A Neural Network-Based Photovoltaic Power Prediction Method and Device Constrained by Physical Mechanisms

Abstract

This disclosure provides an exemplary embodiment of a method, apparatus, device, medium, and program product for predicting photovoltaic power using a neural network based on physical mechanism constraints. The method includes: obtaining a photovoltaic dataset by determining photovoltaic-related data and performing data preprocessing; constructing an equivalent circuit constraint loss term based on the equivalent circuit equation of a single diode in a photovoltaic cell, constructing a power correlation constraint loss term based on the photovoltaic power-irradiance-temperature correlation equation, and constructing a comprehensive loss function based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term; constructing a neural network model based on physical mechanism constraints, training it based on the photovoltaic dataset and the comprehensive loss function, and obtaining a neural network photovoltaic power prediction model based on physical mechanism constraints; predicting photovoltaic power; and achieving the synergy between physical mechanism constraints and data-driven approaches, as well as accurate prediction of photovoltaic power.

Description

Technical Field

[0001] This disclosure relates to the field of photovoltaic power prediction technology, and in particular to a method, apparatus, equipment, medium, and program product for photovoltaic power prediction based on a neural network constrained by physical mechanisms. Background Technology

[0002] Existing photovoltaic power prediction methods mainly fall into two categories: pure data-driven prediction and pure physical mechanism-constrained prediction. Pure data-driven prediction utilizes the characteristics of massive amounts of data to achieve prediction, but it suffers from the following drawbacks: the prediction model lacks physical constraints, and the prediction results may contradict physical laws; the prediction error is large when data is insufficient; the prediction model is susceptible to interference from abnormal data, thus affecting the prediction accuracy. On the other hand, pure physical mechanism-constrained prediction achieves photovoltaic power prediction by deriving physical equations, but it still has its shortcomings: it simplifies complex factors in actual operation, making it difficult to adapt to actual engineering scenarios, resulting in limited prediction accuracy; it cannot optimize the model using measured data; some parameters are difficult to obtain accurately in actual operation, and the derivation of physical equations is inefficient. Summary of the Invention

[0003] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a method, apparatus, device, medium, and program product for predicting photovoltaic power based on physical mechanism constraints using neural networks.

[0004] To achieve the above objectives, a first aspect of the exemplary embodiments of this disclosure provides a neural network-based photovoltaic power prediction method constrained by physical mechanisms, the method comprising: Identify photovoltaic-related data and perform data preprocessing to obtain a preprocessed photovoltaic dataset. Based on the equivalent circuit equation of a single diode in a photovoltaic cell and the photovoltaic dataset, an equivalent circuit constraint loss term is constructed. Based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, a power correlation constraint loss term is constructed. Based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term, a comprehensive loss function is constructed. A neural network model based on physical mechanism constraints is constructed, and the neural network model is trained based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints. The photovoltaic power is predicted based on the neural network photovoltaic power prediction model.

[0005] In some exemplary embodiments, the photovoltaic-related data includes at least photovoltaic power, solar irradiance, ambient temperature, and wind speed; After identifying and preprocessing relevant photovoltaic (PV) data, a preprocessed PV dataset is obtained, including: Based on linear interpolation, the missing data in the photovoltaic power, solar irradiance and wind speed are interpolated; Outliers in the photovoltaic-related data are identified, and replacements are performed on the outliers based on the linear interpolation. The outliers include negative power and irradiance values ​​that exceed the sensor's measurement range.

[0006] In some exemplary embodiments, based on the equivalent circuit equation of a single diode in a photovoltaic cell and the photovoltaic dataset, an equivalent circuit constraint loss term is constructed, including: Based on the equivalent circuit equation of a single diode in a photovoltaic cell, the theoretical output current equation of the photovoltaic cell at any given moment is determined. Based on the short-circuit current, reverse saturation current, output voltage, absolute temperature, series resistance, and parallel resistance at that moment, the theoretical output current of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output current of the photovoltaic cell at that moment and the number of time periods are determined. Based on the number of time periods, the absolute value of the difference between the theoretical output current and the actual output current is arithmetically averaged to construct the equivalent circuit constraint loss term.

[0007] In some exemplary embodiments, based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, a power correlation constraint loss term is constructed, including: Based on the photovoltaic dataset, the solar irradiance and the actual operating temperature of the photovoltaic cells at that moment are determined. Based on the solar irradiance, the actual operating temperature of the photovoltaic cell, the photovoltaic power-irradiance-temperature correlation equation, the photovoltaic module attenuation correction coefficient, and the solar irradiance and temperature under standard test conditions, the theoretical output power of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output power of the photovoltaic cell at that moment is determined. Based on the number of time periods, the absolute value of the difference between the actual output power and the theoretical output power is arithmetically averaged to construct a power-related constraint loss term.

[0008] In some exemplary embodiments, a comprehensive loss function is constructed based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term, including: Based on the photovoltaic dataset, the actual photovoltaic power at that moment is determined, and based on the actual photovoltaic power and the predicted photovoltaic power at that moment, a prediction accuracy loss term is constructed. A comprehensive loss function is constructed by weighting and synthesizing the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term.

[0009] In some exemplary embodiments, a neural network model based on physical mechanism constraints is constructed, and the neural network model is trained based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints, including: A neural network model based on physical mechanism constraints is constructed. The solar irradiance, ambient temperature, and wind speed in the photovoltaic dataset are used as the inputs to the neural network model, and the photovoltaic power in the photovoltaic dataset is used as the prediction target of the neural network model. The neural network model is trained through the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints.

[0010] Based on the same inventive concept, a second aspect of the exemplary embodiments of this disclosure provides a neural network photovoltaic power prediction device based on physical mechanism constraints, the device comprising: The preprocessing module is configured to determine photovoltaic-related data and perform data preprocessing to obtain a preprocessed photovoltaic dataset. The comprehensive loss module is configured to construct an equivalent circuit constraint loss term based on the equivalent circuit equation of a single diode in a photovoltaic cell and the photovoltaic dataset, construct a power correlation constraint loss term based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, and construct a comprehensive loss function based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term. The model building module is configured to build a neural network model based on physical mechanism constraints, and train the neural network model based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints. The power prediction module is configured to predict the photovoltaic power based on the neural network photovoltaic power prediction model.

[0011] The apparatus provided in this exemplary embodiment, wherein the preprocessing module is specifically used for: After identifying and preprocessing relevant photovoltaic (PV) data, a preprocessed PV dataset is obtained, including: Based on linear interpolation, the missing data in the photovoltaic power, solar irradiance and wind speed are interpolated; Outliers in the photovoltaic-related data are identified, and replacements are performed on the outliers based on the linear interpolation. The outliers include negative power and irradiance values ​​that exceed the sensor's measurement range.

[0012] The apparatus provided in the exemplary embodiments of this disclosure, wherein the integrated loss module is specifically used for: Based on the equivalent circuit equation of a single diode in a photovoltaic cell, the theoretical output current equation of the photovoltaic cell at any given moment is determined. Based on the short-circuit current, reverse saturation current, output voltage, absolute temperature, series resistance, and parallel resistance at that moment, the theoretical output current of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output current of the photovoltaic cell at that moment and the number of time periods are determined. Based on the number of time periods, the absolute value of the difference between the theoretical output current and the actual output current is arithmetically averaged to construct the equivalent circuit constraint loss term.

[0013] The apparatus provided in the exemplary embodiments of this disclosure, wherein the integrated loss module is specifically used for: Based on the photovoltaic dataset, the solar irradiance and the actual operating temperature of the photovoltaic cells at that moment are determined. Based on the solar irradiance, the actual operating temperature of the photovoltaic cell, the photovoltaic power-irradiance-temperature correlation equation, the photovoltaic module attenuation correction coefficient, and the solar irradiance and temperature under standard test conditions, the theoretical output power of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output power of the photovoltaic cell at that moment is determined. Based on the number of time periods, the absolute value of the difference between the actual output power and the theoretical output power is arithmetically averaged to construct a power-related constraint loss term.

[0014] The apparatus provided in the exemplary embodiments of this disclosure, wherein the integrated loss module is specifically used for: Based on the photovoltaic dataset, the actual photovoltaic power at that moment is determined, and based on the actual photovoltaic power and the predicted photovoltaic power at that moment, a prediction accuracy loss term is constructed. A comprehensive loss function is constructed by weighting and synthesizing the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term.

[0015] The apparatus provided in the exemplary embodiments of this disclosure, wherein the model building module is specifically used for: A neural network model based on physical mechanism constraints is constructed. The solar irradiance, ambient temperature, and wind speed in the photovoltaic dataset are used as the inputs to the neural network model, and the photovoltaic power in the photovoltaic dataset is used as the prediction target of the neural network model. The neural network model is trained through the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints.

[0016] Based on the same inventive concept, a third aspect of the exemplary embodiments of this disclosure provides an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement a neural network photovoltaic power prediction method based on physical mechanism constraints as provided in the exemplary embodiments of this disclosure.

[0017] Based on the same inventive concept, a fourth aspect of the exemplary embodiments of this disclosure provides a computer-readable storage medium storing a computer program for executing a neural network photovoltaic power prediction method based on physical mechanism constraints as provided in the exemplary embodiments of this disclosure.

[0018] Based on the same inventive concept, a fifth aspect of the exemplary embodiments of this disclosure provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the method as described in the first aspect.

[0019] The technical solution provided by the exemplary embodiments of this disclosure has the following advantages compared with the prior art: This exemplary embodiment provides a neural network photovoltaic power prediction method based on physical mechanism constraints. The method obtains a photovoltaic dataset by determining relevant photovoltaic data and performing data preprocessing. Based on the equivalent circuit equation of a single diode in a photovoltaic cell, an equivalent circuit constraint loss term is constructed. Based on the photovoltaic power-irradiance-temperature correlation equation, a power correlation constraint loss term is constructed. A comprehensive loss function is then constructed based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction accuracy loss term. A neural network model based on physical mechanism constraints is constructed and trained using the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints. The method then predicts photovoltaic power, achieving a synergy between physical mechanism constraints and data-driven approaches, and enabling accurate prediction of photovoltaic power. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 A flowchart illustrating a neural network photovoltaic power prediction method based on physical mechanism constraints, provided as an exemplary embodiment of this disclosure; Figure 2 A schematic diagram of the structure of a neural network photovoltaic power prediction device based on physical mechanism constraints, provided as an exemplary embodiment of this disclosure; Figure 3 A schematic diagram of the structure of an electronic device provided for an exemplary embodiment of this disclosure. Detailed Implementation

[0022] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0023] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0024] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0025] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0026] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0027] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0028] To address the aforementioned issues, this disclosure provides an exemplary embodiment of a neural network-based photovoltaic power prediction method constrained by physical mechanisms. The method will be described below with reference to specific embodiments.

[0029] Figure 1This is a flowchart illustrating a neural network photovoltaic power prediction method based on physical mechanism constraints, which is provided as an exemplary embodiment of the present disclosure. The method can be executed by a neural network photovoltaic power prediction device based on physical mechanism constraints, wherein the device can be implemented in software and / or hardware, and is generally integrated into an electronic device.

[0030] like Figure 1 As shown, the neural network photovoltaic power prediction method based on physical mechanism constraints includes the following steps: Step S101: Determine photovoltaic-related data and perform data preprocessing to obtain a photovoltaic dataset after data preprocessing.

[0031] In some exemplary embodiments, the photovoltaic-related data includes at least photovoltaic power, solar irradiance, ambient temperature, and wind speed; After identifying and preprocessing relevant photovoltaic (PV) data, a preprocessed PV dataset is obtained, including: Based on linear interpolation, the missing data in the photovoltaic power, solar irradiance and wind speed are interpolated; Outliers in the photovoltaic-related data are identified, and replacements are performed on the outliers based on the linear interpolation. The outliers include negative power and irradiance values ​​that exceed the sensor's measurement range.

[0032] The above difference processing ensures the continuity of photovoltaic-related data; the above replacement processing improves the rationality of the data.

[0033] Step S102: Based on the equivalent circuit equation of a single diode in a photovoltaic cell and the photovoltaic dataset, an equivalent circuit constraint loss term is constructed. Based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, a power correlation constraint loss term is constructed. Based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term, a comprehensive loss function is constructed.

[0034] In some exemplary embodiments, based on the equivalent circuit equation of a single diode in a photovoltaic cell and the photovoltaic dataset, an equivalent circuit constraint loss term is constructed, including: Based on the equivalent circuit equation of a single diode in a photovoltaic cell, the theoretical output current equation of the photovoltaic cell at any given moment is determined. Based on the short-circuit current, reverse saturation current, output voltage, absolute temperature, series resistance, and parallel resistance at that moment, the theoretical output current of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output current of the photovoltaic cell at that moment and the number of time periods are determined. Based on the number of time periods, the absolute value of the difference between the theoretical output current and the actual output current is arithmetically averaged to construct the equivalent circuit constraint loss term.

[0035] In some exemplary embodiments, based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, a power correlation constraint loss term is constructed, including: Based on the photovoltaic dataset, the solar irradiance and the actual operating temperature of the photovoltaic cells at that moment are determined. Based on the solar irradiance, the actual operating temperature of the photovoltaic cell, the photovoltaic power-irradiance-temperature correlation equation, the photovoltaic module attenuation correction coefficient, and the solar irradiance and temperature under standard test conditions, the theoretical output power of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output power of the photovoltaic cell at that moment is determined. Based on the number of time periods, the absolute value of the difference between the actual output power and the theoretical output power is arithmetically averaged to construct a power-related constraint loss term.

[0036] In some exemplary embodiments, a comprehensive loss function is constructed based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term, including: Based on the photovoltaic dataset, the actual photovoltaic power at that moment is determined, and based on the actual photovoltaic power and the predicted photovoltaic power at that moment, a prediction accuracy loss term is constructed. A comprehensive loss function is constructed by weighting and synthesizing the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term.

[0037] In some exemplary embodiments, a photovoltaic module may be obtained by connecting a number of photovoltaic cells in series and parallel.

[0038] As an example, the equivalent circuit constraint loss term is constructed as follows: ; in, Represents the equivalent circuit constraint loss term; Indicates that the photovoltaic cell is in the first The actual output current over a time period; Indicates that the photovoltaic cell is in the first Short-circuit current over a time period; Indicates that the photovoltaic cell is in the first Reverse saturation current over a time period; Represents the amount of electron charge, a fixed value. ; Indicates that the photovoltaic cell is in the first Output voltage over a time period; This represents the ideality factor of a photovoltaic cell, with a range of values. ; Boltzmann constant; a fixed value ; Indicates the photovoltaic cell's first The absolute temperature over a given time period; Indicates the series resistance of a photovoltaic cell; Indicates the parallel resistance of the photovoltaic cell; Indicates the number of time periods.

[0039] As an example, the power correlation constraint loss term is constructed as follows: ; in, This represents the power-related constraint loss term; Indicates that the photovoltaic cell is in the first The actual output power over a given time period; This represents the photovoltaic module degradation correction factor, with a value range of... ; This indicates the rated power of the photovoltaic cell under standard test conditions; Indicates that the photovoltaic cell is in the first Solar irradiance over a specific time period; This indicates the solar irradiance of a photovoltaic cell under standard test conditions. This represents the temperature coefficient of a photovoltaic module, with a range of values. ; Indicates that the photovoltaic cell is in the first The actual operating temperature over a specific time period; This indicates the temperature of the photovoltaic cell under standard test conditions, a fixed value of 25℃. Indicates the number of time periods; The above formula ensures that the model output satisfies the correlation law between photovoltaic power, irradiance, and temperature.

[0040] As an example, the formula for constructing the prediction accuracy loss term is as follows: ; in, This represents the loss term indicating the accuracy of the prediction results; Indicates the first Predicted photovoltaic power for a given time period; Indicates the first The actual photovoltaic power over a given time period; Indicates the number of time periods.

[0041] As an example, the predicted photovoltaic power in the above formula is a known quantity, generated by the neural network model during the current training.

[0042] The above formula ensures the accuracy of photovoltaic power prediction by defining a loss term to quantify the deviation between predicted and actual power, and improves the deviation correction efficiency through the physical characteristics of the neural network model.

[0043] As an example, the comprehensive loss function is constructed as follows: ; in, Represents the overall loss function; Represents the equivalent circuit constraint loss term; This represents the power-related constraint loss term; This represents the loss term indicating the accuracy of the prediction results; , , This represents the weighting coefficient.

[0044] As an example, weighting coefficients Weighting coefficients of the equivalent circuit constraint loss term It can take the value 0.3; the weighting coefficient of the power-related constraint loss term. It can take the value 0.2; the weighting coefficient of the prediction accuracy loss term. It can take the value 0.5.

[0045] The above formula integrates the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term, and uses the physical characteristics of the neural network model to form a comprehensive loss function for the neural network model, thereby strengthening the fusion of physical constraints and the model.

[0046] Step S103: Construct a neural network model based on physical mechanism constraints. Train the neural network model based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints.

[0047] In some exemplary embodiments, a neural network model based on physical mechanism constraints is constructed, and the neural network model is trained based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints, including: A neural network model based on physical mechanism constraints is constructed. The solar irradiance, ambient temperature, and wind speed in the photovoltaic dataset are used as the inputs to the neural network model, and the photovoltaic power in the photovoltaic dataset is used as the prediction target of the neural network model. The neural network model is trained through the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints.

[0048] In some exemplary embodiments, a neural network model based on physical mechanism constraints is constructed. The neural network model is constructed using TensorFlow, which effectively utilizes the physical characteristics inherent in the neural network model itself. The loss function of the neural network model is replaced with a comprehensive loss function that considers the physical mechanism constraints of photovoltaic power generation, thereby achieving the synergy between the inherent physical characteristics of the model and the physical mechanism constraints.

[0049] The above steps further improve the neural network model's fit to physical mechanism constraints and its prediction accuracy.

[0050] To achieve the above embodiments, this disclosure also proposes a neural network photovoltaic power prediction device based on physical mechanism constraints.

[0051] The beneficial effects of this disclosure are: This disclosure solves the shortcomings of pure data-driven and pure physical mechanism-constrained prediction by embedding photovoltaic power generation-specific physical mechanism constraints (photovoltaic cell single diode equivalent circuit equation, photovoltaic power-irradiance-temperature correlation equation, etc.) and making full use of the physical characteristics of the neural network model itself, achieving the dual support of "inherent physical characteristics of neural network + photovoltaic power generation-specific physical constraints".

[0052] This disclosure reduces the impact of data interference on prediction results through data preprocessing.

[0053] This disclosure trains the model using measured data, thus compensating for the insufficient prediction accuracy caused by the simplification factors of pure physical models.

[0054] Figure 2 This is a schematic diagram of a neural network photovoltaic power prediction device based on physical mechanism constraints, provided as an exemplary embodiment of this disclosure. The device 200 can be implemented by software and / or hardware and is generally integrated into an electronic device. Figure 2 As shown, the device 200 includes: a preprocessing module 201, a comprehensive loss module 202, a model building module 203, and a power prediction module 204, wherein, Preprocessing module 201 is configured to determine long series of photovoltaic-related data and perform data preprocessing to obtain a photovoltaic dataset after data preprocessing. The comprehensive loss module 202 is configured to construct an equivalent circuit constraint loss term based on the photovoltaic cell single diode equivalent circuit equation and the photovoltaic dataset, construct a power correlation constraint loss term based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, and construct a comprehensive loss function based on the equivalent circuit constraint loss term, the power correlation constraint loss term and the prediction result accuracy loss term. The model building module 203 is configured to build a neural network model based on physical mechanism constraints, and train the neural network model based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints. The power prediction module 204 is configured to predict the photovoltaic power based on the neural network photovoltaic power prediction model.

[0055] The apparatus provided in the exemplary embodiments of this disclosure, wherein the preprocessing module 201 is specifically used for: After identifying and preprocessing relevant photovoltaic (PV) data, a preprocessed PV dataset is obtained, including: Based on linear interpolation, the missing data in the photovoltaic power, solar irradiance and wind speed are interpolated; Outliers in the photovoltaic-related data are identified, and replacements are performed on the outliers based on the linear interpolation. The outliers include negative power and irradiance values ​​that exceed the sensor's measurement range.

[0056] The apparatus provided in the exemplary embodiments of this disclosure, wherein the integrated loss module 202 is specifically used for: Based on the equivalent circuit equation of a single diode in a photovoltaic cell, the theoretical output current equation of the photovoltaic cell at any given moment is determined. Based on the short-circuit current, reverse saturation current, output voltage, absolute temperature, series resistance, and parallel resistance at that moment, the theoretical output current of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output current of the photovoltaic cell at that moment and the number of time periods are determined. Based on the number of time periods, the absolute value of the difference between the theoretical output current and the actual output current is arithmetically averaged to construct the equivalent circuit constraint loss term.

[0057] The apparatus provided in the exemplary embodiments of this disclosure, wherein the integrated loss module 202 is specifically used for: Based on the photovoltaic dataset, the solar irradiance and the actual operating temperature of the photovoltaic cells at that moment are determined. Based on the solar irradiance, the actual operating temperature of the photovoltaic cell, the photovoltaic power-irradiance-temperature correlation equation, the photovoltaic module attenuation correction coefficient, and the solar irradiance and temperature under standard test conditions, the theoretical output power of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output power of the photovoltaic cell at that moment is determined. Based on the number of time periods, the absolute value of the difference between the actual output power and the theoretical output power is arithmetically averaged to construct a power-related constraint loss term.

[0058] The apparatus provided in the exemplary embodiments of this disclosure, wherein the integrated loss module 202 is specifically used for: Based on the photovoltaic dataset, the actual photovoltaic power at that moment is determined, and based on the actual photovoltaic power and the predicted photovoltaic power at that moment, a prediction accuracy loss term is constructed. A comprehensive loss function is constructed by weighting and synthesizing the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term.

[0059] The apparatus provided in the exemplary embodiments of this disclosure, wherein the model building module 203 is specifically used for: A neural network model based on physical mechanism constraints is constructed. The solar irradiance, ambient temperature, and wind speed in the photovoltaic dataset are used as the inputs to the neural network model, and the photovoltaic power in the photovoltaic dataset is used as the prediction target of the neural network model. The neural network model is trained through the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints.

[0060] The physical mechanism-constrained neural network photovoltaic power prediction device provided in the exemplary embodiments of this disclosure can execute the physical mechanism-constrained neural network photovoltaic power prediction method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the method execution.

[0061] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program / instructions, which, when executed by a processor, implements a neural network photovoltaic power prediction method based on physical mechanism constraints as described in the above embodiments.

[0062] Figure 3 A schematic diagram of the structure of an electronic device provided for an exemplary embodiment of this disclosure.

[0063] The following is a detailed reference. Figure 3 The diagram illustrates a structural schematic suitable for implementing the electronic device 300 in the exemplary embodiments of this disclosure. The electronic device 300 in the exemplary embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the exemplary embodiments disclosed herein.

[0064] like Figure 3As shown, the electronic device 300 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a memory 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processor 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0065] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0066] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from memory 308, or installed from ROM 302. When the computer program is executed by processor 301, it performs the functions defined in an exemplary embodiment of this disclosure of a neural network photovoltaic power prediction method based on physical mechanism constraints.

[0067] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0068] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0069] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0070] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned neural network photovoltaic power prediction method based on physical mechanism constraints.

[0071] Electronic devices can be programmed with computer program code in one or more programming languages ​​or combinations thereof to perform the operations of this disclosure. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0073] The units described in the exemplary embodiments of this disclosure can be implemented in software or in hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0074] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0075] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. 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 (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0076] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0077] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0078] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A neural network-based photovoltaic power prediction method constrained by physical mechanisms, characterized in that, include: Identify photovoltaic-related data and perform data preprocessing to obtain a preprocessed photovoltaic dataset. Based on the equivalent circuit equation of a single diode in a photovoltaic cell and the photovoltaic dataset, an equivalent circuit constraint loss term is constructed. Based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, a power correlation constraint loss term is constructed. Based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term, a comprehensive loss function is constructed. A neural network model based on physical mechanism constraints is constructed, and the neural network model is trained based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints. The photovoltaic power is predicted based on the neural network photovoltaic power prediction model.

2. The method according to claim 1, characterized in that, The photovoltaic-related data includes at least photovoltaic power, solar irradiance, ambient temperature, and wind speed; After identifying and preprocessing relevant photovoltaic (PV) data, a preprocessed PV dataset is obtained, including: Based on linear interpolation, the missing data in the photovoltaic power, solar irradiance and wind speed are interpolated; Outliers in the photovoltaic-related data are identified, and replacements are performed on the outliers based on the linear interpolation. The outliers include negative power and irradiance values ​​that exceed the sensor's measurement range.

3. The method according to claim 1, characterized in that, Based on the equivalent circuit equation of a single diode in a photovoltaic cell and the aforementioned photovoltaic dataset, an equivalent circuit constraint loss term is constructed, including: Based on the equivalent circuit equation of a single diode in a photovoltaic cell, the theoretical output current equation of the photovoltaic cell at any given moment is determined. Based on the short-circuit current, reverse saturation current, output voltage, absolute temperature, series resistance, and parallel resistance at that moment, the theoretical output current of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output current of the photovoltaic cell at that moment and the number of time periods are determined. Based on the number of time periods, the absolute value of the difference between the theoretical output current and the actual output current is arithmetically averaged to construct the equivalent circuit constraint loss term.

4. The method according to claim 3, characterized in that, Based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, a power correlation constraint loss term is constructed, including: Based on the photovoltaic dataset, the solar irradiance and the actual operating temperature of the photovoltaic cells at that moment are determined. Based on the solar irradiance, the actual operating temperature of the photovoltaic cell, the photovoltaic power-irradiance-temperature correlation equation, the photovoltaic module attenuation correction coefficient, and the solar irradiance and temperature under standard test conditions, the theoretical output power of the photovoltaic cell at that moment is determined. Based on the photovoltaic dataset, the actual output power of the photovoltaic cell at that moment is determined. Based on the number of time periods, the absolute value of the difference between the actual output power and the theoretical output power is arithmetically averaged to construct a power-related constraint loss term.

5. The method according to claim 4, characterized in that, Based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term, a comprehensive loss function is constructed, including: Based on the photovoltaic dataset, the actual photovoltaic power at that moment is determined, and based on the actual photovoltaic power and the predicted photovoltaic power at that moment, a prediction accuracy loss term is constructed. A comprehensive loss function is constructed by weighting and synthesizing the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term.

6. The method according to claim 1, characterized in that, A neural network model based on physical mechanism constraints is constructed, and the neural network model is trained based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints, including: A neural network model based on physical mechanism constraints is constructed. The solar irradiance, ambient temperature, and wind speed in the photovoltaic dataset are used as the inputs to the neural network model, and the photovoltaic power in the photovoltaic dataset is used as the prediction target of the neural network model. The neural network model is trained through the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints.

7. A neural network photovoltaic power prediction device based on physical mechanism constraints, the device comprising: The preprocessing module is configured to determine photovoltaic-related data and perform data preprocessing to obtain a preprocessed photovoltaic dataset. The comprehensive loss module is configured to construct an equivalent circuit constraint loss term based on the equivalent circuit equation of a single diode in a photovoltaic cell and the photovoltaic dataset, construct a power correlation constraint loss term based on the photovoltaic power-irradiance-temperature correlation equation and the photovoltaic dataset, and construct a comprehensive loss function based on the equivalent circuit constraint loss term, the power correlation constraint loss term, and the prediction result accuracy loss term. The model building module is configured to build a neural network model based on physical mechanism constraints, and train the neural network model based on the photovoltaic dataset and the comprehensive loss function to obtain a neural network photovoltaic power prediction model based on physical mechanism constraints. The power prediction module is configured to predict the photovoltaic power based on the neural network photovoltaic power prediction model.

8. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program / instruction thereon, which, when executed by a processor, implements the steps of the method described in any one of claims 1-6.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-6.

Images