Photovoltaic power generation power prediction method and device
Through technical means such as entropy weight method and non-negative matrix decomposition, the weight information and target parameters of photovoltaic power generation prediction are determined, and the support vector machine model is used to predict, which solves the problem of large cluster power prediction error in the existing technology and improves the prediction accuracy.
Patent Information
- Application Number
- CN202411424614.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-09-30
- Filing Date
- 2024-10-12
- Publication Date
- 2025-02-07
AI Technical Summary
In the prior art, the power grid dispatching department has caused large cluster power prediction errors through the method of simply accumulating power prediction of power plants, and the prediction modes of different power plants are inconsistent, which increases the error of cluster power prediction.
Use the entropy weight method to obtain the initial data, determine the weight information of the day to be tested and the historical day, determine the similar day from the historical day based on these weight information, obtain the sample data of the similar day, and determine the target through non-negative matrix decomposition and grid search method. Parameters, and finally predict photovoltaic power generation power based on the support vector machine model.
This method can improve the accuracy of photovoltaic power generation prediction, reduce errors, and adapt to the prediction modes of different power stations.
Smart Images
Figure CN119401391A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a photovoltaic power generation power prediction method. Background Art
[0002] At present, the power grid dispatching department requires power stations (including wind power and photovoltaic power) to report power forecasts, including short-term and ultra-short-term power forecasts, for system power generation planning and real-time dispatching of power systems. At present, the power grid dispatching produces cluster output forecast services by simply adding up the predicted power of power stations. There are certain errors in the power forecast of power stations. Different power stations have different prediction modes, and all operating data of all power stations are required, which increases the error of cluster power forecast.
[0003] Therefore, a better solution is urgently needed. Summary of the invention
[0004] In view of this, the present invention provides a photovoltaic power generation power prediction method to solve the technical defects existing in the prior art.
[0005] According to a first aspect of the present invention, there is provided a photovoltaic power prediction method, comprising:
[0006] Obtain initial data, and determine the weight information of the test day and historical days based on the entropy weight method and the initial data;
[0007] Determine similar days from historical days based on weight information;
[0008] Obtain sample data of similar days and determine target parameters based on the sample data;
[0009] A target model is determined based on the target parameters, and a photovoltaic power generation power prediction result is determined based on the sample data and the target model.
[0010] In a possible implementation, initial data is obtained, and weight information of the test day and the historical day is determined based on the entropy weight method and the initial data, including:
[0011] Obtain initial data, preprocess the data based on preprocessing rules, and obtain target data;
[0012] The weight information of the test day and historical days is determined based on the entropy weight method and target data.
[0013] In a possible implementation, determining similar days from historical days based on weight information includes:
[0014] A weight threshold is determined, and based on the weight information and the weight threshold, a similar day corresponding to the day to be tested is determined from historical days.
[0015] In a possible implementation, obtaining sample data of similar days and determining target parameters based on the sample data include:
[0016] Obtain sample data of similar days, decompose the sample data using a non-negative matrix factorization algorithm, and determine a low-dimensional matrix;
[0017] The target parameters are determined by grid search method based on low-dimensional matrix.
[0018] In a possible implementation, determining a photovoltaic power generation power prediction result based on sample data and a target model includes:
[0019] The sample data is input into the target model to obtain the photovoltaic power generation power prediction result; wherein the target model is the SVM model.
[0020] In a possible implementation, the weight information of the test day and the historical day is determined based on the entropy weight method and the target data, including:
[0021] Determine at least two sub-feature vectors based on the target data;
[0022] Normalizing at least two sub-feature vectors to determine a comparison vector;
[0023] Based on the comparison vector of the day to be tested and the comparison vector of the historical days, the weight information of the day to be tested and the historical days is determined.
[0024] In a possible implementation manner, the weight information includes a weighted Euclidean distance.
[0025] According to a second aspect of the present invention, there is provided a photovoltaic power generation power prediction device, comprising:
[0026] A weight determination module is configured to obtain initial data and determine weight information of the test day and the historical day based on the entropy weight method and the initial data;
[0027] a data determination module configured to determine similar days from historical days based on weight information;
[0028] a parameter determination module configured to obtain sample data of similar days and determine target parameters based on the sample data;
[0029] The power prediction module is configured to determine a target model based on the target parameters, and to determine a photovoltaic power generation power prediction result based on the sample data and the target model.
[0030] According to a third aspect of the present invention, there is provided a computing device, comprising:
[0031] Memory and processor;
[0032] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned photovoltaic power generation prediction method are implemented.
[0033] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned photovoltaic power generation prediction method.
[0034] According to a fifth aspect of the present invention, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned photovoltaic power generation power prediction method.
[0035] The present invention provides a photovoltaic power generation prediction method and device, wherein the photovoltaic power generation prediction method includes: obtaining initial data, determining weight information of a test day and a historical day based on an entropy weight method and the initial data; determining similar days from historical days based on the weight information; obtaining sample data of similar days, and determining target parameters based on the sample data; determining a target model based on the target parameters, and determining a photovoltaic power generation prediction result based on the sample data and the target model. By obtaining initial data, determining weight information of a test day and a historical day based on an entropy weight method and the initial data; determining similar days from historical days based on the weight information; obtaining sample data of similar days, and determining target parameters based on the sample data; determining a target model based on the target parameters, and determining a photovoltaic power generation prediction result based on the sample data and the target model, the accuracy of photovoltaic prediction can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 This is a schematic diagram of a scenario of a photovoltaic power generation power prediction method provided by an embodiment of this specification;
[0037] Figure 2 is a flow chart of a photovoltaic power generation power prediction method provided by an embodiment of this specification;
[0038] Figure 3 It is a structural schematic diagram of a photovoltaic power generation prediction device provided by an embodiment of this specification;
[0039] Figure 4 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION
[0040] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.
[0041] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.
[0042] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0043] In this specification, a photovoltaic power generation power prediction method is provided. This specification also relates to a photovoltaic power generation power prediction device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.
[0044] See also Figure 1 , Figure 1 A schematic diagram of a scenario of a photovoltaic power generation prediction method provided according to an embodiment of the present specification is shown.
[0045] exist Figure 1 In the application scenario, the computing device 101 can obtain initial data, and determine weight information 102 of the test day and the historical day based on the entropy weight method and the initial data. Then, the computing device 101 can determine a similar day 103 from the historical day based on the weight information 102. After that, the computing device 101 can obtain sample data of the similar day 103, and determine a target parameter 104 based on the sample data. Finally, the computing device 101 can determine a target model based on the target parameter 104, and determine a photovoltaic power generation power prediction result based on the sample data and the target model, as shown in the reference numeral 105.
[0046] It should be noted that the computing device 101 can be hardware or software. When the computing device 101 is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device 101 is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.
[0047] See also Figure 2 , Figure 2 A flow chart of a photovoltaic power generation prediction method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.
[0048] Step 201: Obtain initial data, and determine weight information of the test day and historical days based on the entropy weight method and the initial data.
[0049] In one possible implementation, initial data is obtained, and weight information of the day to be measured and historical days is determined based on the entropy weight method and the initial data, including: obtaining initial data, preprocessing the data based on preprocessing rules to obtain target data; and determining weight information of the day to be measured and historical days based on the entropy weight method and the target data.
[0050] The weight information includes the weighted Euclidean distance, and the weight information may also be other correlation calculation methods, which are not limited in this solution.
[0051] In practical applications, since photovoltaic power generation has obvious daily variation periodicity, similar days are selected by calculating the correlation of daily feature vectors.
[0052] In one possible implementation, weight information of the day to be measured and historical days is determined based on the entropy weight method and target data, including: determining at least two sub-feature vectors based on the target data; normalizing at least two sub-feature vectors to determine a comparison vector; and determining weight information of the day to be measured and historical days based on the comparison vector of the day to be measured and the comparison vector of historical days.
[0053] In practical applications, historical days close to the test date and with the same weather type are selected as training samples, and the characteristic vector of daily meteorological parameters is set to be X = [T max, t max ,T min ,t min, T aver ,RH], where T max , T min , T aver are the highest temperature, the lowest temperature, and the average temperature respectively; t max ,t minare the times when the highest temperature and the lowest temperature occur respectively; RH is the relative humidity. The eigenvector is normalized and the eigenvector of the meteorological parameters of the i-th historical day after the processing is recorded as X i =[x i (1),x i (2),…,x i (m)]T, then the characteristic vector of the meteorological parameters of the day to be measured is X0=[x0(1),x0(2),…,x0(m)]T, and the weighted Euclidean distance between the characteristic vector of the meteorological parameters of the i-th historical day and the day to be measured is calculated.
[0054] Step 202: Determine similar days from historical days based on weight information.
[0055] In a possible implementation, determining similar days from historical days based on weight information includes: determining a weight threshold, and determining similar days corresponding to the to-be-tested day from historical days based on the weight information and the weight threshold.
[0056] In practical applications, a correlation threshold may be set. If the correlation between the weight information corresponding to the day to be tested and the weight information of the historical day exceeds the correlation threshold, the historical day is determined as a similar day.
[0057] Step 203: Obtain sample data of similar days, and determine target parameters based on the sample data.
[0058] It should be noted that the training samples may also include photovoltaic power, that is, the photovoltaic power on similar days is input as training samples into the subsequent model for prediction.
[0059] In one possible implementation, sample data of similar days is obtained, and target parameters are determined based on the sample data, including: obtaining sample data of similar days, decomposing the sample data using a non-negative matrix decomposition algorithm to determine a low-dimensional matrix; and determining the target parameters based on the low-dimensional matrix using a grid search method.
[0060] In practical applications, the selected similar dates are input into the support vector machine model as training samples, combined with the modeling algorithm's fast parameter adaptation method, that is, the sample data is decomposed through the non-negative matrix decomposition algorithm to determine the low-dimensional matrix; based on the low-dimensional matrix, the target parameters are determined through the grid search method to determine better parameters.
[0061] Furthermore, the parameters may be optimized by the k-cv method, or by the grid search method and the k-cv method, which is not limited in this solution.
[0062] Step 204: determining a target model based on the target parameters, and determining a photovoltaic power generation power prediction result based on the sample data and the target model.
[0063] In a possible implementation, determining a photovoltaic power generation prediction result based on sample data and a target model includes: inputting the sample data into the target model to obtain a photovoltaic power generation prediction result; wherein the target model is a SVM model.
[0064] Among them, the SVM model is the vector machine model.
[0065] In practical applications, after the vector machine model is established based on the above target parameters, the predicted power values of all photovoltaic power generation predictions can be obtained through the vector machine model.
[0066] The embodiments of this specification provide a photovoltaic power generation prediction method and device, wherein the photovoltaic power generation prediction method includes: obtaining initial data, determining weight information of the day to be measured and the historical day based on the entropy weight method and the initial data; determining similar days from the historical days based on the weight information; obtaining sample data of similar days, and determining target parameters based on the sample data; determining a target model based on the target parameters, and determining photovoltaic power generation prediction results based on the sample data and the target model. The accuracy of photovoltaic prediction can be improved by obtaining initial data, determining weight information of the day to be measured and the historical day based on the entropy weight method and the initial data; determining similar days from the historical days based on the weight information; obtaining sample data of similar days, and determining target parameters based on the sample data; determining a target model based on the target parameters, and determining photovoltaic power generation prediction results based on the sample data and the target model.
[0067] Corresponding to the above method embodiment, this specification also provides a photovoltaic power generation power prediction device embodiment, Figure 3 FIG. 2 shows a schematic diagram of a photovoltaic power generation prediction device provided by an embodiment of the present specification. Figure 3 As shown, the device comprises:
[0068] The weight determination module 301 is configured to obtain initial data and determine the weight information of the test day and the historical day based on the entropy weight method and the initial data;
[0069] A data determination module 302 is configured to determine similar days from historical days based on weight information;
[0070] The parameter determination module 303 is configured to obtain sample data of similar days and determine the target parameters based on the sample data;
[0071] The power prediction module 304 is configured to determine a target model based on the target parameters, and determine a photovoltaic power prediction result based on the sample data and the target model.
[0072] In a possible implementation, the weight determination module 301 is further configured to:
[0073] Obtain initial data, preprocess the data based on preprocessing rules, and obtain target data;
[0074] The weight information of the test day and historical days is determined based on the entropy weight method and target data.
[0075] In a possible implementation, the data determination module 302 is further configured to:
[0076] A weight threshold is determined, and based on the weight information and the weight threshold, a similar day corresponding to the day to be tested is determined from historical days.
[0077] In a possible implementation, the parameter determination module 303 is further configured to:
[0078] Obtain sample data of similar days, decompose the sample data using a non-negative matrix factorization algorithm, and determine a low-dimensional matrix;
[0079] The target parameters are determined by grid search method based on low-dimensional matrix.
[0080] In a possible implementation, the power prediction module 304 is further configured to:
[0081] The sample data is input into the target model to obtain the photovoltaic power generation power prediction result; wherein the target model is the SVM model.
[0082] In a possible implementation, the weight determination module 301 is further configured to:
[0083] Determine at least two sub-feature vectors based on the target data;
[0084] Normalizing at least two sub-feature vectors to determine a comparison vector;
[0085] Based on the comparison vector of the day to be tested and the comparison vector of the historical days, the weight information of the day to be tested and the historical days is determined.
[0086] In a possible implementation, the weight determination module 301 is further configured to:
[0087] The weight information includes the weighted Euclidean distance.
[0088] The embodiments of this specification provide a photovoltaic power generation prediction method and device, wherein the photovoltaic power generation prediction device includes: obtaining initial data, determining weight information of the day to be measured and the historical day based on the entropy weight method and the initial data; determining similar days from the historical days based on the weight information; obtaining sample data of similar days, and determining target parameters based on the sample data; determining a target model based on the target parameters, and determining photovoltaic power generation prediction results based on the sample data and the target model. The accuracy of photovoltaic prediction can be improved by obtaining initial data, determining weight information of the day to be measured and the historical day based on the entropy weight method and the initial data; determining similar days from the historical days based on the weight information; obtaining sample data of similar days, and determining target parameters based on the sample data; determining a target model based on the target parameters, and determining photovoltaic power generation prediction results based on the sample data and the target model.
[0089] The above is a schematic scheme of a photovoltaic power prediction device of this embodiment. It should be noted that the technical scheme of the photovoltaic power prediction device and the technical scheme of the photovoltaic power prediction method mentioned above belong to the same concept, and the details not described in detail in the technical scheme of the photovoltaic power prediction device can be found in the description of the technical scheme of the photovoltaic power prediction method mentioned above.
[0090] Figure 4 The block diagram of a computing device 400 according to one embodiment of the present specification is shown. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.
[0091] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).
[0092] In one embodiment of the present specification, the above components of the computing device 400 and Figure 4 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 4 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.
[0093] The computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 400 may also be a mobile or stationary server.
[0094] Among them, the processor 420 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned photovoltaic power generation prediction method. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned photovoltaic power generation prediction method belong to the same concept. The details of the technical scheme of the computing device that are not described in detail can be found in the description of the technical scheme of the above-mentioned photovoltaic power generation prediction method.
[0095] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned photovoltaic power generation prediction method.
[0096] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the photovoltaic power generation prediction method mentioned above belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the photovoltaic power generation prediction method mentioned above.
[0097] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned photovoltaic power generation prediction method.
[0098] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the photovoltaic power prediction method mentioned above are of the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the photovoltaic power prediction method mentioned above.
[0099] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0100] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0101] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.
[0102] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0103] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.
Claims
1. A photovoltaic power generation power prediction method, characterized in that: include: Acquire initial data, and determine weight information of the test day and historical days based on the entropy weight method and the initial data; determining similar days from the historical days based on the weight information; Acquire sample data of the similar day, and determine target parameters based on the sample data; A target model is determined based on the target parameters, and a photovoltaic power generation power prediction result is determined based on the sample data and the target model.
2. The method according to claim 1, characterized in that The obtaining of initial data and determining weight information of the test day and the historical day based on the entropy weight method and the initial data include: Acquire initial data, and preprocess the data based on a preprocessing rule to obtain target data; The weight information of the day to be measured and the historical days is determined based on the entropy weight method and the target data.
3. The method according to claim 1, characterized in that The determining of similar days from the historical days based on the weight information includes: A weight threshold is determined, and based on the weight information and the weight threshold, a similar day corresponding to the day to be measured is determined from the historical days.
4. The method according to claim 1, characterized in that: The acquiring the sample data of the similar day and determining the target parameter based on the sample data includes: Obtaining sample data of the similar days, and decomposing the sample data using a non-negative matrix decomposition algorithm to determine a low-dimensional matrix; The target parameters are determined by a grid search method based on the low-dimensional matrix.
5. The method according to claim 1, characterized in that The step of determining the photovoltaic power generation power prediction result based on the sample data and the target model includes: The sample data is input into the target model to obtain a photovoltaic power generation power prediction result; wherein the target model is a SVM model.
6. The method according to claim 2, characterized in that The method of determining the weight information of the test day and the historical day based on the entropy weight method and the target data includes: Determine at least two sub-feature vectors based on the target data; Normalizing the at least two sub-feature vectors to determine a comparison vector; Based on the comparison vector of the day to be measured and the comparison vector of the historical day, weight information of the day to be measured and the historical day is determined.
7. The method according to claim 1, characterized in that The weight information includes a weighted Euclidean distance.
8. A photovoltaic power generation power prediction device, characterized in that: include: A weight determination module is configured to obtain initial data and determine weight information of the test day and the historical day based on an entropy weight method and the initial data; a data determination module configured to determine similar days from the historical days based on the weight information; a parameter determination module, configured to obtain sample data of the similar day and determine a target parameter based on the sample data; The power prediction module is configured to determine a target model based on the target parameters, and to determine a photovoltaic power generation power prediction result based on the sample data and the target model.
9. A computing device, characterized in that include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the photovoltaic power generation prediction method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the photovoltaic power generation prediction method according to any one of claims 1 to 7.