Photovoltaic power generation power prediction method, device, equipment, medium and product

Abstract

The application relates to the technical field of power grids and discloses a power prediction method, device, equipment, medium and product for photovoltaic power generation. The method comprises the following steps: acquiring a multimodal historical data set corresponding to a photovoltaic station, adopting a multivariate variational modal decomposition method to perform modal decomposition on the multimodal historical data set, and acquiring a plurality of first modal components; acquiring modal prediction results corresponding to the plurality of first modal components according to the plurality of first modal components through a kernel extreme learning machine prediction model optimized by a multi-target white shark optimization algorithm; finding prediction weight values corresponding to the plurality of first modal components, and acquiring a power prediction result corresponding to the photovoltaic station according to the modal prediction results corresponding to the plurality of first modal components and the prediction weight values. The scheme of the embodiment can realize multimodal data feature mining and efficient prediction of the photovoltaic station, and can improve the accuracy of power prediction for photovoltaic power generation.

Description

Technical Field

[0001] This invention relates to the field of power grid technology, and in particular to a method, apparatus, equipment, medium, and product for predicting the power of photovoltaic power generation. Background Technology

[0002] In recent years, the photovoltaic industry has maintained a rapid development trend, and the large-scale, high-proportion integration of new energy sources into the grid has significantly increased the pressure on system operation and power consumption. Compared with traditional energy sources, photovoltaic power generation is more affected by geographical location, environmental climate, and hardware configuration, exhibiting volatility and intermittency, which brings instability problems to the large-scale grid integration of photovoltaic power generation.

[0003] Accurate photovoltaic power forecasting is key to solving the above problems. Currently, existing photovoltaic power forecasting methods are usually based on meteorological data provided by simple weather forecasts for model training and prediction, failing to consider the influence of different modal components in the prediction process. This results in the prediction results failing to accurately reflect the fluctuation of photovoltaic power, leading to poor accuracy in photovoltaic power forecasting. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for predicting the power of photovoltaic power generation, which can improve the accuracy of photovoltaic power generation power prediction.

[0005] According to one aspect of the present invention, a method for predicting the power of photovoltaic power generation is provided, comprising:

[0006] A multimodal historical dataset corresponding to a photovoltaic power station is obtained, and the multivariate variational mode decomposition method is used to perform mode decomposition on the multimodal historical dataset to obtain multiple first mode components;

[0007] The kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm obtains the mode prediction result corresponding to each of the multiple first mode components based on the multiple first mode components.

[0008] Find the prediction weight value corresponding to each of the first mode components, and obtain the power generation prediction result corresponding to the photovoltaic power station based on the mode prediction result and prediction weight value corresponding to each of the first mode components.

[0009] According to another aspect of the present invention, a power prediction device for photovoltaic power generation is provided, comprising:

[0010] The mode decomposition module is used to obtain the multimodal historical dataset corresponding to the photovoltaic power station, and to perform mode decomposition on the multimodal historical dataset using the multivariate variational mode decomposition method to obtain multiple first mode components;

[0011] The modal prediction result acquisition module is used to acquire the modal prediction result corresponding to each of the multiple first modal components based on the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm.

[0012] The power generation prediction module is used to find the prediction weight value corresponding to each of the first mode components, and obtain the power generation prediction result corresponding to the photovoltaic power station based on the mode prediction result and prediction weight value corresponding to each of the first mode components.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the photovoltaic power generation prediction method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program configured to cause a processor to execute and implement the power prediction method for photovoltaic power generation according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the photovoltaic power generation prediction method according to any embodiment of the present invention.

[0019] The technical solution of this invention involves acquiring a multimodal historical dataset corresponding to a photovoltaic power station, and performing modal decomposition on the multimodal historical dataset using a multivariate variational mode decomposition method to obtain multiple first modal components. A kernel extreme learning machine prediction model optimized by a multi-objective white shark optimization algorithm is used to obtain the modal prediction result corresponding to each first modal component. The prediction weight value corresponding to each first modal component is found, and the power generation prediction result corresponding to the photovoltaic power station is obtained based on the modal prediction result and prediction weight value. By optimizing the kernel extreme learning machine prediction model using the multi-objective white shark optimization algorithm to predict different modal components, and obtaining the final power generation prediction result based on the modal prediction result and prediction weight value corresponding to different modal components, the invention achieves multimodal data feature mining and efficient prediction of photovoltaic power stations, thereby improving the accuracy of photovoltaic power generation prediction.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a photovoltaic power generation power prediction method provided according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a schematic diagram of a model optimization process provided in Embodiment 1 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a photovoltaic power generation prediction device according to Embodiment 2 of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the power prediction method for photovoltaic power generation according to an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 This is a flowchart illustrating a photovoltaic power generation prediction method according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the power generation of photovoltaic power plants needs to be predicted. This method can be executed by a photovoltaic power generation prediction device, which can be implemented in hardware and / or software. Typically, the photovoltaic power generation prediction device can be configured in electronic equipment, such as computer equipment or a server. Figure 1 As shown, the method includes:

[0030] S110. Obtain the multimodal historical dataset corresponding to the photovoltaic power station, and use the multivariate variational mode decomposition method to perform mode decomposition on the multimodal historical dataset to obtain multiple first mode components.

[0031] The multimodal historical dataset can include historical power generation data, historical ledger data, and historical weather data. Historical weather data can be meteorological data provided by weather forecasts at historical moments, such as temperature, wind speed, humidity, and cloud cover. In this embodiment, various historical data from distributed photovoltaic power plants can be collected, and a multimodal historical dataset can be constructed using different photovoltaic power plants as labels.

[0032] Optionally, after collecting various historical data from the photovoltaic power station, the collected data can be preprocessed. Typically, preprocessing may include removing invalid and outlier data, supplementing missing data, and standardizing the data. Then, a multimodal historical dataset can be generated based on the preprocessed collected data.

[0033] In this embodiment, after obtaining the multimodal historical dataset, the multivariate variational mode decomposition (MVMD) method can be used to perform mode decomposition on the multidimensional multimodal historical dataset to obtain k modal components IMF1, IMF2, ..., IMF1. k MVMD is a signal decomposition method used to extract modal components from multivariate time series data.

[0034] S120. The kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm obtains the mode prediction result corresponding to each of the multiple first mode components.

[0035] In this embodiment, a Kernelized Extreme Learning Machine (KELM) prediction model can be pre-established, and the Multi-objective White Shark Optimizer (MOWSO) algorithm can be used to optimize the model parameters of this prediction model to obtain the optimal model parameters, thereby obtaining the MOWSO-optimized KELM prediction model. For example, the model parameters may include regularization coefficients, kernel function parameters, etc., and each model parameter can be used as an optimization objective.

[0036] Among them, the MOWSO algorithm combines multi-objective optimization algorithm and great white shark optimization algorithm. It can set multiple optimization objectives and continuously update the position of the great white shark by simulating the predation behavior of the great white shark in order to track the position of the prey, thereby achieving objective optimization.

[0037] In this embodiment, the input to the MOWSO-optimized KELM prediction model can be the modal components obtained by decomposing multimodal historical data using the MVMD method, and the output can be the prediction result corresponding to each modal component. When optimizing the KELM prediction model using the MOWSO algorithm, each individual shark can be used as a set of model parameters, and the optimal model parameters can be obtained by finding the optimal individual.

[0038] Specifically, all first mode components can be input into the MOWSO-optimized KELM prediction model, and the mode prediction results corresponding to each first mode component can be obtained from the model's output. These mode prediction results can be power generation predictions for different mode components.

[0039] S130. Find the prediction weight value corresponding to each of the first mode components, and obtain the power generation prediction result corresponding to the photovoltaic power station based on the mode prediction result and prediction weight value corresponding to each of the first mode components.

[0040] In this embodiment, prediction weight values ​​corresponding to different modal components can be preset and stored in a local database. When needed, the prediction weight value corresponding to each first modal component can be retrieved from the local database. Then, the prediction weight value corresponding to each first modal component can be used to perform a weighted sum of the corresponding modal prediction results, and the sum can be used as the final power generation prediction result. Alternatively, the prediction weight value corresponding to each first modal component can be used to perform a weighted average of the corresponding modal prediction results, and the obtained average value can be used as the final power generation prediction result.

[0041] Optionally, obtaining the power generation prediction result corresponding to the photovoltaic power station based on the mode prediction result and prediction weight value corresponding to each of the first mode components may include:

[0042] Calculate the product of each modality prediction result and its corresponding prediction weight value, and then calculate the sum of the products.

[0043] The quotient of the sum of each product divided by the sum of each prediction weight is used as the predicted power generation result for the photovoltaic power station.

[0044] In this embodiment, the corresponding modal prediction results can be weighted and summed according to the prediction weight values, and the sum of the weighted sums can be divided by the sum of all prediction weight values ​​to calculate the quotient value, which is then used as the power generation prediction result corresponding to the photovoltaic power station.

[0045] The technical solution of this invention involves acquiring a multimodal historical dataset corresponding to a photovoltaic power station, and performing modal decomposition on the multimodal historical dataset using a multivariate variational mode decomposition method to obtain multiple first modal components. A kernel extreme learning machine prediction model optimized by a multi-objective white shark optimization algorithm is used to obtain the modal prediction result corresponding to each first modal component. The prediction weight value corresponding to each first modal component is found, and the power generation prediction result corresponding to the photovoltaic power station is obtained based on the modal prediction result and prediction weight value. By optimizing the kernel extreme learning machine prediction model using the multi-objective white shark optimization algorithm to predict different modal components, and obtaining the final power generation prediction result based on the modal prediction result and prediction weight value corresponding to different modal components, the invention achieves multimodal data feature mining and efficient prediction of photovoltaic power stations, thereby improving the accuracy of photovoltaic power generation prediction.

[0046] In an optional implementation of this embodiment, before obtaining the modal prediction result corresponding to each of the plurality of first modal components based on the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm, the method may further include:

[0047] Based on the multimodal historical datasets corresponding to different photovoltaic power stations, a photovoltaic power station sample dataset is generated, and the photovoltaic power station sample dataset is divided according to a preset ratio to obtain a training sample set and a test sample set.

[0048] An initial kernel extreme learning machine prediction model is established, and the multi-objective white shark optimization algorithm is used to optimize the initial kernel extreme learning machine prediction model based on the training sample set and the test sample set, so as to obtain the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm.

[0049] In this embodiment, historical power generation data, historical ledger data, and historical weather data from distributed photovoltaic (PV) power plants can be collected. The collected data can be preprocessed to generate a PV power plant sample dataset. Then, the PV power plant sample dataset can be divided into a training sample set and a test sample set based on a preset ratio for model training and model testing, respectively. For example, the training sample set and the test sample set can be divided in a 7:3 ratio.

[0050] Specifically, an initial KELM prediction model can be established based on the initial model parameters, and the parameters of the MOWSO algorithm can be initialized. Then, the initialized MOWSO algorithm can be used to optimize the model parameters of the initial KELM prediction model based on the partitioned training sample set, resulting in the MOWSO-optimized KELM prediction model. Furthermore, the MOWSO-optimized KELM prediction model can be evaluated using a test sample set; typical evaluation metrics include mean squared error and root mean square error.

[0051] Optionally, a multi-objective white shark optimization algorithm is used to optimize the initial kernel extreme learning machine prediction model based on the training sample set and the test sample set, resulting in a kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm, which may include:

[0052] Based on the initial kernel extreme learning machine prediction model, an initial population is generated, which includes multiple individuals, each of which corresponds to a set of model parameters.

[0053] The multi-objective white shark optimization algorithm is used to update the initial population based on the training sample set and the test sample set until a preset optimization condition is detected. Based on the current population, the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm is obtained.

[0054] In this embodiment, during model optimization, firstly, an initial population is generated based on a preset number of individuals, their locations, and training samples. Then, the population fitness is evaluated, and the non-dominated ranking and crowding distance are calculated. The non-dominated ranking is used to classify the population, and the crowding distance is used to rank individuals within the same ranking; a larger crowding distance indicates a more excellent individual, making it easier to retain. Further, a random search is performed on the individuals in the population to ensure all individuals track the optimal solution, and new individuals are generated based on the optimal solution. These new individuals are then merged into the initial population to update it. Finally, it is determined whether the current population meets preset optimization conditions, such as reaching a set maximum number of iterations or meeting set accuracy requirements. If these conditions are not met, model optimization continues. If they are met, a non-dominated set is generated based on the current population, and a MOWSO-optimized KELM prediction model is built based on this non-dominated set.

[0055] Optionally, after dividing the photovoltaic power station sample dataset into a training sample set and a test sample set according to a preset ratio, the method may further include:

[0056] The training sample set is decomposed into multiple second mode components using a multivariate variational mode decomposition method.

[0057] The permutation entropy corresponding to each second modal component is calculated, and the prediction weight value corresponding to each second modal component is obtained based on the permutation entropy.

[0058] In this embodiment, after obtaining the training sample set, the MVMD method can be used in advance to perform mode decomposition on the training sample set to obtain multiple mode components IMF1, IMF2, ..., IMF k Then, the permutation entropy of different modal components can be calculated. Permutation entropy is an indicator of the complexity of a time series; the more regular the time series, the smaller its permutation entropy, and the more complex the time series, the larger its permutation entropy. Furthermore, the modal components can be sorted in descending order of their corresponding permutation entropy, and the predicted weight values ​​corresponding to different modal components can be obtained based on the sorting results and the preset relationship between the sorting and the weight values.

[0059] In one specific implementation of this embodiment, the model optimization process can be as follows: Figure 2 As shown, firstly, multidimensional historical data of photovoltaic power plants are collected, including historical power generation data, historical ledger data, and historical weather data. Based on the collected multidimensional historical data, an initial multimodal dataset is generated. Then, the initial multimodal dataset is subjected to data filtering and standardization to obtain an effective sample set. Further, the effective sample set is split into a training sample set and a test sample set according to a set ratio.

[0060] Then, an initial KELM prediction model is established based on the initial model parameters, and the training sample set is input into the initial KELM prediction model to obtain the initial population. Next, the population fitness is evaluated, and the non-dominated ranking and crowding distance are determined. Then, a random search is performed so that the population individuals track the optimal solution, and new individuals are generated based on the optimal solution. Furthermore, the new individuals are merged to update the population, and it is determined whether the current population meets the optimization conditions. If not, the model optimization continues. If so, the MOWSO-optimized KELM prediction model is obtained.

[0061] While optimizing the model, the MVMD method can be used to perform modal decomposition on the training sample set to obtain multiple modal components IMF1, IMF2, ..., IMF1. k Furthermore, it can calculate the permutation entropy of different modal components, and then allocate the weights of different modal components based on the permutation entropy to obtain the prediction weight values ​​W1, W2, ..., W1 for each modal component. k And the prediction weight matrix can be composed of each prediction weight value.

[0062] Finally, the optimized model was tested based on the test sample set. Specifically, the MVMD method was used to decompose the test sample set to obtain multiple modal components, and each modal component was input into the MOWSO-optimized KELM prediction model to obtain the modal prediction results P1, P2, ..., P for each modal component. k Then, the prediction results of each mode can be weighted and averaged according to the prediction weight matrix to obtain the power generation prediction result corresponding to the test sample. By comparing the power generation prediction result with historical power generation data, the power generation prediction effect of the MOWSO-optimized KELM prediction model can be verified.

[0063] Example 2

[0064] Figure 3 This is a schematic diagram of the structure of a photovoltaic power generation prediction device provided in Embodiment 2 of the present invention. Figure 3 As shown, the device includes: a mode decomposition module 210, a mode prediction result acquisition module 220, and a power generation prediction module 230; wherein,

[0065] The mode decomposition module 210 is used to acquire the multimodal historical dataset corresponding to the photovoltaic power station, and to perform mode decomposition on the multimodal historical dataset using the multivariate variational mode decomposition method to obtain multiple first mode components.

[0066] The modal prediction result acquisition module 220 is used to acquire the modal prediction result corresponding to each of the multiple first modal components based on the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm.

[0067] The power generation prediction module 230 is used to find the prediction weight value corresponding to each of the first mode components, and obtain the power generation prediction result corresponding to the photovoltaic power station based on the mode prediction result and prediction weight value corresponding to each of the first mode components.

[0068] The technical solution of this invention involves acquiring a multimodal historical dataset corresponding to a photovoltaic power station, and performing modal decomposition on the multimodal historical dataset using a multivariate variational mode decomposition method to obtain multiple first modal components. A kernel extreme learning machine prediction model optimized by a multi-objective white shark optimization algorithm is used to obtain the modal prediction result corresponding to each first modal component. The prediction weight value corresponding to each first modal component is found, and the power generation prediction result corresponding to the photovoltaic power station is obtained based on the modal prediction result and prediction weight value. By optimizing the kernel extreme learning machine prediction model using the multi-objective white shark optimization algorithm to predict different modal components, and obtaining the final power generation prediction result based on the modal prediction result and prediction weight value corresponding to different modal components, the invention achieves multimodal data feature mining and efficient prediction of photovoltaic power stations, thereby improving the accuracy of photovoltaic power generation prediction.

[0069] Optionally, the photovoltaic power generation prediction device also includes:

[0070] The sample set generation module is used to generate a photovoltaic power station sample dataset based on the multimodal historical dataset corresponding to different photovoltaic power stations, and to divide the photovoltaic power station sample dataset according to a preset ratio to obtain a training sample set and a test sample set.

[0071] The model optimization module is used to establish an initial kernel extreme learning machine prediction model and to optimize the initial kernel extreme learning machine prediction model using the multi-objective white shark optimization algorithm based on the training sample set and the test sample set, thereby obtaining the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm.

[0072] Optionally, the model optimization module is specifically used to generate an initial population based on the initial kernel extreme learning machine prediction model. The initial population includes multiple individuals, and each individual corresponds to a set of model parameters.

[0073] The multi-objective white shark optimization algorithm is used to update the initial population based on the training sample set and the test sample set until a preset optimization condition is detected. Based on the current population, the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm is obtained.

[0074] Optionally, the photovoltaic power generation prediction device also includes:

[0075] The sample decomposition module is used to perform mode decomposition on the training sample set using a multivariate variational mode decomposition method to obtain multiple second mode components.

[0076] The weight acquisition module is used to calculate the permutation entropy corresponding to each of the second modal components, and to obtain the prediction weight value corresponding to each of the second modal components based on the permutation entropy.

[0077] Optionally, the power generation prediction module 230 is specifically used to calculate the product of each mode prediction result and the corresponding prediction weight value, and to calculate the sum of each product;

[0078] The quotient of the sum of each product divided by the sum of each prediction weight is used as the predicted power generation result for the photovoltaic power station.

[0079] Optionally, the multimodal historical dataset includes historical power generation data, historical ledger data, and historical weather data.

[0080] The photovoltaic power prediction device provided in this embodiment of the invention can execute the photovoltaic power prediction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0081] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0082] Example 3

[0083] Figure 4 A schematic diagram of an electronic device 30 that can be used to implement embodiments of the present invention is shown. The electronic device 30 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 30 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0084] like Figure 4As shown, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32 or a random access memory (RAM) 33, communicatively connected to the at least one processor 31. The memory stores computer programs executable by the at least one processor. The processor 31 can perform various appropriate actions and processes based on the computer program stored in the ROM 32 or loaded from the storage unit 38 into the RAM 33. The RAM 33 can also store various programs and data required for the operation of the electronic device 30. The processor 31, ROM 32, and RAM 33 are interconnected via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.

[0085] Multiple components in electronic device 30 are connected to I / O interface 35, including: input unit 36, such as keyboard, mouse, etc.; output unit 37, such as various types of monitors, speakers, etc.; storage unit 38, such as disk, optical disk, etc.; and communication unit 39, such as network card, modem, wireless transceiver, etc. Communication unit 39 allows electronic device 30 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0086] Processor 31 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 31 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 31 performs the various methods and processes described above, such as power prediction methods for photovoltaic power generation.

[0087] In some embodiments, the photovoltaic power generation prediction method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 30 via ROM 32 and / or communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the photovoltaic power generation prediction method described above can be performed. Alternatively, in other embodiments, processor 31 can be configured to perform the photovoltaic power generation prediction method by any other suitable means (e.g., by means of firmware).

[0088] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0089] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0090] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0091] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 30, which includes: a display device (e.g., a cathode ray tube or liquid crystal display) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device 30. Other types of devices can also be used to provide interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0092] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0093] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact via a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server.

[0094] This embodiment may also include a computer program product, which includes a computer program that, when executed by a processor, implements the photovoltaic power generation prediction method provided in any embodiment of the present invention.

[0095] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0096] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting the power output of photovoltaic power generation, characterized in that, include: A multimodal historical dataset corresponding to a photovoltaic power station is obtained, and the multivariate variational mode decomposition method is used to perform mode decomposition on the multimodal historical dataset to obtain multiple first mode components; The kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm obtains the mode prediction result corresponding to each of the multiple first mode components based on the multiple first mode components. Find the prediction weight value corresponding to each of the first mode components, and obtain the power generation prediction result corresponding to the photovoltaic power station based on the mode prediction result and prediction weight value corresponding to each of the first mode components. Before obtaining the modal prediction result corresponding to each of the multiple first modal components based on the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm, the method further includes: Based on the multimodal historical datasets corresponding to different photovoltaic power stations, a photovoltaic power station sample dataset is generated, and the photovoltaic power station sample dataset is divided according to a preset ratio to obtain a training sample set and a test sample set. An initial kernel extreme learning machine prediction model is established, and the multi-objective white shark optimization algorithm is used to optimize the initial kernel extreme learning machine prediction model based on the training sample set and the test sample set, so as to obtain the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm. The multi-objective white shark optimization algorithm is used to optimize the initial kernel extreme learning machine prediction model based on the training sample set and the test sample set, resulting in a kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm, including: Based on the initial kernel extreme learning machine prediction model, an initial population is generated, which includes multiple individuals, each of which corresponds to a set of model parameters. The multi-objective white shark optimization algorithm is used to update the initial population based on the training sample set and the test sample set until a preset optimization condition is detected. Based on the current population, the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm is obtained.

2. The method according to claim 1, characterized in that, After dividing the photovoltaic power station sample dataset into a training sample set and a test sample set according to a preset ratio, the method further includes: The training sample set is decomposed into multiple second mode components using a multivariate variational mode decomposition method. The permutation entropy corresponding to each second modal component is calculated, and the prediction weight value corresponding to each second modal component is obtained based on the permutation entropy.

3. The method according to claim 1, characterized in that, Based on the mode prediction results and prediction weight values ​​corresponding to each of the first mode components, the power generation prediction results corresponding to the photovoltaic power station are obtained, including: Calculate the product of each modality prediction result and its corresponding prediction weight value, and then calculate the sum of the products. The quotient of the sum of each product divided by the sum of each prediction weight is used as the predicted power generation result for the photovoltaic power station.

4. The method according to any one of claims 1-3, characterized in that, The multimodal historical dataset includes historical power generation data, historical ledger data, and historical weather data.

5. A photovoltaic power generation power prediction device, used to execute the photovoltaic power generation power prediction method as described in any one of claims 1-4, characterized in that, include: The mode decomposition module is used to obtain the multimodal historical dataset corresponding to the photovoltaic power station, and to perform mode decomposition on the multimodal historical dataset using the multivariate variational mode decomposition method to obtain multiple first mode components; The modal prediction result acquisition module is used to acquire the modal prediction result corresponding to each of the multiple first modal components based on the kernel extreme learning machine prediction model optimized by the multi-objective white shark optimization algorithm. The power generation prediction module is used to find the prediction weight value corresponding to each of the first mode components, and obtain the power generation prediction result corresponding to the photovoltaic power station based on the mode prediction result and prediction weight value corresponding to each of the first mode components.

6. An electronic device, characterized in that, The electronic device includes: At least one processor, and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the photovoltaic power generation power prediction method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the power prediction method for photovoltaic power generation according to any one of claims 1-4.

8. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the photovoltaic power generation prediction method according to any one of claims 1-4.

Images