New energy installation configuration capacity prediction method, system and equipment based on pumped storage power station and medium

Abstract

The invention discloses a new energy installation configuration capacity prediction method, system and device based on a pumped storage power station, and a medium, and relates to the field of new energy consumption capability prediction of the pumped storage power station, and the method comprises the steps: obtaining historical load data and influence factor data of the pumped storage power station in a power grid as target data; and performing abnormal data detection on the target data by adopting a DBSCAN algorithm, removing the abnormal data from the target data to obtain the target data after the abnormal data is removed, preprocessing the target data after the abnormal data is removed, inputting the preprocessed target data into the new energy installation configuration capacity prediction model, and predicting the new energy installation configuration capacity. Outputting a new energy installation configuration capacity prediction value; the prediction precision of the new energy installation configuration capacity can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of predicting the consumption capacity of new energy by pumped-storage power stations, and particularly to a method, system, device and medium for predicting the installed capacity of new energy based on pumped-storage power stations. Background Art

[0002] In recent years, the installed capacity and total consumption of new energy connected to the grid have increased rapidly. With the continuous increase in the grid-connected capacity of new energy, the consumption contradiction has become increasingly prominent, and problems such as wind curtailment and PV curtailment have occurred in some areas.

[0003] China's resource endowment determines that currently new energy is mainly distributed in the "Three-North" regions, while the load centers are in the southeast coastal areas. Taking the northwest as an example, since 2009, the average annual growth rate of new energy installed capacity in the northwest has been 51.16%, while the growth rate of the total electricity consumption of the whole society during the same period has only been 10.47%. The local consumption space of new energy is limited and it seriously relies on external transmission. However, the construction period of the external transmission channels is much longer than that of new energy construction, resulting in the improvement of external transmission capacity not being able to keep up with the growth rate of new energy installed capacity, and new energy curtailment thus occurs. Therefore, the root cause of the new energy curtailment problem is the uncoordinated development of the power source, grid and load caused by the fact that the new energy installation speed far exceeds the load growth rate and the grid construction speed. Therefore, it is very important to predict and reasonably allocate the installed capacity of new energy. However, there are currently problems of low prediction accuracy and poor effect in predicting the installed capacity configuration of new energy. Summary of the Invention

[0004] The purpose of the present application is to provide a method, system, device and medium for predicting the installed capacity of new energy based on pumped-storage power stations to solve the problem of low prediction accuracy of the installed capacity of new energy.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In the first aspect, the present application provides a method for predicting the installed capacity of new energy based on a pumped-storage power station. The method for predicting the installed capacity of new energy based on a pumped-storage power station includes:

[0007] Obtain the historical load data and influencing factor data of the pumped-storage power station in the power grid, and use the historical load data and influencing factor data as target data;

[0008] Adopt the DBSCAN algorithm to detect abnormal data in the target data, obtain the abnormal data, and remove the abnormal data from the target data to obtain the target data after removing the abnormal data;

[0009] Preprocess the target data after removing the abnormal data to obtain the preprocessed target data;

[0010] Input the preprocessed target data into the new energy installed capacity prediction model to output the predicted value of the new energy installed capacity; the new energy installed capacity prediction model is obtained by training an LSTM model using a training set; the training set includes sample historical load data, sample influencing factor data, and new energy installed capacity sample values.

[0011] Optionally, use the DBSCAN algorithm to detect abnormal data in the target data, obtain the abnormal data, and remove the abnormal data from the target data. Specifically, it includes:

[0012] Regard a target data as a sample point. For each sample point, calculate the cohesion and separation degree respectively.

[0013] Based on the cohesion and separation degree, calculate the silhouette coefficient of the sample point.

[0014] Calculate the average silhouette coefficient based on the silhouette coefficients of all sample points.

[0015] For each sample point, determine whether the silhouette coefficient of the current sample point is greater than the average silhouette coefficient.

[0016] If so, determine that the current sample point is normal data.

[0017] If not, determine that the current sample point is abnormal data, and remove the abnormal data to obtain the target data after removing the abnormal data.

[0018] Optionally, the calculation formula for the cohesion is:

[0019]

[0020] The calculation formula for the separation degree is:

[0021]

[0022] The calculation formula for the silhouette coefficient is:

[0023]

[0024] The calculation formula for the average silhouette coefficient is:

[0025]

[0026] Among them, a(i) represents the cohesion of sample point i; C i represents the in-cluster sample points corresponding to the i sample points; both i and j represent the sample point numbers; d(i,j) represents the distance between sample points i and j; b(i) represents the separation degree of sample point i; C kDenote the in - cluster sample points corresponding to k sample points; s(i) represents the silhouette coefficient of sample point i; S represents the average value of the silhouette coefficients of all sample points; C represents the sample points of all clusters; n represents the number of sample points of all clusters.

[0027] Optionally, pre - process the target data after removing abnormal data to obtain the pre - processed target data, specifically including:

[0028] Perform normalization processing on the target data after removing abnormal data to obtain the pre - processed target data.

[0029] Optionally, the LSTM model includes an input layer, a first convolutional layer, a first average pooling layer, a second convolutional layer, a second average pooling layer, a first fully - connected layer, a second fully - connected layer, and a third fully - connected layer connected in sequence.

[0030] Optionally, the training process of the new energy installed capacity prediction model specifically includes:

[0031] Input the sample historical load data and sample influencing factor data into the LSTM model, and output the predicted value of the new energy installed capacity of the sample;

[0032] Construct a loss function based on the predicted value of the new energy installed capacity of the sample and the sample value of the new energy installed capacity, and adjust the network parameters of the LSTM model according to the loss function to obtain the new energy installed capacity prediction model.

[0033] Optionally, after obtaining the new energy installed capacity prediction model, it further includes:

[0034] Obtain test samples and construct a test data set based on the test samples;

[0035] Detect and pre - process abnormal data in the test samples to obtain pre - processed test samples;

[0036] Input the pre - processed test samples into the new energy installed capacity prediction model to obtain the test value of the new energy installed capacity of the sample;

[0037] Calculate the absolute error, root - mean - square error, and correlation coefficient respectively according to the test value of the new energy installed capacity of the sample and the sample value of the new energy installed capacity;

[0038] Evaluate the error accuracy of the new energy installed capacity prediction model according to the absolute error, root - mean - square error, and correlation coefficient.

[0039] Second aspect, the present application provides a new energy installed capacity prediction system for a pumped storage power station. The new energy installed capacity prediction system for the pumped storage power station is based on the new energy installed capacity prediction method for the pumped storage power station, and the new energy installed capacity prediction system for the pumped storage power station includes:

[0040] A target data determination unit, configured to obtain historical load data and influencing factor data of pumped storage in the power grid, and use the historical load data and the influencing factor data as target data;

[0041] An abnormal data detection unit, configured to use the DBSCAN algorithm to detect abnormal data in the target data, obtain the abnormal data, and remove the abnormal data from the target data to obtain the target data after removing the abnormal data;

[0042] A preprocessing unit, configured to preprocess the target data after removing the abnormal data to obtain the preprocessed target data;

[0043] A new energy installed capacity prediction value determination unit, configured to input the preprocessed target data into a new energy installed capacity prediction model, and output a new energy installed capacity prediction value; the new energy installed capacity prediction model is obtained by training an LSTM model using a training set; the training set includes sample historical load data, sample influencing factor data, and new energy installed capacity sample values.

[0044] Third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the new energy installed capacity prediction method for the pumped storage power station described in any one of the above.

[0045] Fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the new energy installed capacity prediction method for the pumped storage power station described in any one of the above are implemented.

[0046] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0047] The present application provides a new energy installed capacity prediction method, system, device, and medium for a pumped storage power station. The new energy installed capacity prediction model is used to predict the new energy installed capacity, improving the prediction accuracy; at the same time, the DBSCAN algorithm is added to remove abnormal data during the processing of the training set, reducing the influence of abnormal data on model training and further improving the prediction accuracy of the model. Description of the Drawings

[0048] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0049] Figure 1 It is an application environment diagram of a new energy installed capacity prediction method based on a pumped-storage power station in an embodiment of the present application;

[0050] Figure 2 It is a schematic flowchart of a new energy installed capacity prediction method based on a pumped-storage power station provided in an embodiment of the present application;

[0051] Figure 3 It is a schematic diagram of the module structure of the LSTM model provided in an embodiment of the present application;

[0052] Figure 4 It is a schematic diagram of the structure of the LSTM model provided in another embodiment of the present application;

[0053] Figure 5 It is a schematic diagram of the functional modules of a new energy installed capacity prediction system based on a pumped-storage power station provided in an embodiment of the present application;

[0054] Figure 6 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application.

[0055] Reference numerals:

[0056] Target data determination unit - 1, abnormal data detection unit - 2, preprocessing unit - 3, new energy installed capacity prediction value determination unit - 4. Detailed implementation manners

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0058] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0059] Pumped storage is the most mature technology currently, with the most significant carbon emission reduction benefits throughout the life cycle, the best economy, and the most favorable conditions for large-scale development. It is an urgent requirement for building a new power system with new energy as the main body. As the highest-quality regulating power source in the power system, the basic, comprehensive, and public characteristics of pumped storage are more prominent in the new power system.

[0060] The new energy installed capacity prediction method based on a pumped storage power station provided by the embodiments of this application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the historical load data and influencing factor data of the pumped storage power station in the power grid to the server 104. After receiving the historical load data and influencing factor data of the pumped storage power station in the power grid, for the historical load data and influencing factor data of the pumped storage power station in the power grid, the server 104 predicts the new energy installed capacity based on the historical load data and influencing factor data of the pumped storage power station in the power grid, and obtains the predicted value of the new energy installed capacity. The server 104 can feedback the obtained predicted value of the new energy installed capacity to the terminal 102. In addition, in some embodiments, the new energy installed capacity prediction method based on a pumped storage power station can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly predict the new energy installed capacity for the historical load data and influencing factor data of the pumped storage power station in the power grid, or the server 104 can obtain the historical load data and influencing factor data of the pumped storage power station in the power grid from the data storage system and predict the new energy installed capacity for the historical load data and influencing factor data of the pumped storage power station in the power grid.

[0061] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smartphones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0062] In an exemplary embodiment, as Figure 2As shown, a method for predicting the installed capacity of new energy based on a pumped-storage power station is provided. This method is executed by a computer device, specifically, it can be executed alone by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of this application, taking this method applied to Figure 1 the server 104 in

[0063] Step S1: Obtain the historical load data and influencing factor data of the pumped-storage power station in the power grid, and use the historical load data and influencing factor data as target data. Among them, the historical load data includes pumped-storage access data; the influencing factor data includes temperature, month, time, rainfall, basin water level, and whether it is a working day, etc.

[0064] Step S2: Use the DBSCAN algorithm to detect abnormal data in the target data, obtain the abnormal data, and remove the abnormal data from the target data to obtain the target data after removing the abnormal data.

[0065] In an exemplary embodiment, step S2 specifically includes:

[0066] Step S21: Regard a target data as a sample point. For each sample point, calculate the cohesion degree and the separation degree respectively. Among them, the calculation formula for the cohesion degree is:

[0067]

[0068] The calculation formula for the separation degree is:

[0069]

[0070] Step S22: Calculate the silhouette coefficient of the sample point based on the cohesion degree and the separation degree; the calculation formula for the silhouette coefficient is:

[0071]

[0072] Step S23: Calculate the average silhouette coefficient based on the silhouette coefficients of all sample points; the calculation formula for the average silhouette coefficient is:

[0073]

[0074] Among them, a(i) represents the cohesion degree of sample point i, which is the average distance from sample point i to the other points within the cluster; C i represents the sample points within the cluster corresponding to the i-th sample point; both i and j represent the sample point numbers; d(i,j) represents the distance between sample point i and j; b(i) represents the separation degree of sample point i, which is the minimum value of the average distance from sample point i to the sample points within other clusters; C krepresents the sample points in the cluster corresponding to k sample points; s(i) represents the silhouette coefficient of sample point i; S represents the average of the silhouette coefficients of all sample points; C represents the sample points of all clusters; n represents the number of sample points in all clusters.

[0075] Step S24: for each sample point, determine whether the silhouette coefficient of the current sample point is greater than the average silhouette coefficient.

[0076] Step S25: If yes, the current sample point is determined to be normal data.

[0077] Step S26: if not, determine that the current sample point is abnormal data, and remove the abnormal data to obtain the target data after removing the abnormal data.

[0078] In order to select the most reasonable parameters, the cohesion, separation and silhouette coefficient are optimized through iteration, and various parameter combinations are modeled separately. The silhouette coefficients of various models are calculated to judge the effect of the abnormal data detection model.

[0079] Step S3, preprocessing the target data after removing the abnormal data to obtain preprocessed target data.

[0080] Since the target data contains data of different dimensions such as power grid composition, technological development factors and other related influencing factors, if no preprocessing is performed, the influence of parameters of some factors will be ignored, which will also affect the model prediction efficiency. In an exemplary embodiment, the above step S3 specifically includes:

[0081] The target data after removing abnormal data is normalized to obtain preprocessed target data.

[0082] Step S4, input the preprocessed target data into the new energy installed capacity configuration capacity prediction model, and output the new energy installed capacity configuration capacity prediction value; the new energy installed capacity configuration capacity prediction model is obtained by training the LSTM model using a training set; the training set includes sample historical load data, sample influencing factor data and new energy installed capacity configuration capacity sample value.

[0083] In an exemplary embodiment, the training process of the new energy installed capacity prediction model specifically includes:

[0084] Step S41, input the sample historical load data and the sample influencing factor data into the LSTM model, and output the sample new energy installed capacity prediction value.

[0085] Step S42: Construct a loss function based on the predicted value of the sample new energy installed capacity configuration and the sample value of the new energy installed capacity configuration, and adjust the network parameters of the LSTM model according to the loss function to obtain a new energy installed capacity prediction model.

[0086] In an exemplary embodiment, as Figure 3 shown, the LSTM model includes an input layer, a first convolutional layer, a first average pooling layer, a second convolutional layer, a second average pooling layer, a first fully connected layer, a second fully connected layer, and a third fully connected layer connected in sequence. As Figure 4 shown, the memory module of the LSTM network includes a forget gate, an input gate, and an output gate; the input x t in the forget gate, together with the state memory module S t-1 and the intermediate output h t-1 , jointly determine the forgotten part of the state memory module; in the input gate, x t is respectively processed by the sigmoid function and the tanh function and then jointly calculates the retention vector in the memory module; h t is jointly determined by the updated S t and o t ; its corresponding calculation process is shown in Equations (5) to (10):

[0087] f t =σ(W fx ·x t +W fh h t-1 +b f ) (5)

[0088] i t =σ(W ix· x t +W ih· h t-1 +b i ) (6)

[0089] g t =tanh(W gx· x t +W gh· h t-1 +b g ) (7)

[0090] o t =σ(W ox· x t +W oh· h t-1 +b o ) (8)

[0091] S t =g t ⊙it +S t-1 ⊙f t-1 (9)

[0092] h t =tanh(S t )⊙o t (10)

[0093] Among them, f t represents the output of the forget gate; σ is the Sigmoid function; W fx represents the weight vector corresponding to x t in the forget gate; x t represents the input of the forget gate; W fh represents the weight vector corresponding to h t-1 in the forget gate; h t-1 represents the hidden state at the previous time step; b f represents the bias vector of the forget gate; i t represents the sigmoid gating signal of the input gate; W ix represents the weight vector corresponding to x t in the input gate; W ih represents the weight vector corresponding to h t-1 in the input gate; b i represents the bias vector of the input gate; g t represents the candidate memory cell state; tanh is the hyperbolic tangent function; W gx represents the weight vector corresponding to x t in the candidate memory; W gh represents the weight vector corresponding to h t-1 in the candidate memory; b g represents the bias parameter of the candidate memory; o t represents the sigmoid gating signal of the output gate; W ox represents the weight vector corresponding to x t in the output gate; W oh represents the weight vector corresponding to h t-1 in the output gate; b o represents the bias vector of the output gate; S t represents the memory cell; S t-1 represents the past memory cell; f t-1 represents the output of the forget gate at the previous time step; h t represents the hidden state; ⊙ represents element-wise multiplication of vectors.

[0094] In addition, before step S41, it also includes normalizing the sample historical load data and sample influencing factor data, and the formula for normalization is as follows:

[0095]

[0096] Wherein, y t ′ est_i is the historical load data and sample influencing factor data of the i-th preprocessed sample; y test_i is the historical load data and sample influencing factor data of the i-th sample; y test_max , y test_min are the maximum and minimum values of the historical load data or sample influencing factor data of the samples in the training set.

[0097] Through normalization processing, the convergence speed of the algorithm is improved, and the training efficiency of the model is increased.

[0098] In an exemplary embodiment, in order to evaluate the error accuracy of the new energy installed capacity prediction model using the test data set and test the prediction ability of the new energy installed capacity prediction model, after obtaining the new energy installed capacity prediction model, it further includes:

[0099] Obtain test samples and construct a test data set X test .

[0100] Perform abnormal data detection and preprocessing on the test samples to obtain preprocessed test samples.

[0101] Input the preprocessed test samples into the new energy installed capacity prediction model to obtain the test values of the sample new energy installed capacity, and perform anti-normalization to obtain the anti-normalized test values of the sample new energy installed capacity Y test_pre .

[0102] Calculate the absolute error, root mean square error and correlation coefficient according to the test values of the sample new energy installed capacity and the sample values of the new energy installed capacity Y test respectively. Among them,

[0103] The calculation formula of the absolute error MAE is as follows:

[0104]

[0105] The calculation formula of the root mean square error RMSE is as follows:

[0106]

[0107] The correlation coefficient R 2 The calculation formula is as follows:

[0108]

[0109] Wherein, m represents the number of test samples; represents the q-th sample value of the new energy installed capacity; represents the qth anti-normalized sample new energy installed capacity test value; Represents the mean of q new energy installed capacity sample values.

[0110] The error accuracy of the new energy installed capacity prediction model is evaluated based on absolute error, root mean square error and correlation coefficient.

[0111] Based on the same inventive concept, the embodiment of the present application also provides a system for predicting the installed capacity of new energy in a pumped-storage power station for realizing the method for predicting the installed capacity of new energy in a pumped-storage power station involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the system for predicting the installed capacity of new energy in a pumped-storage power station provided below can refer to the limitations of the method for predicting the installed capacity of new energy in a pumped-storage power station above, and will not be repeated here.

[0112] In an exemplary embodiment, Figure 5 As shown, a new energy installed capacity prediction system for a pumped storage power station is provided, comprising: a target data determination unit 1, an abnormal data detection unit 2, a preprocessing unit 3 and a new energy installed capacity prediction value determination unit 4.

[0113] The target data determination unit 1 is used to obtain historical load data and influencing factor data of pumped storage in the power grid, and use the historical load data and influencing factor data as target data.

[0114] The abnormal data detection unit 2 is used to perform abnormal data detection on the target data using the DBSCAN algorithm to obtain abnormal data, and remove the abnormal data from the target data to obtain the target data after the abnormal data is removed.

[0115] The preprocessing unit 3 is used to preprocess the target data after the abnormal data is removed to obtain the preprocessed target data.

[0116] The new energy installed capacity prediction value determination unit 4 is used to input the preprocessed target data into the new energy installed capacity prediction model and output the new energy installed capacity prediction value; the new energy installed capacity prediction model is obtained by training the LSTM model using a training set; the training set includes sample historical load data, sample influencing factor data and new energy installed capacity sample value.

[0117] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the predicted values of the new energy installed capacity configuration. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for predicting the new energy installed capacity configuration of a pumped-storage power station.

[0118] Those skilled in the art can understand that Figure 6 The structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0119] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0121] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0122] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0123] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0124] In this article, specific examples are used to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for predicting the installed capacity of new energy based on a pumped storage power station, characterized in that: The method for predicting the installed capacity of new energy based on pumped storage power station includes: Obtain historical load data and influencing factor data of pumped storage power stations in the power grid, and use the historical load data and influencing factor data as target data; The DBSCAN algorithm is used to detect abnormal data on the target data to obtain abnormal data, and the abnormal data is removed from the target data to obtain the target data after the abnormal data is removed; Preprocessing the target data after removing abnormal data to obtain preprocessed target data; The preprocessed target data is input into the new energy installed capacity configuration capacity prediction model, and the new energy installed capacity configuration capacity prediction value is output; the new energy installed capacity configuration capacity prediction model is obtained by training the LSTM model with a training set; the training set includes sample historical load data, sample influencing factor data and new energy installed capacity configuration capacity sample value.

2. The method for predicting the installed capacity of new energy based on a pumped storage power station according to claim 1 is characterized in that: The DBSCAN algorithm is used to detect abnormal data on the target data to obtain abnormal data, and the abnormal data is removed from the target data to obtain the target data after the abnormal data is removed, specifically including: Consider a target data as a sample point, and calculate the cohesion and separation for each sample point; Based on the cohesion and separation, the silhouette coefficient of the sample points is calculated; Calculate the average value of the silhouette coefficient based on the silhouette coefficients of all sample points; For each sample point, determine whether the silhouette coefficient of the current sample point is greater than the average silhouette coefficient; If yes, the current sample point is determined to be normal data; If not, the current sample point is determined to be abnormal data, and the abnormal data is removed to obtain the target data after the abnormal data is removed.

3. The method for predicting the installed capacity of new energy based on a pumped storage power station according to claim 2 is characterized in that: The calculation formula of cohesion is: The calculation formula of separation degree is: The calculation formula of silhouette coefficient is: The calculation formula for the mean value of the silhouette coefficient is: Where a(i) represents the cohesion of sample point i; C i represents the sample point in the cluster corresponding to the i sample point; i and j both represent the sample point serial number; d(i,j) represents the distance between sample points i and j; b(i) represents the separation degree of sample point i; C k represents the sample points in the cluster corresponding to k sample points; s(i) represents the silhouette coefficient of sample point i; S represents the average of the silhouette coefficients of all sample points; C represents the sample points of all clusters; n represents the number of sample points in all clusters.

4. The method for predicting the installed capacity of new energy based on a pumped storage power station according to claim 1, characterized in that: The target data after removing abnormal data is preprocessed to obtain preprocessed target data, which specifically includes: The target data after removing abnormal data is normalized to obtain preprocessed target data.

5. The method for predicting the installed capacity of new energy based on a pumped storage power station according to claim 1, characterized in that: The LSTM model includes an input layer, a first convolutional layer, a first average pooling layer, a second convolutional layer, a second average pooling layer, a first fully connected layer, a second fully connected layer and a third fully connected layer, which are connected in sequence.

6. The method for predicting the installed capacity of new energy based on a pumped storage power station according to claim 1, characterized in that: The training process of the new energy installed capacity prediction model specifically includes: Input the sample historical load data and sample influencing factor data into the LSTM model, and output the predicted value of the sample new energy installed capacity configuration; A loss function is constructed according to the sample new energy installed capacity prediction value and the new energy installed capacity sample value, and the network parameters of the LSTM model are adjusted according to the loss function to obtain the new energy installed capacity prediction model.

7. The method for predicting the installed capacity of new energy based on a pumped storage power station according to claim 6 is characterized in that: After obtaining the new energy installed capacity prediction model, it also includes: Obtain test samples and build a test data set based on the test samples; Perform abnormal data detection and preprocessing on the test sample to obtain a preprocessed test sample; Input the preprocessed test sample into the new energy installed capacity prediction model to obtain the sample new energy installed capacity test value; According to the sample new energy installed capacity test value and the new energy installed capacity sample value, the absolute error, the root mean square error and the correlation coefficient are calculated respectively; The error accuracy of the new energy installed capacity prediction model is evaluated based on absolute error, root mean square error and correlation coefficient.

8. A new energy installed capacity prediction system for a pumped storage power station, characterized in that: The new energy installed capacity prediction system of the pumped storage power station is based on the new energy installed capacity prediction method based on the pumped storage power station according to any one of claims 1 to 7, and the new energy installed capacity prediction system of the pumped storage power station comprises: A target data determination unit, used to obtain historical load data and influencing factor data of pumped storage in the power grid, and use the historical load data and influencing factor data as target data; An abnormal data detection unit is used to perform abnormal data detection on the target data using the DBSCAN algorithm to obtain abnormal data, and remove the abnormal data from the target data to obtain the target data after removing the abnormal data; A preprocessing unit, used for preprocessing the target data after removing the abnormal data, to obtain the preprocessed target data; The new energy installed capacity configuration prediction value determination unit is used to input the preprocessed target data into the new energy installed capacity configuration prediction model, and output the new energy installed capacity configuration prediction value; the new energy installed capacity configuration prediction model is obtained by training the LSTM model with a training set; the training set includes sample historical load data, sample influencing factor data and new energy installed capacity configuration sample value.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for predicting the installed capacity of new energy based on a pumped-storage power station as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the installed capacity of new energy based on a pumped storage power station as described in any one of claims 1 to 7 is implemented.

Images