Intelligent regulation method based on distributed new energy power station

Abstract

The present application relates to the field of new energy technology, in particular to a kind of wisdom regulation and control method based on distributed new energy power station.The method comprises: obtaining the target quantity characteristic value of environmental data type at future monitoring time, and obtaining the data window of environmental data type at future monitoring time according to the target quantity characteristic value of environmental data type at future monitoring time, input the data window into the prediction model of environmental data type and output the predicted environmental data of environmental data type at future monitoring time;According to the predicted environmental data of different environmental data types and the power generation prediction model, the predicted power generation of distributed new energy power station is obtained, and the distributed new energy power station is regulated and controlled according to the predicted power generation.The present application can improve the accuracy of predicting the power generation of distributed new energy power station, so as to ensure the effect of regulating and controlling the power output to power grid by distributed new energy power station subsequently.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to an intelligent control method based on a distributed new energy power station. Background Art

[0002] Since the dispatching and control of distributed new energy power stations is crucial to improving the stability of power grid operation, enhancing the efficiency of new energy consumption, optimizing energy utilization efficiency, and reducing operating costs, it is currently crucial to dispatch and control distributed new energy power stations. In other words, it is currently crucial to regulate distributed new energy power stations.

[0003] In the existing technology, the environmental data of the location of the distributed new energy power station is usually predicted first, and then the power generation of the distributed new energy power station at future times is predicted based on the predicted environmental data, and the power output of the distributed new energy power station to the power grid is regulated based on the predicted power generation of the distributed new energy power station; however, when predicting environmental data, historical environmental data of a fixed length or historical environmental data of a random length is generally selected to predict the future environment of the location of the distributed new energy power station as input for prediction, but when using historical environmental data of a fixed length or historical environmental data of a random length as input for predicting environmental data, the impact of environmental changes on the prediction of future environmental data will be ignored, that is, using historical environmental data of a fixed length or historical environmental data of a random length as input for prediction When predicting future environmental data, the model for predicting environmental data will have a weak response capability to environmental changes or a weak ability to capture environmental changes, which will lead to unreliable and inaccurate environmental predictions when predicting the future environment of the location of the distributed new energy power station. The unreliable and inaccurate environmental predictions will lead to unreliable and inaccurate predictions when predicting the power generation of the distributed new energy power station based on the predicted environmental data. When the power generation of the distributed new energy power station is predicted inaccurately, the subsequent regulation of the electric energy output by the distributed new energy power station to the power grid will be poor. Therefore, how to improve the accuracy of predicting the power generation of the distributed new energy power station to ensure the effect of subsequent regulation of the electric energy output by the distributed new energy power station to the power grid has become an urgent problem to be solved. Summary of the Invention

[0004] In order to solve the above problems, the present invention provides an intelligent control method based on a distributed new energy power station. The technical solutions adopted are as follows:

[0005] An embodiment of the present invention provides a smart control method based on a distributed new energy power station, comprising the following steps:

[0006] Obtaining environmental data sequences corresponding to different environmental data types at the current monitoring moment, where the data in the environmental data sequences are environmental data collected at the location of the distributed new energy power station;

[0007] For any environmental data type, a seasonal component curve and a residual component curve of the environmental data sequence corresponding to the environmental data type are obtained, and based on the extreme value points on the seasonal component curve, an extreme value moment combination corresponding to the environmental data type at the current monitoring moment is obtained, and based on the difference between two extreme value moments in the extreme value moment combination and the position of the horizontal coordinate on the residual component curve belonging to the extreme value moment, a target quantity characteristic value of the environmental data type at the future monitoring moment is obtained, and based on the target quantity characteristic value of the environmental data type at the future monitoring moment, a data window of the environmental data type at the future monitoring moment is obtained, and the data window is input into a prediction model of the environmental data type to output predicted environmental data of the environmental data type at the future monitoring moment;

[0008] The predicted power generation of the distributed new energy power station is obtained based on the predicted environmental data of different environmental data types and the power generation prediction model, and the distributed new energy power station is regulated according to the predicted power generation.

[0009] Beneficial effects: The present invention first obtains an environmental data sequence corresponding to different environmental data types at the current monitoring moment; then obtains the extreme point on the seasonal component curve of the environmental data sequence to obtain the extreme moment combination corresponding to the environmental data type at the current monitoring moment; according to the difference between the two extreme moments in the extreme moment combination and the position of the horizontal coordinate on the residual component curve of the environmental data sequence belonging to the extreme moment, obtains the target quantity characteristic value of the environmental data type at the future monitoring moment; and according to the target quantity characteristic value of the environmental data type at the future monitoring moment, obtains the data window of the environmental data type at the future monitoring moment; inputs the data window into the prediction model of the environmental data type to output the predicted environmental data of the environmental data type at the future monitoring moment; obtains the predicted power generation of the distributed new energy power station according to the predicted environmental data of different environmental data types and the power generation prediction model, and regulates the distributed new energy power station according to the predicted power generation. Moreover, the present invention can improve the accuracy of predicting the power generation of the distributed new energy power station by adaptively obtaining the data window, thereby ensuring the effect of subsequently regulating the electric energy output by the distributed new energy power station to the power grid, thereby avoiding the phenomenon of damage to the power grid operation stability and economic and market losses as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 paying any creative work.

[0011] Figure 1 This is a flow chart of an intelligent control method based on a distributed new energy power station according to the present invention. DETAILED DESCRIPTION

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field fall within the scope of protection of the embodiments of the present invention.

[0013] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0014] This embodiment provides a smart control method based on a distributed new energy power station, which is described in detail as follows:

[0015] like Figure 1 As shown, the intelligent control method based on the distributed new energy power station includes the following steps:

[0016] Step S001 obtains the environmental data sequences corresponding to different environmental data types at the current monitoring moment.

[0017] This embodiment improves the accuracy of prediction of the power generation of the distributed new energy power station by improving the accuracy of prediction of the environmental data at the location of the distributed new energy power station, thereby ensuring the effect of subsequent regulation of the electric energy output by the distributed new energy power station to the power grid; in addition, for the convenience of analysis, this embodiment will subsequently analyze and describe the process of regulating the electric energy output by any distributed new energy power station connected to the power grid.

[0018] First, obtain the location of the distributed new energy power station and record it as the monitoring location, obtain all environmental data types related to the power generation of the distributed new energy power station, and record the set constructed by all environmental data types related to the power generation of the distributed new energy power station as the environmental data type set corresponding to the distributed new energy power station. If the change of a certain type of environmental data will affect the power generation of the distributed new energy power station, it means that the corresponding environmental data type is the environmental data type related to the power generation of the distributed new energy power station. For example, for photovoltaic distributed new energy power stations, an increase in light intensity usually increases photovoltaic power generation. Although temperature increase is accompanied by strong light, excessive temperature will reduce the conversion efficiency of component power generation, thereby inhibiting power generation. Rising humidity will cause clouds or turbid air, reducing solar radiation reaching the surface of the component, thereby reducing power generation. Therefore, light intensity, ambient temperature, and ambient humidity are all environmental data related to the power generation of distributed new energy power stations. Data type, then the environmental data type set includes light intensity, ambient temperature, and ambient humidity; then at the current monitoring moment, the environmental data sequence corresponding to each environmental data type in the environmental data type set is obtained; and at the current monitoring moment, the specific acquisition process of the environmental data sequence corresponding to any environmental data type is: first, the moment when the environmental data belonging to the environmental data type is collected at the monitoring position is obtained, and recorded as the starting monitoring moment of the environmental data type, and then the time series sequence consisting of all environmental data belonging to the environmental data type collected by the environmental data collection device within the time period from the starting monitoring moment of the environmental data type to the current monitoring moment is recorded as the environmental data sequence corresponding to the environmental data type at the current monitoring moment, and the environmental data sequence corresponding to the environmental data type at the current monitoring moment includes the environmental data belonging to the environmental data type collected at the current monitoring moment.

[0019] In this embodiment, the environmental data collected or predicted are mainly meteorological data, and all environmental data types in the above-mentioned environmental data type set are collected synchronously, that is, the type and number of types of environmental data collected at any time are consistent with the data type and number of types in the environmental data type set; in addition, in specific applications, implementers usually set the time interval between adjacent collection moments based on the scale of the power station, hardware conditions and grid connection protocol, such as the time interval between adjacent monitoring moments can be set to between 5 minutes and 1 hour; and it should also be noted that monitoring equipment is generally used to monitor and collect environmental data at the location of distributed new energy power stations, such as using temperature and humidity sensors to monitor and collect the ambient temperature, ambient humidity, etc. at the location of distributed new energy power stations.

[0020] Therefore, this embodiment obtains the environmental data sequence corresponding to different environmental data types at the current monitoring moment through the above process, and the data in the environmental data sequence are all actual data collected. The main reason why environmental factors affect the power generation of distributed power stations is that distributed power stations need to convert external energy into electrical energy during the power generation process.

[0021] Step S002: for any environmental data type, obtain the seasonal component curve and the residual component curve of the environmental data sequence corresponding to the environmental data type, and obtain the extreme value moment combination corresponding to the environmental data type at the current monitoring moment based on the extreme value points on the seasonal component curve; obtain the target quantity characteristic value of the environmental data type at the future monitoring moment based on the difference between the two extreme value moments in the extreme value moment combination and the position of the horizontal coordinate on the residual component curve belonging to the extreme value moment; obtain the data window of the environmental data type at the future monitoring moment based on the target quantity characteristic value of the environmental data type at the future monitoring moment, input the data window into the prediction model of the environmental data type to output the predicted environmental data of the environmental data type at the future monitoring moment.

[0022] Currently, when regulating and controlling distributed new energy power stations, the power generation of the distributed new energy power stations is usually predicted through the predicted environmental data of the location of the distributed new energy power stations, and then the power transmission of the distributed new energy power stations to the power grid is regulated based on the predicted results; however, when predicting the environmental data of the location of the distributed new energy power station, historical environmental data of a fixed length or historical environmental data of a random length are generally selected to realize the prediction of future environmental data at the monitoring location. However, this process of predicting future environmental data with historical environmental data of a fixed length or historical environmental data of a random length will not only ignore the impact of environmental change characteristics on future environmental predictions, but will also be easily interfered by early invalid data, resulting in prediction lag or increased error. That is, when predicting future environmental data with historical environmental data of a fixed length or historical environmental data of a random length as input during prediction, the model for predicting environmental data will have a weak ability to respond to environmental changes, the model for predicting environmental data will have a weak ability to capture environmental changes, and the prediction results of the model for predicting environmental data will be more likely to be interfered with by early invalid data, which will lead to the prediction of the future environment at the location of the distributed new energy power station. When the environmental data at the monitoring location is predicted at a certain moment, the problem of unreliable and inaccurate environmental prediction occurs. For example, if the environmental data at the monitoring location is predicted at a certain moment, and the environmental data close to the moment is more volatile than the historical environmental data farther away from the moment, that is, the environment at the monitoring location at the moment has a high fluctuation trend, then if the environmental data at the monitoring location is predicted at the moment, the long historical environmental data is still selected as the input of the prediction model, which will result in the inability to capture the changing characteristics of the environment at the monitoring location at the moment, and thus it will be difficult to capture the sudden environmental changes when predicting the power generation. The immediate impact of changes on power generation will lead to unreliable and inaccurate predictions when the power generation of distributed renewable energy power stations is predicted based on the predicted environmental data. When the power generation of distributed renewable energy power stations is predicted inaccurately, the subsequent regulation of the power output of distributed renewable energy power stations to the power grid will be less effective. When the regulation of the power output of distributed renewable energy power stations to the power grid is less effective, it will cause a series of consequences such as damage to the stability of power grid operation and economic and market losses. That is, the inaccurate power generation prediction will affect the stability of the power grid, economic benefits, etc.

[0023] In order to ensure the effect of regulating the electric energy output by the distributed new energy power station to the power grid, this embodiment needs to improve the prediction accuracy and reliability of the power generation of the distributed new energy power station. The prediction accuracy and prediction reliability of the power generation of the distributed new energy power station are related to the prediction reliability and accuracy of the environmental data at the monitoring location. Therefore, this embodiment will improve the prediction accuracy of the power generation of the distributed new energy power station by improving the prediction reliability and accuracy of the environmental data at the monitoring location. In addition, this embodiment mainly analyzes the characteristics of the environmental data close to the prediction time to adaptively determine the length of the historical data obtained for prediction, thereby improving the prediction accuracy of the power generation of the distributed new energy power station. That is to say, this embodiment improves the response ability of the prediction model used for environmental data prediction to environmental changes, the ability to capture environmental changes, and the ability to capture the periodic change characteristics of data by adaptively regulating the data window used for prediction, thereby improving the prediction reliability and accuracy of the environmental data at the monitoring location.

[0024] Based on the above analysis, it can be seen that before obtaining the predicted environmental data, this embodiment needs to adaptively obtain the data window for environmental data prediction, that is, the data window at the future monitoring moment. The data window at the future monitoring moment is mainly used to predict the environmental data at the monitoring location at the future monitoring moment. Since the types of environmental data that affect the power generation of the distributed new energy power station are diverse, and different types of environmental data will also have different characteristics at the same moment, the size of the data window used when predicting environmental data belonging to different environmental data types will also be different. Therefore, this embodiment needs to obtain the data window of each environmental data type at the future monitoring moment. In addition, since the method for obtaining the data window of all environmental data types at any monitoring moment is the same, this embodiment will be described as an example for the convenience of understanding and analysis. The future monitoring moment in this embodiment mainly refers to the next monitoring moment of the current monitoring moment. Then the specific acquisition process of the data window of the environmental data type W at the future monitoring moment is:

[0025] First, the environmental data sequence corresponding to the environmental data type W at the current monitoring moment is subjected to STL decomposition to obtain the seasonal components and residual components of each environmental data in the environmental data sequence corresponding to the environmental data type W at the previous monitoring moment. Then, the seasonal mapping space and residual mapping space corresponding to the environmental data type W are constructed. Afterwards, the seasonal components of all environmental data in the environmental data sequence corresponding to the environmental data type W at the current monitoring moment and the collection time of the corresponding environmental data are mapped to the seasonal mapping space to obtain the seasonal component data points in the seasonal mapping space. All seasonal component data points in the seasonal mapping space are connected in sequence according to the chronological order, and the connected curve is recorded as the environmental data sequence corresponding to the environmental data type W at the current monitoring moment. Seasonal component curve, the residual components of all environmental data in the environmental data sequence corresponding to the environmental data type W at the current monitoring moment and the collection time of the corresponding environmental data are mapped to the residual mapping space to obtain the residual component data points in the residual mapping space, and all residual component data points in the residual mapping space are connected in sequence according to the chronological order, and the connected curve is recorded as the residual component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment, that is, the horizontal axis of the seasonal mapping space corresponding to the environmental data type W is time, and the vertical axis is seasonal component, the horizontal axis of the residual mapping space is time, and the vertical axis is residual component, and the process of STL decomposition of the data is a well-known technology, so it will not be described in detail. After obtaining the residual component curve and the seasonal component curve, the extreme point on the seasonal component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment is obtained. The extreme point is obtained by using the derivation method, and according to the extreme point on the seasonal component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment, the extreme moment combination corresponding to the environmental data type W at the current monitoring moment is obtained, and then according to the difference between the two extreme moments in the extreme moment combination corresponding to the environmental data type W at the current monitoring moment and the position of the horizontal coordinate belonging to the extreme moment on the residual component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment, the target quantity characteristic value of the environmental data type W at the future monitoring moment is obtained, and according to the target quantity characteristic value of the environmental data type W at the future monitoring moment, the data window of the environmental data type W at the future monitoring moment is obtained. The target quantity characteristic value of the environmental data type W at the future monitoring moment is positively correlated with the data window of the environmental data type W at the future monitoring moment, so the target quantity characteristic value can be used as the basis for determining the data window.

[0026] In this embodiment, according to the extreme value points on the seasonal component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment, the specific process of obtaining the extreme value moment combination corresponding to the environmental data type W at the current monitoring moment is: first, the horizontal coordinate values ​​of all the extreme value points on the seasonal component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment are sorted in chronological order, and the sorted sequence is recorded as the extreme value moment sequence, and the extreme value points include maximum value points and minimum value points, and if a certain extreme value moment in the extreme value moment sequence is the horizontal coordinate value of a certain extreme value point on the seasonal component curve, and the extreme value point is based on the current monitoring moment. The seasonal component of a certain environmental data in the environmental data sequence corresponding to the environmental data type W and the collection time of the environmental data are mapped, then the value of the extreme moment is the collection time of the environmental data; then any two adjacent extreme moments in the extreme moment sequence are constructed into a combination, and the combinations constructed by all two adjacent extreme moments in the extreme moment sequence are recorded as the extreme moment combinations corresponding to the environmental data type W at the current monitoring moment, and the number of extreme moment combinations corresponding to the environmental data type W at the current monitoring moment is the number of extreme moments in the extreme moment sequence minus 1, and the construction of the extreme moment combination is for subsequent analysis of data features.

[0027] In this embodiment, according to the difference between the two extreme moments in the extreme moment combination corresponding to the environmental data type W at the current monitoring moment and the position of the extreme moment on the residual component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment, the specific process of obtaining the target quantity characteristic value of the environmental data type W at the future monitoring moment is as follows: first, according to the time interval between the two extreme moments in the extreme moment combination closest to the current monitoring moment in time and the time interval between the two extreme moments in any extreme moment combination, the initial quantity characteristic value of the environmental data type W at the future monitoring moment is obtained; because unpredictable weather changes or sudden weather changes may occur, when such unpredictable weather changes or sudden weather changes occur, the data window length should be further reduced so that the prediction model for environmental data prediction pays more attention to local historical data. Therefore, in order to further improve the prediction accuracy of environmental data, this embodiment further needs to analyze the random fluctuation characterization value of the environmental data type W at the future monitoring moment, and further adjust the initial quantity characteristic value based on the obtained random fluctuation characterization value, that is, this embodiment first obtains the current monitoring moment on the residual component curve of the environmental data sequence corresponding to the environmental data type W at the current monitoring moment. The residual component curve segment corresponding to each extreme moment combination corresponding to the environmental data type W at the measuring moment, and the combination of the two endpoints of the residual component curve segment corresponding to the extreme moment combination is the corresponding extreme moment combination, that is, if the two extreme moments in a certain extreme moment combination are t1 and t2, then the residual component curve segment from the data point with the abscissa t1 to the data point with the abscissa t2 on the residual component curve is the residual component curve segment corresponding to the extreme moment combination; then, according to the mean of the absolute values ​​of all residual components on the residual component curve segment corresponding to each extreme moment combination corresponding to the environmental data type W at the current monitoring moment and the extreme moment The standard deviation of all residual components on the residual component curve segment corresponding to the combination of moments is obtained to obtain the random fluctuation characterization value of the environmental data type W at the future monitoring moment, and the larger the random fluctuation characterization value, the greater the degree of adjustment to the initial quantity characteristic value, that is, the larger the random fluctuation characterization value, the shorter the length of the data window obtained subsequently; finally, the result of multiplying the random fluctuation characterization value of the environmental data type W at the future monitoring moment by the preset first constant minus the initial quantity characteristic value of the environmental data type W at the future monitoring moment is obtained, and used as the target quantity characteristic value of the environmental data type W at the future monitoring moment, that is, the target quantity characteristic value of the environmental data type W at the future monitoring moment is ,in, is the initial quantity characteristic value of the environmental data type W at the future monitoring moment, C1 is the preset first constant, since The value range is 0 to 1, so in this embodiment, C1 is set to 1. It is the random fluctuation characterization value of the environmental data type W at the future monitoring moment.

[0028] In this embodiment, the specific process of obtaining the initial quantitative characteristic value of the environmental data type W at the future monitoring moment is as follows: first, obtain the time interval between the two extreme value moments in the extreme value moment combination, and record it as the distance value corresponding to the corresponding extreme value moment combination; obtain the middle moment of the time period formed by the two extreme value moments in the extreme value moment combination, and record it as the characterization moment of the corresponding extreme value moment combination, that is, if the two extreme value moments in a certain extreme value moment combination are t1 and t2 respectively, the middle moment between t1 and t2 is the characterization moment of the extreme value moment combination; then calculate the normalized value of the inverse of the time interval between the characterization moment of the extreme value moment combination and the current moment, and use it as the distance weight value of the corresponding extreme value moment combination; and if the inverse of the time interval between the characterization moment of the extreme value moment combination and the current moment is recorded as the initial weight of the corresponding extreme value moment combination, then the result of normalizing the initial weight of the extreme value moment combination is the sum of the initial weight of the corresponding extreme value moment combination and the current moment. The cumulative result of the initial weights of all extreme value moment combinations corresponding to the environmental data type W at the previous monitoring moment, that is, since in the subsequent calculation of the stability index value and the random fluctuation characterization value, the reference value of the extreme value moment combination closer to the current monitoring moment is greater, so the distance weight value of the extreme value moment combination closer to the current monitoring moment is greater; then, among all the extreme value moment combinations corresponding to the environmental data type W at the current monitoring moment, the extreme value moment combination closest to the current monitoring moment in time is obtained, and recorded as the nearest neighbor combination corresponding to the environmental data type W at the current monitoring moment; then the weighted difference value of the extreme value moment combination is obtained, and the weighted difference value corresponding to any extreme value moment combination is the result of multiplying the absolute value of the difference between the distance value corresponding to the extreme value moment combination and the distance value corresponding to the nearest neighbor combination by the distance weight value of the extreme value moment, that is, the weighted difference value corresponding to the sth extreme value moment combination corresponding to the environmental data type W at the current monitoring moment is , where T0 is the distance value corresponding to the nearest neighbor combination corresponding to the environmental data type W at the current monitoring moment, is the distance value corresponding to the sth extreme moment combination of the environmental data type W at the current monitoring moment, is the distance weight value of the sth extreme moment combination corresponding to the environmental data type W at the current monitoring moment; then the weighted difference values ​​of all extreme moment combinations corresponding to the environmental data type W at the current monitoring moment are obtained and accumulated to obtain the negative correlation mapping value of the result, and recorded as the stability index value corresponding to the environmental data type W at the current monitoring moment, that is, the stability index value corresponding to the environmental data type W at the current monitoring moment is , exp() is an exponential function with constant e as the base. And the smaller the stability index value corresponding to the environmental data type W at the current monitoring moment, that is, The larger the value, the higher the stability index value. The larger the stability index value is, the higher the stability index value is. The larger the stability index value is, the higher the stability index value is. The smaller it is, the higher the stability of the overall historical data is for the environmental data type W. Therefore, the data window length of the environmental data type W obtained at the future monitoring moment should be longer to improve the reference to historical data, thereby improving the accuracy of the prediction. Then, the mean of the distance values ​​corresponding to all extreme moment combinations of the environmental data type W at the current monitoring moment is obtained, and recorded as the periodic index value corresponding to the environmental data type W at the current monitoring moment. The environmental data has a certain periodicity of change. In order to more completely capture the periodic characteristics of the data during subsequent predictions and improve the accuracy of the prediction results, this embodiment should make the periodic change faster. The shorter the data window is, the slower the periodic change of the data window is, and when the mean of the distance values ​​corresponding to all extreme value moment combinations corresponding to the environmental data type W at the current monitoring moment is larger, it indicates that the change cycle of the environmental data belonging to the environmental data type W is slower, and when the mean of the distance values ​​corresponding to all extreme value moment combinations corresponding to the environmental data type W at the current monitoring moment is smaller, it indicates that the change cycle of the environmental data belonging to the environmental data type W is faster; finally, the product of the stability index value corresponding to the environmental data type W at the current monitoring moment and the periodic index value corresponding to the environmental data type W at the current monitoring moment is obtained, and recorded as the initial quantity characteristic value of the environmental data type W at the future monitoring moment.

[0029] Based on the above, it can be seen that when the initial quantity characteristic value is smaller, it indicates that the data closer to the future monitoring time is more unstable than the data farther away from the future monitoring time, which also indicates that the data change cycle of the environmental data type W at the monitoring location is faster. Therefore, when predicting the data belonging to the environmental data type W at the future monitoring time, only by focusing on the data closer to the future monitoring time can the recent change trend and periodic characteristics of the environmental data type W be captured more accurately. That is, only by focusing on the data closer to the future monitoring time can the prediction accuracy of the data belonging to the environmental data type W at the future monitoring time be improved, which also means that a shorter data window should be used at this time to better Capture the recent change characteristics of the environmental data type W at the monitoring location, or in other words, a shorter data window should be used to predict the data belonging to the environmental data type W at the future monitoring time; and when the initial quantity characteristic value is larger, it indicates that from the beginning of monitoring the environmental data type W to the current monitoring time, the overall change of the data belonging to the environmental data type W is relatively stable and the data change cycle is longer. Then, when predicting the data belonging to the environmental data type W at the future monitoring time, a longer data window should be used to ensure the prediction accuracy of the environmental data type W at the future monitoring time, and when the data change cycle is long, using a longer data window for prediction can more completely capture the data periodic characteristics, making the prediction result more accurate.

[0030] In this embodiment, the specific process of obtaining the random fluctuation characterization value of the environmental data type W at the future monitoring moment is as follows: first, obtain the mean of the absolute values ​​of all residual components on the residual item curve segment corresponding to the extreme value moment combination, and record it as the residual mean of the corresponding extreme value moment combination; obtain the standard deviation of all residual components on the residual item curve segment corresponding to the extreme value moment combination, and use it as the residual standard deviation of the corresponding extreme value moment combination, and the residual component on the residual item curve segment corresponding to the extreme value moment combination refers to the vertical coordinate value of the residual component data point on the residual item curve segment; then obtain the product of the standard deviation corresponding to the extreme value moment combination and the residual mean corresponding to the extreme value moment combination, and record it as the residual eigenvalue corresponding to the corresponding extreme value moment combination; then obtain the result of comparing the residual eigenvalue corresponding to the extreme value moment combination with the residual eigenvalue corresponding to the nearest neighbor combination, and then multiply the result by the distance weight value of the corresponding extreme value moment combination, and use it as the random eigenvalue of the corresponding extreme value moment combination, that is, the random eigenvalue of the sth extreme value moment combination corresponding to the environmental data type W at the current monitoring moment is ,in, is the residual standard deviation of the nearest neighbor combination corresponding to the environmental data type W at the current monitoring moment, F0 is the residual mean of the nearest neighbor combination corresponding to the environmental data type W at the current monitoring moment, is the residual standard deviation of the sth extreme moment combination corresponding to the environmental data type W at the current monitoring moment, It is the residual mean of the sth extreme moment combination corresponding to the environmental data type W at the current monitoring moment; finally, the normalized value of the cumulative sum of the random eigenvalues ​​of all extreme moment combinations corresponding to the environmental data type W at the current monitoring moment is used as the random fluctuation representation value of the environmental data type W at the current monitoring moment. At this time, the normalization function Norm() is used to normalize the cumulative sum of the random eigenvalues ​​of all extreme moment combinations corresponding to the environmental data type W at the current monitoring moment.

[0031] Moreover, when the random fluctuation characterization value of the environmental data type W at the future monitoring moment is larger, it indicates that there is a greater possibility of unpredictable weather changes or sudden weather changes within the local time range of the current monitoring moment, such as sandstorms, rain, etc., then when predicting the environmental number belonging to the environmental data type W at the next monitoring moment of the current monitoring moment, it is necessary to focus on using data closer to the future monitoring moment in order to more accurately capture this change, that is, only by focusing on using data closer to the future monitoring moment can the prediction accuracy of the data belonging to the environmental data type W at the future monitoring moment be improved, which also means that a shorter data window should be used at this time to better capture the recent change characteristics of the data belonging to the environmental data type W at the monitoring location, or in other words, a shorter data window should be used at this time to predict the future monitoring moment. The data belonging to the environmental data type W at the monitoring moment is predicted, so the greater the random fluctuation characterization value of the environmental data type W at the future monitoring moment, the greater the adjustment degree of the initial quantity characteristic value of the environmental data type W at the future monitoring moment; when the random fluctuation characterization value of the environmental data type W at the future monitoring moment is smaller, it indicates that the possibility of unpredictable weather changes or sudden weather changes within the local time range of the current monitoring moment is smaller, then at this time, in order to ensure the accuracy of the prediction, the degree of adjustment of the initial quantity characteristic value of the environmental data type W at the future monitoring moment should be smaller, that is, at this time, the target quantity characteristic value close to the initial quantity characteristic value can be used to obtain the data window; in this embodiment, the characteristics expressed by the extreme moment combination closest to the current monitoring moment can better reflect the recent changing trend of the environment.

[0032] In this embodiment, the specific process of obtaining the data window of the environmental data type W at the future monitoring moment according to the target quantity characteristic value of the environmental data type W at the future monitoring moment is as follows: first, a preset number of monitoring moments are selected as sample moments before the future monitoring moment, and the target quantity characteristic value of the environmental data type W at each sample moment is obtained. In this embodiment, the implementer can determine the value of the preset number according to the total number of monitoring moments before the future monitoring moment. For example, the preset number can be set to 70% of the total number of monitoring moments before the future monitoring moment in this embodiment, and when selecting the sample moment, it is selected according to the distance from the future monitoring moment, that is, the monitoring data closer to the future monitoring moment is selected first. In addition, the method for obtaining the target quantity characteristic value of the environmental data type W at the sample moment is the same as that of the future monitoring moment. The method for obtaining the target quantity characteristic value of the environmental data type W at the measuring moment is the same, so it will not be described in detail in this embodiment; then, based on the target quantity characteristic value of the environmental data type W at the sampling moment, the target intercept and target slope corresponding to the environmental data type W are obtained; then, based on the target intercept and target slope corresponding to the environmental data type W, a function is constructed, whose intercept is the target intercept corresponding to the environmental data type W, whose slope is the target slope corresponding to the environmental data type W, whose input is the target quantity characteristic value of the environmental data type W, and whose output is the data length of the environmental data type W, and is recorded as the data length function corresponding to the environmental data type W; then, based on the data length function corresponding to the environmental data type W and the target quantity characteristic value of the environmental data type W at the future monitoring moment, the data window of the environmental data type W at the future monitoring moment is obtained.

[0033] In this embodiment, the specific process of obtaining the data window of the environmental data type W at the future monitoring moment according to the data length function corresponding to the environmental data type W and the target quantity characteristic value of the environmental data type W at the future monitoring moment is as follows: inputting the target quantity characteristic value of the environmental data type W at the future monitoring moment into the data length function corresponding to the environmental data type W, and rounding up the output result of the data length function corresponding to the environmental data type W at this time as the data length of the environmental data type W at the future monitoring moment; then traversing from the current monitoring moment forward until the traversed environmental data belonging to the environmental data type W is equal to the data length of the environmental data type W at the future monitoring moment, and stopping the traversal, and recording the window composed of all the traversed environmental data belonging to the environmental data type W as the data window of the environmental data type W at the future monitoring moment, that is, if the current monitoring moment is the Zth monitoring moment and the data length of the environmental data type W at the future monitoring moment is L, then the data window composed of the environmental data belonging to the environmental data type W collected at all monitoring moments between the current monitoring moment and the ZLth monitoring moment is the data window of the environmental data type W at the future monitoring moment, including the data collected at the current monitoring moment and the ZLth monitoring moment.

[0034] In this embodiment, the specific process of obtaining the target intercept and target slope corresponding to the environmental data type W is as follows: first randomly select an intercept and a slope, and since the target quantity characteristic value obtained in this embodiment is positively correlated with the data length, the slope value in this embodiment is required to be a positive number, and the intercept value is a natural number, and then the combination constructed by the randomly selected intercept and slope is recorded as the parameter combination corresponding to the first iteration of the environmental data type W, and the preferred index value of the parameter combination corresponding to the first iteration of the environmental data type W is obtained, and then the parameter update method in the Yes optimization algorithm is used to update the intercept and slope in the parameter combination corresponding to the first iteration of the environmental data type W, and the updated result is recorded as the parameter combination corresponding to the second iteration of the environmental data type W, and the preferred index value of the parameter combination corresponding to the second iteration of the environmental data type W is continued to be obtained, and then the parameter update method in the Yes optimization algorithm is continued to be used to update the environmental data type W. The intercept and slope in the parameter combination corresponding to the second iteration under type W are updated, and the updated result is recorded as the parameter combination corresponding to the third iteration under the environmental data type W, and the preferred index value of the parameter combination corresponding to the third iteration under the environmental data type W is continued to be obtained, and so on, until the number of iterations reaches the preset number of iterations, and the parameter combination corresponding to each iteration under the environmental data type W and the preferred index value of the parameter combination corresponding to each iteration under the environmental data type W are statistically obtained, and then, among the parameter combinations corresponding to all iterations under the environmental data type W, the slope and intercept in the parameter combination corresponding to the largest preferred index value are selected as the target intercept and target slope corresponding to the environmental data type W; and since the process of parameter optimization using the Yes optimization algorithm is a well-known technology, this embodiment will not be described in detail; in addition, the number of iterations preset for the iteration stop condition needs to be set according to the size of the parameter value range, such as it can be set to 50 times.

[0035] In this embodiment, the specific process of the preferred index value of the parameter combination corresponding to the i-th iteration under the environmental data type W is: first, the slope and intercept in the parameter combination corresponding to the i-th iteration under the environmental data type W are recorded as the experimental slope and experimental intercept respectively, and the actual data at each sample moment and the predicted data at each sample moment under the parameter combination corresponding to the i-th iteration are obtained, and the actual data of any sample moment t at this time is the data with a collection time equal to the sample moment t in the environmental data sequence corresponding to the environmental data type W at the current monitoring moment, that is, the actual data of any sample moment t at this time is the environmental data belonging to the environmental data type W collected at the sample moment t; then, the mean square error is calculated based on the actual data of all sample moments and the predicted data of the sample moment t under the parameter combination corresponding to the i-th iteration, and recorded as the preferred index value of the parameter combination corresponding to the i-th iteration under the environmental data type W; that is, the preferred index value of the parameter combination corresponding to the i-th iteration under the environmental data type W is , where J is the number of sample moments, is the actual data at the jth sampling moment among all the sampling moments, and is also the environmental data belonging to the environmental data type W collected at the jth sampling moment, It is the predicted data at the j-th sample moment under the parameter combination corresponding to the i-th iteration, and it is also the prediction result of the data belonging to the environmental data type W at the j-th sample moment when the slope and intercept belong to the parameters in the parameter combination corresponding to the i-th iteration; and the target intercept and target slope determined by parameter optimization through the Yesian optimization algorithm can make the subsequent prediction results more reliable and accurate.

[0036] In this embodiment, the specific process of obtaining the predicted data at each sample moment under the parameter combination corresponding to the i-th iteration is as follows: the target quantity characteristic value of the environmental data type W at the sample moment t is multiplied by the experimental slope and then added to the experimental intercept, and the result obtained by rounding up is recorded as T; in the environmental data sequence corresponding to the environmental data type W before the sample moment t and at the current monitoring moment, a continuous data segment with an acquisition time and the sample moment t and a length of T is obtained, and recorded as the experimental data window of the parameter combination corresponding to the sample moment t at the i-th iteration, that is, if the sample moment t is the m-th monitoring moment in the time period from the start of monitoring the environmental data type W to the current monitoring moment, and the environmental data type at the current monitoring moment is The collection time of the mth data in the environmental data sequence corresponding to W is the mth monitoring moment, and the collection time of the mTth data in the environmental data sequence corresponding to the environmental data type W at the current monitoring moment is the mTth monitoring moment. Then the data in the experimental data window at the sample time t under the parameter combination corresponding to the i-th iteration is composed of the data from the mth data to the mTth data in the environmental data sequence corresponding to the environmental data type W at the current monitoring moment; the experimental data window at the sample time t under the parameter combination corresponding to the i-th iteration is input into the prediction model of the environmental data type W, and the output result of the prediction model of the environmental data type W at this time is the predicted data of the sample time t under the parameter combination corresponding to the i-th iteration.

[0037] It should be noted that the prediction model of the environmental data type W is a trained LSTM model, and the input of the prediction model of the environmental data type W is the historical data belonging to the environmental data type W, and the output is the predicted data belonging to the environmental data type W, that is, the data predicted by the prediction model of the environmental data type W belongs to the environmental data type W.

[0038] After obtaining the data window of the environmental data type W at the future monitoring moment, the data window of the environmental data type W at the future monitoring moment is input into the prediction model of the environmental data type W, and the result output by the prediction model of the environmental data type W at this time is recorded as the predicted environmental data of the environmental data type W at the future monitoring moment, that is, the predicted environmental data of the environmental data type W at the future monitoring moment refers to the predicted environmental data of the location of the distributed new energy power station at the future monitoring moment; and the future monitoring moments in this embodiment refer to the monitoring moments adjacent to the current monitoring moment and located after the current monitoring moment in time, that is, the next monitoring moment of the current monitoring moment.

[0039] Therefore, this embodiment obtains the predicted environmental data of the environmental data type W at the future monitoring moment through the above process, and since the method for obtaining the predicted environmental data of different environmental data types at the future monitoring moment is the same as the method for obtaining the predicted environmental data of the environmental data type W at the above future monitoring moment, this embodiment can also obtain the predicted environmental data of each environmental data type in the environmental data type set at the future monitoring moment through the above process.

[0040] Step S003: Obtain predicted power generation of the distributed new energy power station based on predicted environmental data of different environmental data types and a power generation prediction model, and regulate the distributed new energy power station based on the predicted power generation.

[0041] After obtaining the predicted environmental data for each environmental data type in the set of environmental data types at the future monitoring time, the predicted environmental data for each environmental data type in the set of environmental data types at the future monitoring time is input into the power generation prediction model, and the output of the power generation prediction model at this time is recorded as the predicted power generation of the distributed new energy power station at the future monitoring time. The power generation prediction model in this embodiment is also a trained LSTM model, but there are differences in the input and output between the power generation prediction model and the prediction model for the above-mentioned environmental data types. The input of the power generation prediction model is the predicted environmental data, and the output is the predicted power generation, while the input of the prediction model for environmental data type W is the historical environmental data, and the output is the predicted environmental data. Since the training process of the LSTM model is a well-known technology, this embodiment will not further describe the model training process.

[0042] Then, the distributed new energy power station is regulated according to the predicted power generation of the distributed new energy power station at the future monitoring time, and the power output of the distributed new energy power station to the power grid is mainly regulated according to the predicted power generation and the load required in the power grid. Since the predicted power generation of the distributed new energy power station and the load required in the power grid are known, the method of regulating the power output of the distributed new energy power station connected to the power grid to the power grid is a well-known technology, so it will not be described in this embodiment.

[0043] At this point, this embodiment completes the regulation of the distributed new energy power station.

[0044] In summary, this embodiment first obtains the environmental data sequence corresponding to different environmental data types at the current monitoring moment; then obtains the extreme point on the seasonal component curve of the environmental data sequence to obtain the extreme moment combination corresponding to the environmental data type at the current monitoring moment; according to the difference between the two extreme moments in the extreme moment combination and the position of the horizontal coordinate on the residual component curve of the environmental data sequence belonging to the extreme moment, obtains the target quantity characteristic value of the environmental data type at the future monitoring moment, and obtains the data window of the environmental data type at the future monitoring moment according to the target quantity characteristic value of the environmental data type at the future monitoring moment, inputs the data window into the prediction model of the environmental data type to output the predicted environmental data of the environmental data type at the future monitoring moment; obtains the predicted power generation of the distributed new energy power station according to the predicted environmental data of different environmental data types and the power generation prediction model, and regulates the distributed new energy power station according to the predicted power generation. This embodiment can improve the accuracy of the prediction of the power generation of the distributed new energy power station by adaptively obtaining the data window, thereby ensuring the effect of the subsequent regulation of the electric energy output by the distributed new energy power station to the power grid, thereby avoiding the damage to the stability of the power grid operation and the economic and market losses as much as possible.

[0045] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A smart control method based on distributed new energy power stations, characterized in that: The method comprises the following steps: Obtaining environmental data sequences corresponding to different environmental data types at the current monitoring moment, where the data in the environmental data sequences are environmental data collected at the location of the distributed new energy power station; For any environmental data type, a seasonal component curve and a residual component curve of the environmental data sequence corresponding to the environmental data type are obtained, and based on the extreme value points on the seasonal component curve, an extreme value moment combination corresponding to the environmental data type at the current monitoring moment is obtained, and based on the difference between two extreme value moments in the extreme value moment combination and the position of the horizontal coordinate on the residual component curve belonging to the extreme value moment, a target quantity characteristic value of the environmental data type at the future monitoring moment is obtained, and based on the target quantity characteristic value of the environmental data type at the future monitoring moment, a data window of the environmental data type at the future monitoring moment is obtained, and the data window is input into a prediction model of the environmental data type to output predicted environmental data of the environmental data type at the future monitoring moment; The predicted power generation of the distributed new energy power station is obtained based on the predicted environmental data of different environmental data types and the power generation prediction model, and the distributed new energy power station is regulated according to the predicted power generation.

2. The intelligent control method based on a distributed new energy power station according to claim 1, characterized in that: The method for obtaining the extreme moment combination includes: The sequence of the horizontal coordinate values ​​of all extreme points on the seasonal component curve arranged in chronological order is recorded as the extreme moment sequence, and the combinations constructed by all two adjacent extreme moments in the extreme moment sequence are recorded as the extreme moment combinations corresponding to the environmental data type at the current monitoring moment.

3. The intelligent control method based on a distributed new energy power station according to claim 1, characterized in that: The method for obtaining the target quantity characteristic value of the environmental data type at the future monitoring time includes: According to the time interval between two extreme moments in the extreme moment combination closest to the current monitoring moment in time and the time interval between two extreme moments in any extreme moment combination, the initial quantity characteristic value of the environmental data type at the future monitoring moment is obtained; on the residual component curve, the residual component curve segment corresponding to each extreme moment combination is obtained, and the combination formed by the horizontal coordinates of the endpoints of the residual component curve segment corresponding to the extreme moment combination is the corresponding extreme moment combination, and according to the mean of the absolute values ​​of all residual components on the residual component curve segment corresponding to the extreme moment combination and the standard deviation of all residual components on the residual component curve segment corresponding to the extreme moment combination, the random fluctuation characterization value of the environmental data type at the future monitoring moment is obtained; the result of subtracting the random fluctuation characterization value from the preset first constant and multiplying it by the initial quantity characteristic value of the environmental data type at the future monitoring moment is used as the target quantity characteristic value of the environmental data type at the future monitoring moment.

4. The intelligent control method based on a distributed new energy power station according to claim 3, characterized in that: The method for obtaining the initial quantitative characteristic value of the environmental data type at the future monitoring time includes: The time interval between the two extreme moments in the extreme moment combination is recorded as the distance value corresponding to the corresponding extreme moment combination, and the normalized value of the reciprocal of the time interval between the middle moment between the two extreme moments in the extreme moment combination and the current monitoring moment is recorded as the distance weight value of the corresponding extreme moment combination; among all extreme moment combinations, the extreme moment combination closest to the current monitoring moment in time is recorded as the nearest neighbor combination; the weighted difference value of the extreme moment combination is obtained, and the weighted difference value corresponding to the extreme moment combination is the absolute difference between the distance value corresponding to the corresponding extreme moment combination and the distance value corresponding to the nearest neighbor combination. The value is then multiplied by the distance weight value at the corresponding extreme value moment; the negative correlation mapping value obtained by accumulating the weighted difference values ​​of all extreme value moment combinations corresponding to the environmental data type at the current monitoring moment is recorded as the stability index value corresponding to the environmental data type at the current monitoring moment; the average of the distance values ​​corresponding to all extreme value moment combinations corresponding to the environmental data type at the current monitoring moment is recorded as the periodicity index value corresponding to the environmental data type at the current monitoring moment; the product of the stability index value and the periodicity index value is recorded as the initial quantity characteristic value of the environmental data type at the future monitoring moment.

5. The intelligent control method based on a distributed new energy power station according to claim 4, characterized in that: The method for obtaining the random fluctuation characterization value of the environmental data type at the future monitoring time includes: The mean of the absolute values ​​of all residual components on the residual item curve segment corresponding to the extreme value moment combination is taken as the residual mean of the corresponding extreme value moment combination, the standard deviation of all residual components on the residual item curve segment corresponding to the extreme value moment combination is taken as the residual standard deviation of the corresponding extreme value moment combination, the product of the residual standard deviation of the extreme value moment combination and the residual mean of the corresponding extreme value moment combination is recorded as the residual eigenvalue of the corresponding extreme value moment combination, the result of comparing the residual eigenvalue of the extreme value moment combination with the residual eigenvalue of the nearest neighbor combination and then multiplying the result by the distance weight value of the corresponding extreme value moment combination is taken as the random eigenvalue of the corresponding extreme value moment combination, and the normalized value of the cumulative sum of the random eigenvalues ​​of all extreme value moment combinations corresponding to the environmental data type at the current monitoring moment is taken as the random fluctuation characterization value of the environmental data type at the current monitoring moment.

6. The intelligent control method based on a distributed new energy power station according to claim 1, characterized in that: The method for obtaining a data window of the environmental data type at a future monitoring moment according to a target quantity characteristic value of the environmental data type at a future monitoring moment includes: A preset number of monitoring moments are selected as sample moments before the future monitoring moments, and the target quantity characteristic values ​​of the environmental data type at the sample moments are obtained; based on the target quantity characteristic values ​​of the environmental data type at the sample moments, the target intercept and target slope corresponding to the environmental data type are obtained; based on the target intercept and target slope corresponding to the environmental data type, a function is constructed, whose intercept is the target intercept corresponding to the environmental data type, whose slope is the target slope corresponding to the environmental data type, whose input is the target quantity characteristic value of the environmental data type, and whose output is the data length, and is recorded as the data length function corresponding to the environmental data type; based on the data length function corresponding to the environmental data type and the target quantity characteristic values ​​of the environmental data type at the future monitoring moments, a data window of the environmental data type at the future monitoring moments is obtained.

7. The intelligent control method based on a distributed new energy power station according to claim 6, characterized in that: The method for obtaining a data window of the environmental data type at a future monitoring moment according to a data length function corresponding to the environmental data type and a target quantity characteristic value of the environmental data type at a future monitoring moment includes: The target quantity characteristic value of the environmental data type at the current monitoring moment is input into the data length function corresponding to the environmental data type, and the rounded value of the output result of the data length function is recorded as the data length of the environmental data type at the future monitoring moment; traversing from the current monitoring moment forward until the traversed environmental data belonging to the environmental data type is equal to the data length of the environmental data type at the future monitoring moment, and stopping the traversal, and recording the window composed of all the traversed environmental data belonging to the environmental data type as the data window of the environmental data type at the future monitoring moment.

8. The intelligent control method based on a distributed new energy power station according to claim 7, characterized in that: The method for obtaining the target intercept and target slope corresponding to the environmental data type includes: A combination constructed by a randomly selected intercept and a slope is recorded as the parameter combination corresponding to the first iteration, and the preferred index value of the parameter combination corresponding to the first iteration under the environmental data type is obtained. The intercept and slope in the parameter combination corresponding to the first iteration are updated using the Yes optimization algorithm to obtain the parameter combination corresponding to the second iteration and the preferred index value of the parameter combination corresponding to the second iteration under the environmental data type. The intercept and slope in the parameter combination corresponding to the second iteration are continued to be updated using the Yes optimization algorithm to obtain the parameter combination corresponding to the third iteration and the judgment index value of the parameter combination corresponding to the third iteration under the environmental data type. This process is repeated until the number of iterations reaches the preset number of iterations, and the parameter combination corresponding to each iteration under the environmental data type and the preferred index value of the parameter combination corresponding to each iteration under the environmental data type are statistically obtained. The slope and intercept in the parameter combination corresponding to the minimum preferred index value are selected as the target intercept and target slope corresponding to the environmental data type.

9. The intelligent control method based on a distributed new energy power station according to claim 8, characterized in that: The method for obtaining the optimal index value of the parameter combination corresponding to any iteration includes: For the i-th iteration under the environmental data type, the slope and intercept in the parameter combination corresponding to the i-th iteration under the environmental data type are respectively recorded as the experimental slope and experimental intercept, and the actual data at each sample moment and the predicted data at each sample moment under the parameter combination corresponding to the i-th iteration are obtained. The actual data at any sample moment t is the environmental data belonging to the environmental data type collected at the sample moment t; the mean square error calculated based on the actual data of all sample moments and the predicted data at the sample moment t under the parameter combination corresponding to the i-th iteration is recorded as the preferred index value of the parameter combination corresponding to the i-th iteration under the environmental data type.

10. The intelligent control method based on a distributed new energy power station according to claim 9, characterized in that: The method for obtaining the prediction data at each sample moment under the parameter combination corresponding to the i-th iteration includes: The integer value of the result obtained by multiplying the target quantity characteristic value of the environmental data type at the sample time t by the experimental slope and then adding the result to the experimental intercept is recorded as T; before the sample time t, a continuous data segment with an acquisition time adjacent to the sample time t and a length of T is obtained, and recorded as the experimental data window under the parameter combination corresponding to the i-th iteration of the sample time t, the experimental data window under the parameter combination corresponding to the i-th iteration of the sample time t is input into the prediction model of the environmental data type, and the output result of the prediction model of the environmental data type is recorded as the predicted data of the sample time t under the parameter combination corresponding to the i-th iteration.

11. The intelligent control method based on a distributed new energy power station according to claim 1, characterized in that: A method for obtaining predicted power generation of a distributed new energy power station based on predicted environmental data of different environmental data types and a power generation prediction model includes: Construct an electricity prediction model, and input the predicted environmental data of all environmental data types at future monitoring moments into the power generation prediction model, and record the output result of the power generation prediction model as the predicted power generation of the distributed new energy power station at future monitoring moments.

12. The intelligent control method based on a distributed new energy power station according to claim 1, characterized in that: The power prediction model is an LSTM model.

Images