A remote intelligent operation and maintenance method and system based on photovoltaic and wind power data

Abstract

The application provides a remote intelligent operation and maintenance method and system based on photovoltaic and wind power data, which comprises the following steps: obtaining a plurality of original data sets of a plurality of wind and light field stations, and forming a plurality of standby data sets after preprocessing; obtaining a time sequence length parameter and a spatial correlation matrix through the standby data sets; constructing an initial output prediction model, updating the initial output prediction model to a final output prediction model through the time sequence length parameter and the spatial correlation matrix, and then obtaining historical prediction output data and real prediction output data; obtaining a prediction error corresponding to the historical prediction output data, expanding the real prediction output data into a real prediction output range through a plurality of prediction errors, and judging whether there is a maintenance requirement. Through the above method, end-to-end automatic remote intelligent operation and maintenance is realized, a real-time monitoring means for wind and light field stations is provided, the consumption of manpower and material resources is reduced, the time cost is saved, and the real-time performance and accuracy of maintenance are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data prediction, in particular to a remote intelligent operation and maintenance method and system based on photovoltaic and wind power data. BACKGROUND

[0002] At present, energy power has gradually transformed from high-carbon, mainly fossil energy to low-carbon, mainly clean energy. With the continuous reduction of large-scale energy storage costs, wind and light stations have become the mainstream trend of new energy power due to their multi-time scale energy complementary characteristics.

[0003] The wind and light station uses a solar cell array and a wind turbine to store the generated electric energy in a storage battery pack. When the user needs to use electricity, the inverter converts the stored direct current in the storage battery pack into alternating current and sends it to the user load through the power transmission line.

[0004] The existing operation of the wind and light station is generally carried out in remote areas or unattended conditions. It is difficult and cumbersome to monitor and maintain the wind and light station distributed on the ground in real time, which requires a large amount of time cost and human and material resources, and it is difficult to ensure the real-time maintenance. SUMMARY

[0005] In view of the deficiencies of the prior art, the purpose of the present application is to provide a remote intelligent operation and maintenance method and system based on photovoltaic and wind power data, which aims to solve the technical problems that the wind and light station is located in a remote place and is distributed scattered, it is difficult and cumbersome to monitor and maintain it in real time, it requires a large amount of time cost and human and material resources, and it is difficult to ensure the real-time maintenance.

[0006] In order to achieve the above purpose, in a first aspect, the present application provides a remote intelligent operation and maintenance method based on photovoltaic and wind power data, comprising the following steps:

[0007] Obtain a plurality of original data sets of a plurality of wind and light stations, the original data set comprising original output data and original meteorological data, and preprocess the original data set to obtain a standby data set comprising standby output data and standby meteorological data;

[0008] Obtain a time series length parameter and a spatial correlation matrix corresponding to all wind and light stations through a plurality of standby output data;

[0009] Construct an initial output prediction model, and construct an input data set and a result data set, update the initial output prediction model to a final output prediction model through the input data set, the result data set, the time series length parameter and the spatial correlation matrix, and obtain historical prediction output data through the final output prediction model;

[0010] Obtaining a prediction error corresponding to the historical predicted output data, obtaining true predicted output data by the final output prediction model, expanding the true predicted output data into a true predicted output range by a plurality of the prediction errors, comparing true output data with the true predicted output range to determine whether there is a maintenance requirement.

[0011] Further, the step of preprocessing the original data set to obtain a to-be-used data set comprising to-be-used output data and to-be-used meteorological data comprises:

[0012] Performing missing data filling and anomaly processing on the original output data and original meteorological data to obtain to-be-used output data and stage meteorological data;

[0013] Performing normalization processing on the stage meteorological data to obtain to-be-used meteorological data, and the to-be-used output data and the to-be-used meteorological data constitute a to-be-used data set.

[0014] Further, the to-be-used output data comprises to-be-used output values in a plurality of continuous time frames, and the step of obtaining a time series length parameter and a spatial correlation matrix corresponding to all wind and light field stations by a plurality of the to-be-used output data comprises:

[0015] Obtaining a field station output mean value based on a plurality of the to-be-used output values, setting a plurality of delay orders, and obtaining a time series correlation coefficient corresponding to the delay order by the to-be-used output values, the field station output mean value, and the delay order;

[0016] Selecting a time series correlation coefficient greater than a first correlation threshold value as a candidate correlation coefficient, and selecting a delay order corresponding to the smallest candidate correlation coefficient as a time series length parameter;

[0017] Obtaining a spatial correlation coefficient between two wind and light field stations by the to-be-used output values and the field station output mean value, and constructing a correlation relationship between two wind and light field stations with a spatial correlation coefficient greater than a second correlation threshold value to form a spatial correlation matrix.

[0018] Further, the formula for obtaining the time series correlation coefficient is:

[0019] ,

[0020] wherein, denotes the time series correlation coefficient, denotes the to-be-used output value in the tth time frame, denotes the field station output mean value, denotes the delay order, denotes the total sampling duration;

[0021] The formula for obtaining the spatial correlation coefficient is:

[0022] ,

[0023] wherein, represents a spatial correlation coefficient between the ith wind-solar station and the jth wind-solar station, represents a standby output value of the ith wind-solar station at the tth time frame, represents a standby output value of the jth wind-solar station at the tth time frame, represents a station output mean value of the ith wind-solar station, represents a station output mean value of the jth wind-solar station.

[0024] Further, the step of constructing the input data set and the result data set comprises:

[0025] selecting a reference time node, and dividing the standby output data into a first data set and a result data set through the reference time node;

[0026] dividing a second data set corresponding to the first data set from the standby meteorological data through the reference time node;

[0027] splicing the first data set and the second data set into an input data set.

[0028] Further, the initial output prediction model comprises a spatial convolution module and a time attention module, and the step of updating the initial output prediction model into a final output prediction model through the input data set, the result data set, the time sequence length parameter and the spatial correlation matrix comprises:

[0029] constructing a dynamic correlation matrix in the spatial convolution module through the input data set based on the spatial correlation matrix;

[0030] converting the input data set into a stage feature set through the dynamic correlation matrix, the stage feature set comprising stage sub-features under a plurality of time sequences;

[0031] setting a division window in the time attention module through the time sequence length parameter, inputting the stage feature set into the time attention module to select a to-be-updated sub-feature from a plurality of the stage sub-features, and selecting a plurality of reference sub-features from a plurality of the stage sub-features based on the division window, generating a final sub-feature corresponding to the to-be-updated sub-feature through the to-be-updated sub-feature and the plurality of reference sub-features;

[0032] The final sub-features are combined into a prediction output set, and a loss function is constructed by the prediction output set and the result data set to update the initial output prediction model into a final output prediction model.

[0033] Further, the step of constructing the dynamic correlation matrix in the spatial convolution module by the input data set comprises:

[0034] An attention score between two wind and light field stations is obtained by the input data set;

[0035] The attention score is normalized to obtain an attention weight between two wind and light field stations;

[0036] The attention weights are combined into the dynamic correlation matrix.

[0037] Further, the attention score is obtained according to the following formula:

[0038] ,

[0039] Wherein, represents the attention score of the ith wind and light field station and the jth wind and light field station at the tth time frame, 、 、 、 、 All represent learnable parameters, represents a transpose symbol, represents the time frame sub-data of the ith wind and light field station and the jth wind and light field station in the input data set at the tth time frame, represents an activation function.

[0040] Further, the step of expanding the real prediction output data into a real prediction output range by the plurality of prediction errors comprises:

[0041] The plurality of prediction errors are sorted, and a first position threshold and a second position threshold are set;

[0042] The total number of the plurality of prediction errors is obtained, the first error is selected from the plurality of prediction errors by the total number and the first position threshold, and the second error is selected from the plurality of prediction errors by the total number and the second position threshold;

[0043] The real prediction output data are superimposed with the first error and the second error respectively to form a real prediction output range.

[0044] In a second aspect, the embodiments of the present application provide a remote intelligent operation and maintenance system based on photovoltaic and wind power data, which is applied to the remote intelligent operation and maintenance method based on photovoltaic and wind power data as described in the first aspect above, and the system comprises:

[0045] a processing module configured to acquire a plurality of original data sets of a plurality of wind and light field stations, the original data sets comprising original output data, original meteorological data and original location data, and to pre-process the original data sets to acquire a standby data set comprising standby output data, standby meteorological data and standby location data;

[0046] an extraction module configured to acquire a time series length parameter and a spatial correlation matrix corresponding to all wind and light field stations through a plurality of the standby output data;

[0047] a prediction module configured to construct an initial output prediction model, construct an input data set and a result data set, update the initial output prediction model to a final output prediction model through the input data set, the result data set, the time series length parameter and the spatial correlation matrix, and acquire historical prediction output data through the final output prediction model;

[0048] an execution module configured to acquire prediction errors corresponding to the historical prediction output data, acquire real prediction output data through the final output prediction model, expand the real prediction output data into a real prediction output range through a plurality of the prediction errors, compare real output data with the real prediction output range, and determine whether there is a maintenance requirement.

[0049] In a third aspect, the embodiments of the present application provide a computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, and the processor implements the remote intelligent operation and maintenance method based on photovoltaic and wind power data as described in the first aspect above when executing the computer program.

[0050] In a fourth aspect, the embodiments of the present application provide a storage medium having a computer program stored thereon, and the computer program is executable by a processor to implement the remote intelligent operation and maintenance method based on photovoltaic and wind power data as described in the first aspect above.

[0051] Compared with the prior art, the beneficial effects of the present application are that: by acquiring the original output data and the original meteorological data between different wind and light field stations, constructing the time series length parameter and the spatial correlation matrix, the limitations of traditional independent monitoring of a single station are broken through, the correlation of output fluctuations between different wind and light field stations and the periodicity of the output of the same wind and light field station are quantified, and the accuracy of output prediction is improved; by generating the true predicted output range based on the prediction error, the output uncertainty of the wind and light field station is quantified, a reasonable fluctuation range of output prediction is set, and the maintenance false alarm rate is reduced; by constructing the final output prediction model, based on the foregoing method, end-to-end automated remote intelligent operation and maintenance is realized, a means for real-time monitoring of wind and light field stations is provided, the consumption of manpower and material resources is reduced, time cost is saved, and the real-time and accuracy of maintenance are ensured. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 The flow chart of the remote intelligent operation and maintenance method based on photovoltaic and wind power data in the first embodiment of the present application;

[0053] Figure 2 The structural block diagram of the remote intelligent operation and maintenance system based on photovoltaic and wind power data in the second embodiment of the present application;

[0054] The following specific embodiments will further illustrate the present application in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0055] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the related drawings. Several embodiments of the present application are shown in the drawings. However, the present application can be realized in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present application more thorough and comprehensive.

[0056] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there can be a middle element. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or there can be a middle element. The terms "vertical", "horizontal", "left", "right", and similar expressions used herein are for illustrative purposes only.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terminology used in the description of the present application herein is only for the purpose of describing specific embodiments and is not intended to limit the present application. The term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0058] Referring to Figure 1 The first embodiment of the present application provides a remote intelligent operation and maintenance method based on photovoltaic and wind power data, comprising the following steps:

[0059] S10: Obtain a plurality of original data sets of a plurality of wind and light stations, wherein the original data sets include original output data and original meteorological data, and the original data sets are preprocessed to obtain a standby data set including standby output data and standby meteorological data;

[0060] In this embodiment, the original output data is wind power or photovoltaic power. When the original output data is wind power, the original meteorological data includes wind speed and wind direction; when the original output data is photovoltaic power, the original meteorological data is irradiance and temperature. It can be understood that wind power and photovoltaic power can be processed respectively at the same time to complete the remote intelligent operation and maintenance of all wind and light stations. Further, the original output data includes a plurality of sub-output data under a continuous time frame, and the original meteorological data includes a plurality of sub-meteorological data under a continuous time frame, and the sub-meteorological data and the sub-output data correspond one by one.

[0061] The step S10 comprises:

[0062] S110: Perform missing data filling and anomaly processing on the original output data and original meteorological data to obtain standby output data and stage meteorological data;

[0063] In this embodiment, the average value of adjacent time is used for missing data filling, and the anomaly processing refers to adaptive correction of obviously incorrect data, such as directly correcting the sub-output data less than 0 to 0.

[0064] S120: Perform normalization processing on the stage meteorological data to obtain standby meteorological data, and the standby output data and the standby meteorological data constitute a standby data set;

[0065] In the same standby meteorological data, the difference between the maximum value and the minimum value is taken as the denominator, and the difference between each value and the minimum value is taken as the numerator to complete the normalization processing. Normalization processing of the meteorological data can avoid the interference of feature scale difference on the construction of subsequent prediction model.

[0066] S20: Obtain a time sequence length parameter corresponding to all wind and light stations and a spatial correlation matrix through a plurality of standby output data;

[0067] Specifically, the step S20 comprises:

[0068] S210: Obtain a station output mean value based on a plurality of the to-be-used output values, set a plurality of delay orders, and obtain a time series correlation coefficient corresponding to the delay order through the to-be-used output value, the station output mean value, and the delay order;

[0069] The formula for obtaining the time series correlation coefficient is:

[0070] ,

[0071] Wherein, represents the time series correlation coefficient, represents the to-be-used output value in the tth time frame, represents the station output mean value, represents the delay order, represents the total sampling duration.

[0072] S220: Select the time series correlation coefficient greater than the first correlation threshold value as the candidate correlation coefficient, and select the delay order corresponding to the smallest candidate correlation coefficient as the time series length parameter;

[0073] In this embodiment, the first correlation threshold value is 0.6. It should be noted that the delay order starts from 0 and increases, such as a plurality of delay orders of 0, 1, 2, 3, 4, 5, and 6, and the time series correlation coefficients obtained are 0.1, 0.2, 0.4, 0.7, 0.8, and 0.9, respectively. At this time, the candidate correlation coefficients are 0.7, 0.8, and 0.9, and the time series length parameter corresponding to 0.7 is the delay order 4. Further, since a plurality of wind and light stations are processed synchronously, the time series length parameter corresponding to the largest number of a plurality of wind and light stations can be selected as the final value.

[0074] S230: Obtain a spatial correlation coefficient between two wind and light stations through the to-be-used output value and the station output mean value, and construct a correlation relationship between two wind and light stations with a spatial correlation coefficient greater than a second correlation threshold value to form a spatial correlation matrix;

[0075] The formula for obtaining the spatial correlation coefficient is:

[0076] ,

[0077] Wherein, represents the spatial correlation coefficient between the ith wind and light station and the jth wind and light station, represents the to-be-used output value of the ith wind and light station in the tth time frame, represents the to-be-used output value of the jth wind and light station in the tth time frame, represents the station output mean value of the ith wind and light station, The field station output mean value of the jth wind and light field station is represented. Assuming that there are 10 wind and light field stations, the 10 wind and light field stations can be selectively connected according to the spatial correlation coefficient.

[0078] S30: An initial output prediction model is constructed, an input data set and a result data set are constructed, the initial output prediction model is updated to a final output prediction model through the input data set, the result data set, a time sequence length parameter and a spatial correlation matrix, and historical prediction output data is obtained through the final output prediction model.

[0079] The initial output prediction model comprises a spatial convolution module and a time attention module.

[0080] The step 30 comprises:

[0081] S310: A reference time node is selected, and the to-be-used output data is divided into a first data set and a result data set through the reference time node.

[0082] Understandably, the to-be-used output data comprises to-be-used output values in a plurality of continuous time frames, and the to-be-used output data can be divided into a plurality of to-be-used output values in an earlier time and a plurality of to-be-used output values in a later time by taking the reference time node as a boundary, the plurality of to-be-used output values in the earlier time form the first data set, and the plurality of to-be-used output values in the later time form the result data set.

[0083] S320: A second data set corresponding to the first data set is divided from the to-be-used meteorological data through the reference time node.

[0084] Understandably, the to-be-used meteorological data comprises sub-meteorological data in a plurality of continuous time frames, and because the to-be-used output data and the to-be-used meteorological data are one-to-one corresponding in time nodes, after the to-be-used meteorological data is divided, the sub-meteorological data in the earlier time forms the second data set, and by introducing the second data set, the first data set is synchronously input into a prediction model in a subsequent process, which can ensure that the to-be-used meteorological data which has a direct impact on the to-be-used output data is considered in a prediction process, and the prediction result is more accurate.

[0085] S330: The first data set and the second data set are spliced into an input data set.

[0086] S340: A dynamic correlation matrix is constructed in the spatial convolution module through the input data set with the spatial correlation matrix as a reference.

[0087] By inputting the spatial correlation matrix, when the spatial convolution module updates the dynamic correlation matrix, only the data influence between wind and light stations with strong correlation needs to be considered, the complexity of calculation is reduced, the prediction model is prevented from being disturbed by unimportant noise relationships, and the prediction accuracy is improved. Specifically, the attention score between two wind and light stations is obtained through the input data set;

[0088] The formula for obtaining the attention score is:

[0089] ,

[0090] Among them, represents the attention score of the ith wind and light station and the jth wind and light station at the tth time frame, 、 、 、 、 all represent learnable parameters, represents the transpose symbol, represents the time frame sub-data of the ith wind and light station and the jth wind and light station in the input data set at the tth time frame, represents an activation function. It should be noted that the learnable parameters can be iteratively updated by the loss function of the initial processing prediction model after setting the initial value, and then the final value is formed. Generally, the spatial convolution module has multiple convolution layers, therefore, the attention score will be iterated through multiple convolution layers, is the output of the previous convolution layer, which is essentially the time frame sub-data of the ith wind and light station and the jth wind and light station in the input data set at the tth time frame. The time frame sub-data includes the to-be-output value and the meteorological sub-data, representing synchronous processing of all types of input data. Through the spatial convolution module, the data of each wind and light station is fused with the information of other wind and light stations with strong correlation, improving the accuracy of data prediction.

[0091] The attention score is normalized to obtain the attention weight between two wind and light stations;

[0092] The attention score represents the influence of different wind and light stations, in this embodiment, the normalization processing is performed through the Softmax function, taking three wind and light stations as an example: A station, B station, and C station, then the A station has AB attention score and AC attention score, after the normalization processing, there are AB attention weight and AC attention weight, and the sum of the two is 1.

[0093] The attention weights are combined into the dynamic correlation matrix. Understandably, the dynamic correlation matrix is the set of all attention weights between the wind and light stations. It can simultaneously predict the data of different wind and light stations.

[0094] S350: converting the input data set into a stage feature set through the dynamic correlation matrix, the stage feature set including stage sub-features under several time sequences;

[0095] Specifically, for each wind and light station, on the basis of the original data, the original data of other wind and light stations at the corresponding time node are weighted by the attention weights, thereby forming the stage sub-features. Understandably, the number of stage sub-features corresponds to the number of to-be-output values, and the stage sub-features are high-dimensional features formed by comprehensively considering the influence of to-be-output values between different stations and the influence of meteorological sub-data.

[0096] S360: setting a split window in the time attention module through the time sequence length parameter, inputting the stage feature set into the time attention module to select a to-be-updated sub-feature from the stage sub-features and select several reference sub-features from the stage sub-features based on the split window, and generating a final sub-feature corresponding to the to-be-updated sub-feature through the to-be-updated sub-feature and the several reference sub-features;

[0097] The time attention module considers the time correlation of stage sub-features under different time frames, so that the final sub-feature obtained comprehensively considers the spatial relationship and historical change rule between different wind and light stations, further improving the accuracy of subsequent prediction.

[0098] Suppose there are five time frame stage sub-features, namely feature 1, feature 2, feature 3, feature 4 and feature 5, and the prediction needs to be based on feature 5, and the time sequence length parameter is 3, the length of the split window is 3, then the to-be-updated sub-feature is feature 5, and the several reference sub-features are feature 3 and feature 4. After obtaining the several reference sub-features and the to-be-updated sub-feature, the three are weighted into the final sub-feature through the time attention weight matrix. Understandably, the time attention module will generate a hidden state vector at each time step when processing the several reference sub-features and the to-be-updated sub-feature, the hidden state vector condenses the historical information up to the current time, calculates the correlation score between the current time hidden state vector and the historical time hidden state vector, and then forms the time attention weight matrix through normalization processing. In this embodiment, the correlation score is obtained through a score function.

[0099] S370: combine the plurality of final sub-features into a prediction output set, and build a loss function through the prediction output set and the result data set to update the initial output prediction model into a final output prediction model;

[0100] It can be understood that, in order to synchronize the output prediction of different wind and light stations, the plurality of final sub-features are prediction values of different stations at different time frames. By building a loss function with the recorded values of different stations at different time frames in the result data set, the initial output prediction model can be iteratively optimized through the loss function.

[0101] S40: obtaining a prediction error corresponding to the historical predicted output data, obtaining true predicted output data through the final output prediction model, expanding the true predicted output data into a true predicted output range through a plurality of prediction errors, and comparing the true output data with the true predicted output range to determine whether there is a maintenance requirement;

[0102] Because the output of wind and light stations has uncertainty such as intermittency, randomness and volatility, the uncertainty caused by the prediction error cannot be estimated only through deterministic point prediction values. In order to balance prediction accuracy and risk control, the uncertainty needs to be quantified to a certain extent. The historical predicted output data is the prediction output set, and the difference is only the result obtained by the prediction model at different stages. By comparing the historical predicted output data with the result data set, a plurality of prediction errors are formed. The true predicted output data is the result value obtained by the final output prediction model after predicting the output data at the current time.

[0103] The step S40 comprises:

[0104] S410: sorting processing is performed on the plurality of prediction errors, and a first position threshold and a second position threshold are set;

[0105] In this embodiment, the first position threshold is 0.025, and the second position threshold is 0.975.

[0106] S420: obtaining the total number of the plurality of prediction errors, selecting a first error from the plurality of prediction errors through the total number and the first position threshold, and selecting a second error from the plurality of prediction errors through the total number and the second position threshold;

[0107] It can be understood that, if there are 2000 prediction errors, the first error is the 50th prediction error, and the second error is the 1950th prediction error.

[0108] S430: superimposing the real predicted output data with the first error and the second error respectively to form a real predicted output range.

[0109] It can be understood that if the real output data is within the real predicted output range, no maintenance is needed for the corresponding wind and light field station, and if the real output data is outside the real predicted output range, maintenance is needed for the corresponding wind and light field station.

[0110] By obtaining the original output data and the original meteorological data between different wind and light field stations, the time series length parameter and the spatial correlation matrix are constructed, which breaks through the limitation of traditional independent monitoring of a single station, quantifies the correlation of output fluctuations between different wind and light field stations and the periodicity of the output of the same wind and light field station, and improves the accuracy of output prediction; by generating the real predicted output range based on the prediction error, the output uncertainty of the wind and light field station is quantified, a reasonable fluctuation range of output prediction is set, and the maintenance false alarm rate is reduced; by constructing the final output prediction model, based on the foregoing method, end-to-end automated remote intelligent operation and maintenance is realized, a means for real-time monitoring of wind and light field stations is provided, consumption of manpower and material resources is reduced, time cost is saved, and real-time and accuracy of maintenance are ensured.

[0111] Please refer to Figure 2 The second embodiment of the present application provides a remote intelligent operation and maintenance system based on photovoltaic and wind power data, which is applied to the remote intelligent operation and maintenance method based on photovoltaic and wind power data in the above-mentioned embodiments, which has been described and will not be repeated. As used below, the terms "module", "unit", "sub-unit" and the like can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware or a combination of software and hardware is also possible and is conceived.

[0112] The system comprises:

[0113] The processing module 10 is configured to obtain a plurality of original data sets of a plurality of wind and light field stations, the original data set comprising original output data and original meteorological data, and to preprocess the original data set to obtain a standby data set comprising standby output data and standby meteorological data.

[0114] The processing module 10 comprises:

[0115] The first unit is configured to perform missing data filling and anomaly processing on the original output data and the original meteorological data to obtain standby output data and standby meteorological data.

[0116] The second unit is configured to normalize the stage meteorological data to obtain to-be-used meteorological data, and the to-be-used output data and the to-be-used meteorological data constitute a to-be-used data set;

[0117] The extraction module 20 is configured to obtain time sequence length parameters and a spatial correlation matrix corresponding to all wind and light stations by using the to-be-used output data.

[0118] The extraction module 20 includes:

[0119] The third unit is configured to obtain a station output mean value based on the to-be-used output values, set a plurality of delay orders, and obtain time sequence correlation coefficients corresponding to the delay orders by using the to-be-used output values, the station output mean value and the delay orders.

[0120] The fourth unit is configured to select time sequence correlation coefficients greater than a first correlation threshold as candidate correlation coefficients, and select a delay order corresponding to the smallest candidate correlation coefficient as a time sequence length parameter.

[0121] The fifth unit is configured to obtain a spatial correlation coefficient between two wind and light stations by using the to-be-used output values and the station output mean value, construct a correlation relationship between the two wind and light stations with the spatial correlation coefficient greater than a second correlation threshold, and form a spatial correlation matrix.

[0122] The prediction module 30 is configured to construct an initial output prediction model, construct an input data set and a result data set, update the initial output prediction model to a final output prediction model by using the input data set, the result data set, the time sequence length parameter and the spatial correlation matrix, and obtain historical prediction output data by using the final output prediction model.

[0123] The prediction module 30 includes:

[0124] The sixth unit is configured to select a reference time node, and divide the to-be-used output data into a first data set and a result data set by using the reference time node.

[0125] The seventh unit is configured to divide a second data set corresponding to the first data set from the to-be-used meteorological data by using the reference time node.

[0126] The eighth unit is configured to splice the first data set and the second data set into an input data set.

[0127] The ninth unit is configured to construct a dynamic correlation matrix in the spatial convolution module by using the input data set as a reference and using the spatial correlation matrix.

[0128] The ninth unit is specifically configured to obtain an attention score between two wind and light stations through the input data set; normalize the attention score to obtain an attention weight between the two wind and light stations; and combine a plurality of the attention weights into the dynamic correlation matrix.

[0129] The tenth unit is configured to convert the input data set into a stage feature set through the dynamic correlation matrix, the stage feature set including stage sub-features in a plurality of time sequences.

[0130] The eleventh unit is configured to set a split window in the time attention module through the time sequence length parameter, input the stage feature set into the time attention module to select a to-be-updated sub-feature from the plurality of stage sub-features, and select a plurality of reference sub-features from the plurality of stage sub-features based on the split window, generate a final sub-feature corresponding to the to-be-updated sub-feature through the to-be-updated sub-feature and the plurality of reference sub-features.

[0131] The twelfth unit is configured to combine a plurality of the final sub-features into a prediction output set, construct a loss function through the prediction output set and the result data set, and update the initial output prediction model into a final output prediction model.

[0132] The execution module 40 is configured to obtain prediction errors corresponding to the historical prediction output data, obtain real prediction output data through the final output prediction model, expand the real prediction output data into a real prediction output range through a plurality of the prediction errors, compare real output data with the real prediction output range, and determine whether there is a maintenance requirement.

[0133] The execution module 40 includes:

[0134] The thirteenth unit is configured to sort a plurality of the prediction errors, and set a first position threshold and a second position threshold.

[0135] The fourteenth unit is configured to obtain a total number of a plurality of the prediction errors, select a first error from a plurality of the prediction errors through the total number and the first position threshold, and select a second error from a plurality of the prediction errors through the total number and the second position threshold.

[0136] The fifteenth unit is configured to superimpose the real prediction output data with the first error and the second error respectively to form a real prediction output range.

[0137] The application further provides a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the remote intelligent operation and maintenance method based on photovoltaic and wind power data as described in the above technical solution when executing the computer program.

[0138] The application further provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the remote intelligent operation and maintenance method based on photovoltaic and wind power data as described in the above technical solution.

[0139] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0140] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A remote intelligent operation and maintenance method based on photovoltaic wind power data, characterized in that, The method comprises the following steps: obtaining a plurality of original data sets of a plurality of wind and light stations, the original data sets comprising original output data and original meteorological data, and preprocessing the original data sets to obtain a to-be-used data set comprising to-be-used output data and to-be-used meteorological data, the to-be-used output data comprising to-be-used output values in a plurality of continuous time frames; obtaining a time sequence length parameter corresponding to all wind and light stations and a spatial correlation matrix through a plurality of the to-be-used output data; the step of obtaining a time sequence length parameter corresponding to all wind and light stations and a spatial correlation matrix through a plurality of the to-be-used output data comprises: obtaining a station output mean value based on a plurality of the to-be-used output values, setting a plurality of delay orders, and obtaining a time series correlation coefficient corresponding to the delay order through the to-be-used output values, the station output mean value and the delay order; selecting a time series correlation coefficient greater than a first correlation threshold as a candidate correlation coefficient, and selecting a delay order corresponding to the smallest candidate correlation coefficient as a time sequence length parameter; obtaining a spatial correlation coefficient between two wind and light stations through the to-be-used output values and the station output mean value, and constructing a correlation relationship between two wind and light stations with a spatial correlation coefficient greater than a second correlation threshold to form a spatial correlation matrix; constructing an initial output prediction model, the initial output prediction model comprising a spatial convolution module and a time attention module, and constructing an input data set and a result data set, updating the initial output prediction model to a final output prediction model through the input data set, the result data set, the time sequence length parameter and the spatial correlation matrix, and obtaining historical prediction output data through the final output prediction model; the step of updating the initial output prediction model to a final output prediction model through the input data set, the result data set, the time sequence length parameter and the spatial correlation matrix comprises: taking the spatial correlation matrix as a reference, constructing a dynamic correlation matrix in the spatial convolution module through the input data set; converting the input data set into a stage feature set through the dynamic correlation matrix, the stage feature set comprising stage sub-features in a plurality of time sequences; setting a split window in the time attention module through the time sequence length parameter, inputting the stage feature set into the time attention module to select a to-be-updated sub-feature from a plurality of the stage sub-features, and selecting a plurality of reference sub-features from a plurality of the stage sub-features based on the split window, generating a final sub-feature corresponding to the to-be-updated sub-feature through the to-be-updated sub-feature and a plurality of the reference sub-features; combining a plurality of the final sub-features into a prediction output set, constructing a loss function through the prediction output set and the result data set to update the initial output prediction model to a final output prediction model; Obtaining a prediction error corresponding to the historical predicted output data, obtaining true predicted output data by the final output prediction model, expanding the true predicted output data into a true predicted output range by a plurality of the prediction errors, comparing true output data with the true predicted output range to determine whether there is a maintenance requirement.

2. The remote intelligent operation and maintenance method based on photovoltaic wind power data according to claim 1, characterized in that, The step of preprocessing the original data set to obtain a to-be-used data set including to-be-used output data and to-be-used meteorological data comprises: Performing missing data filling and anomaly processing on the original output data and original meteorological data to obtain to-be-used output data and stage meteorological data; Performing normalization processing on the stage meteorological data to obtain to-be-used meteorological data, and the to-be-used output data and the to-be-used meteorological data constitute a to-be-used data set.

3. The remote intelligent operation and maintenance method based on photovoltaic wind power data according to claim 1, characterized in that, The formula for obtaining the time correlation coefficient is: ， wherein, denotes a timing correlation coefficient, denotes a to-be-used output value at the tth time frame, denotes a field station output mean value, denotes a delay order, denotes a total sampling duration; The formula for obtaining the spatial correlation coefficient is: ， wherein, represents a spatial correlation coefficient between the ith wind-solar farm and the jth wind-solar farm, represents a standby output value of the ith wind-solar farm at the tth time frame, represents a standby output value of the jth wind-solar farm at the tth time frame, represents a farm output mean value of the ith wind-solar farm, represents a farm output mean value of the jth wind-solar farm.

4. The remote intelligent operation and maintenance method based on photovoltaic wind power data according to claim 1, characterized in that, The step of constructing an input data set and a result data set comprises: Selecting a reference time node, and dividing the to-be-used output data into a first data set and a result data set through the reference time node; Dividing a second data set corresponding to the first data set from the to-be-used meteorological data through the reference time node; Splicing the first data set and the second data set into an input data set.

5. The remote intelligent operation and maintenance method based on photovoltaic wind power data according to claim 1, characterized in that, The step of constructing a dynamic correlation matrix in the spatial convolution module through the input data set comprises: Obtaining an attention score between two wind and light field stations through the input data set; Performing normalization processing on the attention score to obtain an attention weight between two wind and light field stations; Combining a plurality of the attention weights into the dynamic correlation matrix.

6. The remote intelligent operation and maintenance method based on photovoltaic wind power data according to claim 5, characterized in that, The formula for obtaining the attention score is: ， wherein, denotes the attention score of the ith wind-solar farm and the jth wind-solar farm at the tth time frame, denote the learnable parameters, denotes the transpose symbol, denotes the time frame sub-data of the ith wind-solar farm and the jth wind-solar farm in the input data set at the tth time frame, denotes the activation function.​​​​ 7. The remote intelligent operation and maintenance method based on photovoltaic wind power data according to claim 1, characterized in that, The step of expanding the true predicted output data into a true predicted output range through a plurality of the prediction errors comprises: Performing sorting processing on a plurality of the prediction errors, and setting a first position threshold and a second position threshold; Obtaining a total number of a plurality of the prediction errors, selecting a first error from a plurality of the prediction errors through the total number and the first position threshold, and selecting a second error from a plurality of the prediction errors through the total number and the second position threshold; Superimposing the true predicted output data on the first error and the second error respectively to form a true predicted output range.

8. A remote intelligent operation and maintenance system based on photovoltaic and wind power data, applied to the remote intelligent operation and maintenance method based on photovoltaic and wind power data according to any one of claims 1-7, characterized in that, The system comprises: A processing module configured to obtain a plurality of original data sets of a plurality of wind and light field stations, the original data set comprising original output data and original meteorological data, and preprocess the original data set to obtain a to-be-used data set comprising to-be-used output data and to-be-used meteorological data, the to-be-used output data comprising to-be-used output values in a plurality of continuous time frames; An extraction module configured to obtain a time sequence length parameter and a spatial correlation matrix corresponding to all wind and light field stations through a plurality of the to-be-used output data; The extraction module comprises: The third unit is configured to obtain a station output mean value based on the to-be-used output values, set a plurality of delay orders, and obtain a time series correlation coefficient corresponding to the delay order based on the to-be-used output values, the station output mean value, and the delay order; The fourth unit is configured to select a time series correlation coefficient greater than a first correlation threshold as a candidate correlation coefficient, and select a delay order corresponding to the smallest candidate correlation coefficient as a time series length parameter; The fifth unit is configured to obtain a spatial correlation coefficient between two wind and light stations based on the to-be-used output values and the station output mean value, construct a correlation relationship between the two wind and light stations with the spatial correlation coefficient greater than a second correlation threshold, and form a spatial correlation matrix; The prediction module is configured to construct an initial output prediction model including a spatial convolution module and a time attention module, construct an input data set and a result data set, update the initial output prediction model to a final output prediction model based on the input data set, the result data set, the time series length parameter, and the spatial correlation matrix, and obtain historical prediction output data based on the final output prediction model; The prediction module includes: The ninth unit is configured to construct a dynamic correlation matrix in the spatial convolution module based on the input data set and the spatial correlation matrix; The tenth unit is configured to convert the input data set into a stage feature set based on the dynamic correlation matrix, the stage feature set including stage sub-features under a plurality of time series; The eleventh unit is configured to set a split window in the time attention module based on the time series length parameter, input the stage feature set into the time attention module, select a to-be-updated sub-feature from the stage sub-features, select a plurality of reference sub-features from the stage sub-features based on the split window, and generate a final sub-feature corresponding to the to-be-updated sub-feature based on the to-be-updated sub-feature and the plurality of reference sub-features; The twelfth unit is configured to combine a plurality of final sub-features into a prediction output set, construct a loss function based on the prediction output set and the result data set, and update the initial output prediction model to a final output prediction model; The execution module is configured to obtain prediction errors corresponding to the historical prediction output data, obtain real prediction output data based on the final output prediction model, expand the real prediction output data into a real prediction output range based on a plurality of prediction errors, compare real output data with the real prediction output range, and determine whether there is a maintenance requirement.

Images