according to claim 5, characterized in that The conversion rate is marked according to the power storage historical data set and the power generation historical data set to obtain the power utilization rate, including: Calculating the ratio of the power generation historical data set to the power storage historical data set to obtain an initial power utilization rate set; A central trend analysis is performed on the initial power utilization rate set to obtain the power utilization rate.

8. The method according to claim 7, characterized in that Performing a central tendency analysis on the initial power utilization rate set to obtain the power utilization rate includes: the central tendency analysis is a process of obtaining the mode, median or mean.

9. A distributed new energy meteorological data management system, characterized in that: The steps for implementing the method according to any one of claims 1 to 8 include: A management request receiving module, the management request receiving module is used to receive a new energy meteorological data management request through a user terminal, wherein the new energy meteorological data management request includes a distributed new energy type and a distributed new energy deployment location; An associated meteorological index determination module, the associated meteorological index determination module is used to determine an associated meteorological index according to the type of distributed new energy; A meteorological monitoring information acquisition module, which is used to obtain the future time zone meteorological monitoring information of the distributed new energy deployment location through the communication intelligent collection terminal according to the associated meteorological indicators; The power generation prediction module is used to predict the future time zone power generation of distributed renewable energy according to the power generation predictor and send it to the user end.

Images