Photovoltaic array anomaly detection method and device, electronic equipment and storage medium

Abstract

The present disclosure provides an anomaly detection method and device of a photovoltaic array, an electronic device and a storage medium. The method comprises: obtaining a plurality of operation data of the photovoltaic array, and constructing an initial photovoltaic array model, the initial photovoltaic array model having corresponding model parameters; processing the model parameters by using a flower pollination algorithm to determine a target model parameter solution; adjusting the initial photovoltaic array model by using the target model parameter solution to obtain a target photovoltaic array model; and determining an anomaly detection result of the photovoltaic array according to the plurality of operation data and the target photovoltaic array model. Since the model parameters of the initial photovoltaic array model are solved and processed by using the flower pollination algorithm, the accuracy of the model parameter solution can be effectively improved, and the model construction effect of the photovoltaic array model can be effectively improved, so that when the target photovoltaic array model constructed is used for anomaly detection of the photovoltaic array, the anomaly detection effect of the photovoltaic array can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of photovoltaic power generation, and particularly relates to an abnormality detection method and device of a photovoltaic array, an electronic device, and a storage medium. BACKGROUND

[0002] A photovoltaic array is an important component unit of a photovoltaic power generation system. Since the photovoltaic array is operated in an outdoor environment such as strong wind, high temperature, and ultraviolet radiation for a long time, it is prone to operation abnormalities, thereby affecting the power generation efficiency. Therefore, in the technical field of photovoltaic power generation, a photovoltaic array model is usually constructed to realize abnormality detection of the photovoltaic array through the photovoltaic array model.

[0003] In related technologies, when constructing the photovoltaic array model, an analytical method or an iterative method is usually used to solve the model parameters of the photovoltaic array model, so as to construct the photovoltaic array model according to the solution of the model parameters.

[0004] In this way, in the process of solving the model parameters of the photovoltaic array, the solution accuracy of the model parameters is low, which leads to poor construction effect of the photovoltaic array model, thereby affecting the abnormality detection effect of the photovoltaic array when the photovoltaic array model is used to detect the abnormality of the photovoltaic array. SUMMARY

[0005] The present disclosure aims to at least partially solve one of the technical problems in the related art.

[0006] To this end, the present disclosure aims to provide an abnormality detection method and device of a photovoltaic array, an electronic device, and a storage medium. Since the flower pollination algorithm is used to solve the model parameters of the constructed initial photovoltaic array model, the solution accuracy of the model parameters of the photovoltaic array model can be effectively improved, thereby effectively improving the model construction effect of the photovoltaic array model, and effectively improving the abnormality detection effect of the photovoltaic array when the constructed target photovoltaic array model is used for abnormality detection of the photovoltaic array.

[0007] The abnormality detection method of the photovoltaic array provided by the first aspect of the present disclosure comprises: obtaining a plurality of operation data of a photovoltaic array and constructing an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters; processing the model parameters by using a flower pollination algorithm to determine a target model parameter solution; adjusting the initial photovoltaic array model by using the target model parameter solution to obtain a target photovoltaic array model; and determining an abnormality detection result of the photovoltaic array according to the plurality of operation data and the target photovoltaic array model.

[0008] The method for detecting the abnormality of the photovoltaic array provided in the first aspect of the present disclosure comprises the following steps: obtaining a plurality of operation data of the photovoltaic array; constructing an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters; processing the model parameters by using a pollination algorithm to determine a target model parameter solution; adjusting the initial photovoltaic array model by using the target model parameter solution to obtain a target photovoltaic array model; and determining an abnormality detection result of the photovoltaic array according to the plurality of operation data and the target photovoltaic array model. Since the model parameters of the constructed initial photovoltaic array model are processed by using the pollination algorithm, the accuracy of the photovoltaic array model parameter solution can be effectively improved, and the model construction effect of the photovoltaic array model can be effectively improved, so that the abnormality detection effect of the photovoltaic array can be effectively improved when the constructed target photovoltaic array model is used for the abnormality detection of the photovoltaic array.

[0009] The device for detecting the abnormality of the photovoltaic array provided in the second aspect of the present disclosure comprises the following modules: an obtaining module for obtaining a plurality of operation data of the photovoltaic array; a constructing module for constructing an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters; a processing module for processing the model parameters by using a pollination algorithm to determine a target model parameter solution; an adjusting module for adjusting the initial photovoltaic array model by using the target model parameter solution to obtain a target photovoltaic array model; and a determining module for determining an abnormality detection result of the photovoltaic array according to the plurality of operation data and the target photovoltaic array model.

[0010] The device for detecting the abnormality of the photovoltaic array provided in the second aspect of the present disclosure comprises the following modules: an obtaining module for obtaining a plurality of operation data of the photovoltaic array; a constructing module for constructing an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters; a processing module for processing the model parameters by using a pollination algorithm to determine a target model parameter solution; an adjusting module for adjusting the initial photovoltaic array model by using the target model parameter solution to obtain a target photovoltaic array model; and a determining module for determining an abnormality detection result of the photovoltaic array according to the plurality of operation data and the target photovoltaic array model.

[0011] The third aspect of the present disclosure provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, the method for detecting the abnormality of the photovoltaic array provided in the first aspect of the present disclosure is implemented.

[0012] The fourth aspect of the present disclosure provides a non-transitory computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the method for detecting abnormality of a photovoltaic array according to the first aspect of the present disclosure.

[0013] The fifth aspect of the present disclosure provides a computer program product, which, when executed by a processor, performs the method for detecting abnormality of a photovoltaic array according to the first aspect of the present disclosure.

[0014] Additional aspects and advantages of the present disclosure will be made apparent from the following description of embodiments, which proceeds with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0015] The above and / or additional aspects and advantages of the present disclosure will become apparent and be readily appreciated from the following description, including the accompanying drawings, wherein:

[0016] Figure 1 is a flowchart of a method for detecting abnormality of a photovoltaic array according to an embodiment of the present disclosure;

[0017] Figure 2 is a flowchart of a method for detecting abnormality of a photovoltaic array according to another embodiment of the present disclosure;

[0018] Figure 3 is a flowchart of a method for detecting abnormality of a photovoltaic array according to another embodiment of the present disclosure;

[0019] Figure 4 is a structural diagram of a device for detecting abnormality of a photovoltaic array according to an embodiment of the present disclosure;

[0020] Figure 5 is a structural diagram of a device for detecting abnormality of a photovoltaic array according to another embodiment of the present disclosure;

[0021] Figure 6 shows a block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, wherein the same or like reference numerals in different drawings represent the same or like elements or components having the same or similar function. The embodiments described below are examples for explaining the present disclosure and are not intended to limit the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications and equivalents falling within the spirit and scope of the appended claims.

[0023] Figure 1is a flowchart of a photovoltaic array anomaly detection method according to an embodiment of the present disclosure.

[0024] It should be noted that the subject of the photovoltaic array anomaly detection method in this embodiment is a photovoltaic array anomaly detection device, which can be implemented in software and / or hardware. The device can be configured in an electronic device, which can include but is not limited to a terminal, a server, and the like.

[0025] As shown in Figure 1 , the photovoltaic array anomaly detection method comprises:

[0026] S101: Obtain a plurality of running data of the photovoltaic array.

[0027] The photovoltaic array is an important unit of a photovoltaic power generation system. The plurality of related data of the photovoltaic array in actual operation, i.e., the running data, can be, for example, the running parameters of the photovoltaic array, the output current, voltage, and the like of the photovoltaic array, without limitation.

[0028] In the embodiment of the present disclosure, the plurality of running data of the photovoltaic array can be obtained by using an inverter to obtain the current and voltage data [Iori, Vori] of the actual operation of the photovoltaic array (wherein Iori represents the current data of the photovoltaic array, Vori represents the voltage data of the photovoltaic array, and i = (1, …, N). N represents the number of data points of the current and voltage), and the current and voltage data [I ori ,V ori ] obtained by the inverter are taken as the plurality of running data of the photovoltaic array, without limitation.

[0029] In some embodiments, the plurality of running data of the photovoltaic array can also be obtained by providing a corresponding data transmission interface by the photovoltaic array anomaly detection device, and obtaining the plurality of running data of the photovoltaic array via the data transmission interface, or any other possible method, without limitation.

[0030] S102: Construct an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters.

[0031] The photovoltaic array model can be used to simulate the running of the actual photovoltaic array, i.e., the running of the photovoltaic array can be simulated by constructing the photovoltaic array model to detect the running anomaly of the photovoltaic array.

[0032] Wherein, in the initial stage of the photovoltaic array anomaly detection method, the obtained photovoltaic array model can be called an initial photovoltaic array model, which can have some corresponding parameters, which can be called model parameters, which can be initial input parameters, output parameters of the initial photovoltaic array model, and can be, for example, output voltage, output current, etc. of the initial photovoltaic array model, without limitation.

[0033] In some embodiments, the initial photovoltaic array model can be constructed by obtaining a plurality of running data of the photovoltaic array during the operation of the photovoltaic array, and analyzing the plurality of running data obtained to determine the corresponding correlation between the plurality of running data, and constructing the initial photovoltaic array model according to the plurality of running data obtained and the correlation between the plurality of running data.

[0034] Alternatively, the initial photovoltaic array model can also be constructed in any other possible way, for example, simulation software can be used to simulate the actual operation of the photovoltaic array to establish the initial photovoltaic array model, without limitation.

[0035] S103: The flower pollination algorithm is used to process the model parameters to determine the target model parameter solution.

[0036] After the initial photovoltaic array model is established, the model parameters of the initial photovoltaic array model can be processed, and the model parameters obtained by the optimization processing are used as the target model parameters.

[0037] Wherein, the flower pollination algorithm can be used to solve the model parameters of the initial photovoltaic array to obtain the optimal model parameter solution of the initial photovoltaic array model, and the optimal model parameter solution is used as the target model parameter solution.

[0038] That is to say, in the embodiments of the present disclosure, the flower pollination algorithm can be used to solve the model parameters of the initial photovoltaic array to obtain the optimal model parameter solution of the initial photovoltaic array model, and the optimal model parameter solution is used as the target model parameter solution, without limitation.

[0039] Alternatively, any other possible model parameter solving method can also be used to solve the model parameters of the initial photovoltaic array model to obtain the target model parameter solution, for example, analytical method, iterative method and meta-heuristic algorithm, etc. without limitation.

[0040] S104: The initial photovoltaic array model is adjusted using the target model parameter solution to obtain a target photovoltaic array model.

[0041] The target model parameter solution can be used to adjust the initial photovoltaic array model, and the photovoltaic array model obtained through the adjustment can be taken as the target photovoltaic array model.

[0042] In the embodiments of the present disclosure, the target model parameter solution can be used to adjust the initial photovoltaic array model. After the target model parameter solution is determined, the target model parameter solution can be substituted into the initial photovoltaic array, and the photovoltaic array model to which the target model parameter belongs can be taken as the target photovoltaic array model, and no limitation is made in this regard.

[0043] In some embodiments, the target model parameter solution can be used to adjust the initial photovoltaic array model to obtain the target photovoltaic array model. After the target model parameter solution is determined, an adjustment coefficient corresponding to the target model parameter solution can be generated, the adjustment coefficient can be used to adjust the initial photovoltaic array model, and the initial photovoltaic array model can be adjusted based on the adjustment coefficient to obtain the target photovoltaic array model.

[0044] Alternatively, the target model parameter solution can be used to adjust the initial photovoltaic array model to obtain the target photovoltaic array model in any other possible manner, and no limitation is made in this regard.

[0045] S105: Determine an abnormality detection result of the photovoltaic array according to the multiple running data and the target photovoltaic array model.

[0046] After the target photovoltaic array model is constructed, the photovoltaic array can be detected for abnormality according to the multiple running data and the target photovoltaic array model, and a corresponding detection result can be obtained, which can be referred to as an abnormality detection result.

[0047] In some embodiments, the abnormality detection result of the photovoltaic array can be determined according to the multiple running data and the target photovoltaic array model. The multiple running data can be input into the target photovoltaic array model to obtain a running result output by the target photovoltaic array model. Then, the running result can be compared with a pre-set abnormal running condition (which can be adaptively configured in combination with the actual business scenario of the photovoltaic array abnormality detection requirement, and no limitation is made in this regard) to obtain a corresponding comparison result, and the abnormality detection result of the photovoltaic array can be determined according to the comparison result, and no limitation is made in this regard.

[0048] For example, a corresponding reference operation result can be determined in advance for the photovoltaic array, and then the operation result output by the target photovoltaic array model can be compared with the reference operation result, and when the operation result output by the target photovoltaic array model is the same as the reference operation result, it is determined that the photovoltaic array does not have an operation abnormality, and when the operation result output by the target photovoltaic array model is different from the reference operation result, it is determined that the photovoltaic array has an operation abnormality.

[0049] Alternatively, a corresponding operation result threshold can also be determined in advance for the photovoltaic array, and when the operation result output by the target photovoltaic array model is less than the operation result threshold, it is determined that the photovoltaic array has an operation abnormality, and when the operation result output by the target photovoltaic array model is greater than or equal to the operation result threshold, it is determined that the photovoltaic array does not have an operation abnormality, and no limitation is made thereto.

[0050] In this embodiment, a plurality of operation data of the photovoltaic array is obtained, and an initial photovoltaic array model is constructed, wherein the initial photovoltaic array model has corresponding model parameters, the model parameters are processed by using the pollination algorithm to determine a target model parameter solution, the initial photovoltaic array model is adjusted by using the target model parameter solution to obtain a target photovoltaic array model, and an abnormality detection result of the photovoltaic array is determined according to the plurality of operation data and the target photovoltaic array model. Since the model parameters of the constructed initial photovoltaic array model are solved and processed by using the pollination algorithm, the accuracy of solving the model parameters of the photovoltaic array model can be effectively improved, and the model construction effect of the photovoltaic array model can be effectively improved, so that when the constructed target photovoltaic array model is used for abnormality detection of the photovoltaic array, the abnormality detection effect of the photovoltaic array can be effectively improved.

[0051] Figure 2 is a flow diagram of a photovoltaic array abnormality detection method according to another embodiment of the present disclosure.

[0052] As shown in Figure 2 , the photovoltaic array abnormality detection method comprises:

[0053] S201: Obtain a plurality of operation data of a photovoltaic array.

[0054] The description of S201 can be specifically referred to the above embodiments, which will not be repeated here.

[0055] S202: Obtain a plurality of photovoltaic component parameters of a photovoltaic component.

[0056] In the embodiments of the present disclosure, the photovoltaic array model can be composed of a plurality of photovoltaic component models, and correspondingly,

[0057] The plurality of photovoltaic components can have corresponding parameters, which can be referred to as photovoltaic component parameters, which can specifically be, for example, but are not limited to, the number of series photovoltaic components, the output current of the photovoltaic component, the number of parallel photovoltaic components, the output voltage of the photovoltaic component, and the like.

[0058] In the embodiments of the present disclosure, the plurality of photovoltaic component parameters of the plurality of photovoltaic components of the photovoltaic component can be obtained by monitoring the plurality of operating parameters of the plurality of photovoltaic components in the photovoltaic array in operation by using the monitoring device, so as to obtain the plurality of photovoltaic component parameters of the photovoltaic component, and then the subsequent abnormality detection method of the photovoltaic array can be performed based on the obtained plurality of photovoltaic component parameters. For details, please refer to the subsequent embodiments.

[0059] S203: Construct a photovoltaic component model according to the plurality of photovoltaic component parameters.

[0060] In some embodiments, the photovoltaic component model can be constructed according to the plurality of photovoltaic component parameters by analyzing the obtained photovoltaic component parameters to determine the corresponding correlation between the plurality of photovoltaic component parameters, and constructing the photovoltaic component model according to the obtained plurality of photovoltaic component parameters and the corresponding correlation between the plurality of photovoltaic component parameters.

[0061] Alternatively, the photovoltaic component model can also be constructed according to the plurality of photovoltaic component parameters by using simulation software to simulate the actual operation of the photovoltaic component to establish an initial photovoltaic array model, and the like.

[0062] In the embodiments of the present disclosure, the photovoltaic component model can include a plurality of solar cells, which can have corresponding single-diode models.

[0063] Optionally, in some embodiments, the photovoltaic component model can be constructed by obtaining a plurality of solar cell parameters of the solar cell, and constructing a single-diode model according to the plurality of solar cell parameters, and then performing series and / or parallel processing on the plurality of single-diode models to obtain the photovoltaic component model. Since the photovoltaic component model includes a plurality of solar cells, which can have corresponding single-diode models, the single-diode model can be constructed based on the plurality of solar cell parameters, and the series and / or parallel processing can be performed on the plurality of single-diode models to obtain the photovoltaic component model, thereby effectively simplifying the photovoltaic component model construction process and effectively improving the model construction effect of the photovoltaic component model.

[0064] Wherein, the solar cell can have a corresponding parameter during operation, which can be referred to as a solar cell parameter, which can be, for example, the Kelvin temperature of the solar cell, the solar cell output voltage, the solar cell output current, etc., without limitation.

[0065] After obtaining a plurality of solar cell parameters of the solar cell, the disclosure embodiment can determine the equivalent circuit equation between the solar cell and the single diode model according to the plurality of solar cell parameters:

[0066] I cell =I ph -I d -I sh (Formula 1);

[0067]

[0068]

[0069]

[0070] Wherein, substituting formula 2, formula 3, formula 4 into the above formula 1 to obtain the single diode model:

[0071]

[0072] After constructing a plurality of single diode models, the disclosure embodiment can combine the solar cell parameters obtained above, including the number of solar cell series and parallel connections, to process the plurality of single diode models in series and / or parallel to obtain a photovoltaic module model:

[0073]

[0074] Wherein, I ph is the photo-generated current, I d is the diode shunt, I sh is the parallel resistance shunt, I cell is the solar cell output current, I s is the diode reverse saturation current, V cell is the solar cell output voltage, R s is the series resistance, V d is the diode thermal voltage, R sh is the parallel resistance, a is the diode ideality factor, q is the Coulomb charge, k is the Boltzmann constant, and T is the Kelvin temperature of the solar cell.

[0075] S204: generating an initial photovoltaic array model according to the output parameters of the photovoltaic module model and the plurality of photovoltaic module parameters.

[0076] The parameter output by the photovoltaic module model can be referred to as an output parameter, which can be, for example, a current output by the photovoltaic module model, a voltage output by the photovoltaic module model, without limitation.

[0077] In the embodiments of the present disclosure, after the output parameter of the photovoltaic module model and the plurality of photovoltaic module parameters are determined, an initial photovoltaic array model can be generated according to the output parameter of the photovoltaic module model and the plurality of photovoltaic module parameters, which can be represented as:

[0078]

[0079] wherein N pa is the number of parallel photovoltaic modules, N se is the number of series photovoltaic modules, I is the output current of the photovoltaic module, V is the output voltage of the photovoltaic module, I array is the output current of the photovoltaic array, V array is the output voltage of the photovoltaic array.

[0080] In the embodiments of the present disclosure, the plurality of photovoltaic module parameters of the photovoltaic module are obtained, and the photovoltaic module model is constructed according to the plurality of photovoltaic module parameters, and then the initial photovoltaic array model is generated according to the output parameter of the photovoltaic module model and the plurality of photovoltaic module parameters, so that the complex initial photovoltaic array model construction process can be divided into a plurality of simple photovoltaic module model construction processes, thereby greatly simplifying the initial photovoltaic array model construction process and effectively improving the construction effect of the initial photovoltaic array model.

[0081] S205: The model parameters are processed using the pollination algorithm to determine the target model parameter solution.

[0082] S206: The initial photovoltaic array model is adjusted using the target model parameter solution to obtain a target photovoltaic array model.

[0083] The description of S205-S206 can be specifically referred to the above embodiments, which will not be repeated here.

[0084] S207: Reference running data is determined from the plurality of running data.

[0085] The running data in the plurality of running data that can play a reference role in the photovoltaic array anomaly detection method can be referred to as reference running data.

[0086] In the embodiments of the present disclosure, the reference operation data is determined from the plurality of operation data. The current-voltage data [Iori, Vori] of the actual operation of the photovoltaic array is obtained as the plurality of operation data, and the plurality of operation data obtained is filtered by using an outlier detection, a smoothing filter, a fault data screening and the like, so as to determine the corresponding reference current-voltage data [Iimea, Vimea] from the plurality of operation data (wherein i=(1,…,N), N represents the number of data points of the current-voltage, Iimea is the reference current data, and Vimea is the reference voltage data).

[0087] In the embodiments of the present disclosure, after the initial operation data of the photovoltaic array is obtained and the corresponding target photovoltaic array model is constructed, the initial operation data of the photovoltaic array obtained is input into the target photovoltaic array model, so as to obtain the initial operation result output by the target photovoltaic array model.

[0088] In the embodiments of the present disclosure, after the initial operation data of the photovoltaic array is obtained and the corresponding target photovoltaic array model is constructed, the initial operation data of the photovoltaic array obtained is input into the target photovoltaic array model, so as to obtain the initial operation result output by the target photovoltaic array model.

[0089] In the embodiments of the present disclosure, after the initial operation data of the photovoltaic array is obtained and the corresponding target photovoltaic array model is constructed, the initial operation data of the photovoltaic array obtained is input into the target photovoltaic array model, so as to obtain the initial operation result output by the target photovoltaic array model.

[0090] In the embodiments of the present disclosure, after the initial operation data of the photovoltaic array is obtained and the corresponding target photovoltaic array model is constructed, the initial operation data of the photovoltaic array obtained is input into the target photovoltaic array model, so as to obtain the initial operation result output by the target photovoltaic array model.

[0091] In the embodiments of the present disclosure, after the initial operation data of the photovoltaic array is obtained and the corresponding target photovoltaic array model is constructed, the initial operation data of the photovoltaic array obtained is input into the target photovoltaic array model, so as to obtain the initial operation result output by the target photovoltaic array model.

[0092] In the embodiments of the present disclosure, after the initial operation data of the photovoltaic array is obtained and the corresponding target photovoltaic array model is constructed, the initial operation data of the photovoltaic array obtained is input into the target photovoltaic array model, so as to obtain the initial operation result output by the target photovoltaic array model.

[0093] For example, determining whether the reference operation result and the initial operation result meet the matching condition can be: after determining the reference operation result (for example, a photovoltaic array output voltage value) and the initial operation result (for example, a photovoltaic array initial output voltage value), determining a result difference (a voltage difference) between the reference operation result (for example, a photovoltaic array output voltage value) and the initial operation result (for example, a photovoltaic array initial output voltage value), comparing the determined result difference (voltage difference) with a preset difference threshold value, and determining that the reference operation result and the initial operation result meet the matching condition when the result difference is less than the difference threshold value, and determining that the reference operation result and the initial operation result do not meet the matching condition when the result difference is greater than or equal to the difference threshold value. However, this is not limited thereto.

[0094] S211: If the reference operation result and the initial operation result do not meet the matching condition, it is determined that the photovoltaic array has an operation abnormality.

[0095] In the embodiments of the present disclosure, when it is determined that the reference operation result and the initial operation result do not meet the matching condition, it can be determined that the photovoltaic array has an operation abnormality.

[0096] In the embodiments of the present disclosure, by determining the reference operation data from the plurality of operation data, inputting the initial operation data into the target photovoltaic array model to obtain the initial operation result output by the target photovoltaic array model, inputting the reference operation data into the target photovoltaic array model to obtain the reference operation result output by the target photovoltaic array model, and determining whether the reference operation result and the initial operation result meet the matching condition, and then determining that the photovoltaic array has an operation abnormality when the reference operation result and the initial operation result do not meet the matching condition, the target photovoltaic array model constructed can be used to accurately determine the operation abnormality of the photovoltaic array in combination with the reference operation data, thereby effectively improving the photovoltaic array abnormality detection effect and facilitating the implementation of the photovoltaic array abnormality detection method.

[0097] In this embodiment, by acquiring a plurality of operation data of the photovoltaic array, and acquiring a plurality of photovoltaic component parameters of the photovoltaic component, and then constructing a photovoltaic component model according to the plurality of photovoltaic component parameters, and generating an initial photovoltaic array model according to the output parameters of the photovoltaic component model and the plurality of photovoltaic component parameters, the complex initial photovoltaic array model construction process can be divided into a plurality of simple photovoltaic component model construction processes, thereby greatly simplifying the initial photovoltaic array model construction process while effectively improving the construction effect of the initial photovoltaic array model. Then, the flower pollination algorithm is used to process the model parameters to determine the target model parameter solution, and the target model parameter solution is used to adjust the initial photovoltaic array model to obtain a target photovoltaic array model. Then, the reference operation data is determined from the plurality of operation data, and the initial operation data is input into the target photovoltaic array model to obtain the initial operation result output by the target photovoltaic array model. Then, the reference operation data is input into the target photovoltaic array model to obtain the reference operation result output by the target photovoltaic array model, and it is determined whether the reference operation result and the initial operation result meet the matching condition. If the reference operation result and the initial operation result do not meet the matching condition, it is determined that the photovoltaic array has an operation abnormality. In this way, the target photovoltaic array model constructed can accurately judge the operation abnormality of the photovoltaic array in combination with the reference operation data, thereby effectively improving the photovoltaic array abnormality detection effect and facilitating the implementation of the photovoltaic array abnormality detection method.

[0098] Figure 3 is a flow diagram of another embodiment of the photovoltaic array abnormality detection method of the present disclosure.

[0099] As shown in Figure 3 , the photovoltaic array abnormality detection method comprises:

[0100] S301: Acquire a plurality of operation data of the photovoltaic array.

[0101] S302: Construct an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters.

[0102] The description of S301-S302 can be specifically referred to the above embodiments, which will not be repeated here.

[0103] S303: Determine an initial particle position corresponding to each particle in the flower pollination algorithm,

[0104] The present embodiment constructs an initial photovoltaic array model and determines the model parameters (X=[I ph , I s , R s , R shAfter the model parameters are determined, in order to facilitate the subsequent flower pollination algorithm to be executed, a particle can be introduced to correspondingly describe a set of model parameters.

[0105] Each particle is used to correspondingly describe a set of model parameters, and the particle position is used to correspondingly describe a model parameter solution of the corresponding model parameter. The model parameter solution can be uniformly distributed in a feasible model parameter solution range determined at an initial stage when the abnormality detection method of the photovoltaic array starts to be executed, and the model parameter solution is determined to facilitate the subsequent model parameter solution process. However, no limitation is made in this regard.

[0106] At the initial stage when the abnormality detection method of the photovoltaic array starts to be executed, the particle position determined for each particle can be referred to as an initial particle position.

[0107] In some embodiments, the initial particle position corresponding to each particle in the flower pollination algorithm can be determined in the following manner: after the model parameters are determined, a plurality of possible model parameter solutions corresponding to the model parameters are determined, and the particle position corresponding to the plurality of possible model parameter solutions determined in the foregoing manner is used as the initial particle position. Alternatively, a plurality of similar model parameter solutions can be selected from the plurality of possible model parameter solutions determined in the foregoing manner, and the particle position corresponding to the plurality of similar model parameter solutions is used as the initial particle position. However, no limitation is made in this regard.

[0108] Alternatively, in some embodiments, the initial particle position corresponding to each particle in the flower pollination algorithm can be determined in the following manner: each particle is subjected to chaotic mapping processing to determine the initial particle position corresponding to each particle. Since each particle is subjected to chaotic mapping processing, the initial particle position can be relatively uniformly distributed in the feasible solution range, thereby effectively improving the determination effect of the initial particle position.

[0109] That is, in the embodiments of the present disclosure, each particle i = 1, 2,..., pop, pop is the number of particles) is subjected to chaotic mapping (for example, tent mapping (Tent Map), and no limitation is made in this regard) processing to determine the initial particle position corresponding to each particle The chaotic mapping processing process can be specifically represented as:

[0110]

[0111] wherein i = 1, 2,..., pop, j = 1, 2,..., d, U j represents the upper limit of the jth-dimensional position, L j represents the lower limit of the jth-dimensional position, represents the value of the jth-dimensional position of the ith particle, pop represents the number of particles, d represents the dimension of the position, and s ichaotic coefficient of the i-th particle.

[0112] wherein the chaotic coefficient s i satisfies the following condition:

[0113]

[0114] wherein rand is a random number between 0 and 1, m is a function variable, i = 1, 2, …, pop, and pop represents the number of particles.

[0115] S304: Determine an initial fitness value corresponding to the initial particle position.

[0116] wherein the fitness value can be used to describe the solving accuracy of the model parameter solution corresponding to the particle, the greater the fitness value, the higher the solving accuracy of the model parameter solution corresponding to the particle, and vice versa, the smaller the fitness value, the lower the solving accuracy of the model parameter solution corresponding to the particle, which is not limited.

[0117] In the embodiments of the present disclosure, the specific process of determining the initial fitness value corresponding to the particle position can be represented as:

[0118]

[0119]

[0120] wherein, represents the initial fitness value corresponding to the particle position, is the initial particle position determined above, and RMSE i represents the root mean square error of the current, N represents the number of measured voltage points, and I k,mea represents the measured current value corresponding to the k-th voltage, I k,cal represents the current value obtained by solving according to the k-th voltage.

[0121] S305: Determine a reference particle position according to the initial fitness value.

[0122] wherein among the plurality of initial particle positions, the initial particle position that can play a reference role in subsequent abnormal detection of the photovoltaic array, i.e., can be referred to as a reference particle position, can be used to correspondingly describe a better model parameter solution among the plurality of model parameter solutions.

[0123] In some embodiments, the reference particle position can be determined according to the initial fitness value. After the initial fitness value is determined, the initial fitness value can be compared with a preset fitness threshold (which can be adaptively configured according to the actual business scenario of the photovoltaic array anomaly detection requirement, and is not limited herein), and when the initial fitness value is greater than the fitness threshold, the initial particle position corresponding to the initial fitness value can be taken as the reference particle position. Alternatively, any other possible way can be used to determine the reference particle position according to the initial fitness value, such as a model prediction method, an algorithm method, and the like, which are not limited herein.

[0124] Optionally, in some embodiments, the reference particle position can be determined according to the initial fitness value. The maximum fitness value can be determined from the plurality of initial fitness values, and the initial particle position corresponding to the maximum fitness value can be taken as the reference particle position. Since the fitness value can be used to represent the modeling accuracy of the model, when the initial particle position corresponding to the maximum fitness value is taken as the reference particle position, the reference particle position can be used to effectively assist in improving the modeling effect of the subsequent photovoltaic array model, thereby effectively improving the anomaly detection effect of the photovoltaic array.

[0125] The initial fitness value with the maximum value in the plurality of initial fitness values can be referred to as the maximum fitness value.

[0126] That is to say, in the embodiments of the present disclosure, after the plurality of initial fitness values are determined, the maximum fitness value can be determined from the plurality of initial fitness values, and the particle corresponding to the maximum fitness value can be taken as the reference particle position. This process can be specifically represented as:

[0127]

[0128] X * is the reference particle position, is the initial particle position determined above, i = 1, 2,..., pop, and pop represents the number of particles.

[0129] S306: The particle is target processed according to the reference particle position to determine the current particle position corresponding to the particle.

[0130] After the reference particle position is determined in the embodiments of the present disclosure, the particle can be target processed according to the reference particle position to realize the update iteration of the initial particle position corresponding to the particle, and the particle position obtained after the update iteration is taken as the current particle position.

[0131] In some embodiments, the target processing of the particle according to the reference particle position can be that the particle is optimized in position with the reference particle position as a target direction, and the particle position obtained by the foregoing particle optimization is taken as the current particle position, or other arbitrary possible manners can be adopted to implement the target processing of the particle according to the reference particle position to determine the current particle position corresponding to the particle, for example, an algorithmic manner, which is not limited.

[0132] Optionally, in some embodiments, the target processing of the particle according to the reference particle position to determine the current particle position corresponding to the particle can be that, in response to the current pollination probability being greater than the preset pollination probability, the particle is processed by the cross-pollination manner to determine the current particle position corresponding to the particle, or in response to the current pollination probability being less than or equal to the preset pollination probability, the particle is processed by the self-pollination manner to determine the current particle position corresponding to the particle. Since the particle is processed by the cross-pollination manner in response to the current pollination probability being greater than the preset pollination probability, the local search capability of the particle can be effectively improved, and the convergence speed can be accelerated. Since the particle is processed by the self-pollination manner in response to the current pollination probability being less than or equal to the preset pollination probability, the global search capability of the particle can be effectively improved, and the solution of the model parameters can be prevented from falling into a local optimum.

[0133] The pollination probability is a value migrated from biology to represent which manner (for example, the cross-pollination manner, the self-pollination manner, etc., which is not limited) the model parameter iteration solution is more inclined to.

[0134] The preset pollination probability threshold can be referred to as a preset pollination probability (the preset pollination probability can be represented by p), and the pollination probability determined at the current stage of the photovoltaic array anomaly detection method can be referred to as a current pollination probability (the current pollination probability can be represented by C).

[0135] When the current pollination probability is greater than the preset pollination probability (that is, C > p), the particle can be processed by the cross-pollination manner in the embodiment of the disclosure, that is, the particle can be made to move towards the reference particle position X * in a Levy motion to determine the current particle position corresponding to the particle, and the process can be represented as:

[0136]

[0137]

[0138] wherein, represents the current particle position, X * represents the reference particle position, represents the initial particle position, W i(t) represents the distance of the Levy movement, t is a function variable.

[0139] In order to improve the local search ability of the particle, a wind disturbance mechanism can also be introduced in the above cross-pollination process to optimize the Levy movement, and the optimization process can be represented as:

[0140]

[0141]

[0142] Wherein, θ i represents the wind direction acting on the i-th particle, X * is the reference particle position, initial particle position, represents the current particle position, W i (t) represents the distance of the Levy movement, t is a function variable.

[0143] Alternatively, when the current pollination probability is greater than the preset pollination probability (i.e. C

[0144]

[0145] Wherein, initial particle position, represents the current particle position, pop represents the number of particles, represents the initial particle position of another particle, and ε is a Gaussian random number between 0 and 1.

[0146] In order to improve the local search ability of the particle, a mutation mechanism can also be introduced in the above self-pollination process to optimize the Levy movement, and the optimization process can be represented as:

[0147]

[0148] i≠r and i,r∈(1,pop)

[0149] Wherein, initial particle position, represents the current particle position, pop represents the number of particles, represents the initial particle position of another particle, and ε is a Gaussian random number between 0 and 1.

[0150] S307: In response to the current particle position satisfying the position setting condition, the model parameter solution corresponding to the current particle position is taken as the target model parameter solution.

[0151] After determining the current particle position, the current particle position can be compared with a pre-set position setting condition (the setting condition can be adaptively configured in combination with the abnormal detection demand of the photovoltaic array in the actual business scenario, and no limitation is made to this), and when the current particle position meets the position setting condition, the model parameter solution corresponding to the current particle position is taken as the target model parameter solution.

[0152] For example, comparing the current particle position with the pre-set position setting condition can be comparing the current particle position with the pre-set particle position, and when the current particle position is the same as the pre-set particle position, it is determined that the current particle position meets the position setting condition, and the model parameter solution corresponding to the current particle position is taken as the target model parameter solution, and no limitation is made to this.

[0153] Optionally, in some embodiments, in response to the current particle position meeting the position setting condition, the model parameter solution corresponding to the current particle position is taken as the target model parameter solution can be determining a current fitness value corresponding to the current particle position, and when the current fitness value is greater than the initial fitness value, the model parameter solution corresponding to the current particle position is taken as the target model parameter solution, thereby effectively optimizing the model parameter solution and effectively improving the accuracy and referenceability of the target model parameter solution.

[0154] The fitness value corresponding to the current particle position can be referred to as a current fitness value, which can be used to describe the solving accuracy of the model parameter solution corresponding to the current particle position. The greater the current fitness value, the higher the solving accuracy of the model parameter solution corresponding to the current particle position, and vice versa. The smaller the current fitness value, the lower the solving accuracy of the model parameter solution corresponding to the current particle position, and no limitation is made to this.

[0155] After determining the current particle position , the current fitness value corresponding to the current particle position can be determined, and the process can be represented as:

[0156]

[0157]

[0158] , wherein, is the current fitness value, RMSE i represents the root mean square error of the current, N represents the number of measured voltage points, I k,mea represents the measured current value corresponding to the kth voltage, I k,cal represents the current value obtained by solving according to the kth voltage.

[0159] The embodiment of the present disclosure determines the current fitness value Then, the current fitness value is compared with the initial fitness value determined above, and when the current fitness value is greater than the initial fitness value (i.e. ), the model parameter solution corresponding to the current particle position is taken as the target model parameter solution.

[0160] In the embodiment of the present disclosure, the initial particle position corresponding to each particle in the flower pollination algorithm is determined, wherein each particle is used to correspond to a set of model parameters, and the particle position is used to correspond to the model parameter solution of the corresponding model parameter. The initial fitness value corresponding to the initial particle position is determined, and then the reference particle position is determined according to the initial fitness value. The particles are processed according to the reference particle position to determine the current particle position corresponding to the particles. In response to the current particle position satisfying the position setting condition, the model parameter solution corresponding to the current particle position is taken as the target model parameter solution. Since the flower pollination algorithm is used to solve the model parameters, the accuracy of the model parameter solution can be effectively improved, and the referenceability of the target model parameter can be effectively improved. Therefore, when the target model parameter is used in the subsequent construction process of the target photovoltaic array model, the modeling effect of the target photovoltaic array model can be effectively improved.

[0161] S308: Adjusting the initial photovoltaic array model by using the target model parameter solution to obtain a target photovoltaic array model.

[0162] S309: Determining an abnormality detection result of the photovoltaic array according to the multiple operation data and the target photovoltaic array model.

[0163] The description of S308-S309 can be specifically referred to the above embodiments, which will not be repeated here.

[0164] In this embodiment, multiple operational data of the photovoltaic array are acquired, and an initial photovoltaic array model is constructed. This initial model has corresponding model parameters. The initial particle positions corresponding to each particle in the pollination algorithm are then determined. Each particle describes a set of model parameters, and the particle position describes the model parameter solution for the corresponding model parameters. An initial fitness value corresponding to the initial particle position is determined. Based on the initial fitness value, a reference particle position is determined, and the particle is processed according to the reference particle position to determine the current particle position. In response to the current particle position satisfying the position setting condition, the model parameter solution corresponding to the current particle position is used as the target model parameter solution. Since the pollination algorithm is used to solve the model parameters, the accuracy of the model parameter solution is effectively improved, and the referenceability of the target model parameters is enhanced. Therefore, when the target model parameters are used in the subsequent construction process of the target photovoltaic array model, the modeling effect of the target photovoltaic array model is effectively improved. Finally, based on multiple operational data and the target photovoltaic array model, the anomaly detection results of the photovoltaic array are determined, thereby effectively improving the anomaly detection effect of the photovoltaic array.

[0165] Figure 4 This is a schematic diagram of the structure of an anomaly detection device for a photovoltaic array according to an embodiment of this disclosure.

[0166] like Figure 4 As shown, the anomaly detection device 40 for the photovoltaic array includes:

[0167] The acquisition module 401 is used to acquire multiple operating data of the photovoltaic array;

[0168] Module 402 is used to construct an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters;

[0169] Processing module 403 is used to process the model parameters using a flower pollination algorithm to determine the target model parameter solution;

[0170] The adjustment module 404 is used to adjust the initial photovoltaic array model using the target model parameter solution to obtain the target photovoltaic array model;

[0171] The determination module 405 is used to determine the anomaly detection results of the photovoltaic array based on multiple operating data and the target photovoltaic array model.

[0172] In some embodiments of this disclosure, such as Figure 5 As shown, Figure 5 This is a schematic diagram of the structure of an anomaly detection device for a photovoltaic array according to another embodiment of this disclosure. The construction module 502 includes:

[0173] The acquisition sub-module 4021 is configured to acquire a plurality of photovoltaic module parameters of the photovoltaic module.

[0174] The construction sub-module 4022 is configured to construct a photovoltaic module model according to the plurality of photovoltaic module parameters.

[0175] The generation sub-module 4023 is configured to generate an initial photovoltaic array model according to an output parameter of the photovoltaic module model and the plurality of photovoltaic module parameters.

[0176] In some embodiments of the present disclosure, the photovoltaic module model comprises a plurality of solar cells, and each solar cell has a corresponding single-diode model,

[0177] The construction sub-module 4022 is further configured to:

[0178] acquire a plurality of solar cell parameters of the solar cell;

[0179] construct the single-diode model according to the plurality of solar cell parameters;

[0180] perform series and / or parallel processing on the plurality of single-diode models to obtain the photovoltaic module model.

[0181] In some embodiments of the present disclosure, the processing module 403 comprises:

[0182] The first determination sub-module 4031 is configured to determine an initial particle position corresponding to each particle in the flower pollination algorithm, wherein each particle is used to correspond to a set of model parameters, and the particle position is used to correspond to a model parameter solution of the corresponding model parameter.

[0183] The first determination sub-module 4032 is configured to determine an initial fitness value corresponding to the initial particle position.

[0184] The third determination sub-module 4033 is configured to determine a reference particle position according to the initial fitness value.

[0185] The first processing sub-module 4034 is configured to perform target processing on the particle according to the reference particle position to determine a current particle position corresponding to the particle.

[0186] The second processing sub-module 4035 is configured to take the model parameter solution corresponding to the current particle position as a target model parameter solution in response to the current particle position satisfying a position setting condition.

[0187] In some embodiments of the present disclosure, the first determination sub-module 4031 is further configured to:

[0188] perform chaotic mapping processing on each particle to determine the initial particle position corresponding to each particle.

[0189] In some embodiments of the present disclosure, the second determining sub-module 4033 is further configured to:

[0190] determine the maximum fitness value from the plurality of initial fitness values;

[0191] determine the initial particle position corresponding to the maximum fitness value as the reference particle position.

[0192] In some embodiments of the present disclosure, the first processing sub-module 4034 is further configured to:

[0193] obtain the current pollination probability;

[0194] in response to the current pollination probability being greater than the preset pollination probability, processing the particle by using the cross-pollination mode to determine the current particle position corresponding to the particle; or

[0195] in response to the current pollination probability being less than or equal to the preset pollination probability, processing the particle by using the self-pollination mode to determine the current particle position corresponding to the particle.

[0196] In some embodiments of the present disclosure, the second processing sub-module 4035 is further configured to:

[0197] determine the current fitness value corresponding to the current particle position;

[0198] if the current fitness value is greater than the initial fitness value, determine the model parameter solution corresponding to the current particle position as the target model parameter solution.

[0199] In some embodiments of the present disclosure, the determining module 405 is further configured to:

[0200] determine the reference running data from the plurality of running data;

[0201] input the initial running data into the target photovoltaic array model to obtain an initial running result output by the target photovoltaic array model;

[0202] input the reference running data into the target photovoltaic array model to obtain a reference running result output by the target photovoltaic array model;

[0203] determine whether the reference running result and the initial running result satisfy a matching condition;

[0204] if the reference running result and the initial running result do not satisfy the matching condition, determine that the photovoltaic array has a running abnormality.

[0205] The photovoltaic array anomaly detection method provided in the above Figures 1 to 3 embodiments, the present disclosure further provides a photovoltaic array anomaly detection device. Since the photovoltaic array anomaly detection device provided in the embodiments of the present disclosure corresponds to the photovoltaic array anomaly detection method provided in the above Figures 1 to 3Correspondingly, the abnormality detection method of the photovoltaic array provided in the embodiments is also applicable to the abnormality detection device of the photovoltaic array provided in the embodiments of the present disclosure, and details are not described herein.

[0206] In this embodiment, a plurality of operation data of the photovoltaic array are acquired, and an initial photovoltaic array model is constructed, where the initial photovoltaic array model has corresponding model parameters. Then, the model parameters are processed by using the pollination algorithm to determine a target model parameter solution, and the initial photovoltaic array model is adjusted by using the target model parameter solution to obtain a target photovoltaic array model. In addition, the abnormality detection result of the photovoltaic array is determined according to the plurality of operation data and the target photovoltaic array model. Since the model parameters of the constructed initial photovoltaic array model are solved and processed by using the pollination algorithm, the accuracy of solving the model parameters of the photovoltaic array model can be effectively improved, and the model construction effect of the photovoltaic array model can be effectively improved, so that the abnormality detection effect of the photovoltaic array can be effectively improved when the constructed target photovoltaic array model is used for the abnormality detection of the photovoltaic array.

[0207] To achieve the above-mentioned embodiments, the present disclosure further provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the abnormality detection method of the photovoltaic array provided in the foregoing embodiments of the present disclosure when executing the program.

[0208] To achieve the above-mentioned embodiments, the present disclosure further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the abnormality detection method of the photovoltaic array provided in the foregoing embodiments of the present disclosure.

[0209] To achieve the above-mentioned embodiments, the present disclosure further provides a computer program product, wherein the instructions in the computer program product are executed by a processor to implement the abnormality detection method of the photovoltaic array provided in the foregoing embodiments of the present disclosure.

[0210] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 6 The electronic device 12 shown is merely one example and should not be taken as limiting the scope of functionality or use of embodiments of the present disclosure.

[0211] As shown in Figure 6 The electronic device 12 is in the form of a general computing device. Components of the electronic device 12 can include, but are not limited to, one or more processors or processing units 16, a system memory 28, and a bus 18 that connects the various system components, including the system memory 28 and the processing unit 16.

[0212] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures. By way of example, these architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0213] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that is accessible by electronic device 12 and includes both volatile and non-volatile media, removable and non-removable media.

[0214] Memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (not shown and typically called a "hard drive"). Figure 6

[0215] Although Figure 6 not shown in FIG. 1, a disk drive, a CD-ROM drive, a DVD-ROM drive, or other optical disk drive, can be provided, and can be connected to bus 18 by one or more disk drive interfaces. Storage 28 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.

[0216] ​Program / utility 40 having a set of program modules 42 can be stored in memory 28, for example, including an operating system, one or more application programs, other program modules, and program data, each or some combination thereof, which may

[0217] Electronic device 12 can also communicate with one or more external devices 14 such as a keyboard or pointing device, a display 24, etc.; other devices such as are well known in the art. Communication with such external devices can occur, for example, through input / output (I / O) interfaces 22. Still yet, electronic device 12 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through network adapter 20. As an example, network adapter 20 can include a modem, a network card (wireless or wired), or other well-known interface devices. As depicted, network adapter 20 communicates with the other

[0218] Processing unit(s) 16 can execute instructions and manipulate data to perform a variety of functions, in response to the execution of the program stored in system memory 28. For example, processing unit(s) 16 can perform the anomaly detection method for photovoltaic arrays described in the embodiments above.

[0219] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. The disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure that come within known

[0220] It is to be understood that the disclosure is not limited to the precise construction that has been described and illustrated and that changes can be made in various embodiments and in the details of the disclosed embodiments without departing from the scope of the disclosure. The scope of the disclosure is defined only by the language of the claims.

[0221] It should be noted that in the description of the present disclosure, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present disclosure, the meaning of "a plurality of" is two or more, unless otherwise stated.

[0222] Any process or method descriptions or any other descriptions in flow charts or described herein in other ways can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing specific logic functions or other steps in the process, and the various embodiments of the present disclosure include additional implementations in which the functions are carried out in different orders, in substantially simultaneous fashion, or in reverse order, depending on the functionality involved, as will be understood by those skilled in the art of the embodiments of the present disclosure.

[0223] It should be understood that various parts of the present disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: discrete logic circuit with logic gate circuit for implementing logic functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0224] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiments can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium, and the programs include one or a combination of steps of the method embodiments when executed.

[0225] In addition, each functional unit in each embodiment of the present disclosure can be integrated in one processing module, or each unit can exist physically separately, or two or more units can be integrated in one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of software functional module. The integrated module, if realized in the form of software functional module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0226] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0227] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In the specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any suitable manner in one or more embodiments or examples.

[0228] Although the embodiments of the present disclosure have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present disclosure, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present disclosure.

Claims

1. A method for anomaly detection in a photovoltaic array, characterized in that, include: Acquire multiple operational data points from the photovoltaic array; Construct an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters; Each particle in the flower pollination algorithm is subjected to chaotic mapping to determine the initial particle position corresponding to each particle; wherein each particle is used to describe a set of model parameters, and the particle position is used to describe the model parameter solution corresponding to the model parameters. Determine the initial fitness value corresponding to the initial particle position; The maximum fitness value is determined from the plurality of initial fitness values; The initial particle position corresponding to the maximum fitness value is used as the reference particle position; Get the current pollination probability; In response to the current pollination probability being greater than a preset pollination probability, a cross-pollination method combining wind disturbance is employed to process the particles, thereby determining the current particle position corresponding to the particle. The cross-pollination method combining wind disturbance is as follows: Where, θ i X represents the wind direction acting on the i-th particle. * For the reference particle position, Initial particle position, W represents the current particle position. i (t) represents the distance Lévy traveled, where t is a function variable; or In response to the current pollination probability being less than or equal to the preset pollination probability, the particle is processed using a self-pollination method incorporating a mutation mechanism to determine the current particle position corresponding to the particle. The self-pollination method incorporating a mutation mechanism is as follows: in, Initial particle position, This indicates the current particle position, and `pop` indicates the number of particles. This represents the initial particle position of another particle, where ε is a Gaussian random number between 0 and 1, and α is a random number between 0 and 1. Determine the current fitness value corresponding to the current particle position; If the current fitness value is greater than the initial fitness value, then the model parameter solution corresponding to the current particle position is taken as the target model parameter solution; The initial photovoltaic array model is adjusted using the target model parameter solution to obtain the target photovoltaic array model; Based on multiple operational data and the target photovoltaic array model, the anomaly detection results of the photovoltaic array are determined.

2. The method as described in claim 1, characterized in that, The initial photovoltaic array model includes: multiple photovoltaic module models; The construction of the initial photovoltaic array model includes: Obtain multiple photovoltaic module parameters; The photovoltaic module model is constructed based on multiple photovoltaic module parameters; The initial photovoltaic array model is generated based on the output parameters of the photovoltaic module model and multiple photovoltaic module parameters.

3. The method as described in claim 2, characterized in that, The photovoltaic module model includes: multiple solar cells, each solar cell having a corresponding single diode model. The construction of the photovoltaic module model includes: Obtain multiple solar cell parameters of the solar cell; The single diode model is constructed based on multiple solar cell parameters; Multiple single-diode models are connected in series and / or in parallel to obtain the photovoltaic module model.

4. The method as described in claim 1, characterized in that, The step of determining the anomaly detection result of the photovoltaic array based on multiple operational data and the target photovoltaic array model includes: Determine reference operating data from the plurality of operating data; The initial operating data is input into the target photovoltaic array model to obtain the initial operating results output by the target photovoltaic array model; The reference operating data is input into the target photovoltaic array model to obtain the reference operating results output by the target photovoltaic array model; Determine whether the reference running results and the initial running results meet the matching conditions; If the reference operating results and the initial operating results do not meet the matching conditions, then it is determined that the photovoltaic array has an operating abnormality.

5. An anomaly detection device for a photovoltaic array, characterized in that, include: The acquisition module is used to acquire multiple operational data of the photovoltaic array; A construction module is used to construct an initial photovoltaic array model, wherein the initial photovoltaic array model has corresponding model parameters; The processing module is used to process the model parameters using a flower pollination algorithm to determine the target model parameter solution; An adjustment module is used to adjust the initial photovoltaic array model using the target model parameter solution to obtain the target photovoltaic array model; The determination module is used to determine the anomaly detection result of the photovoltaic array based on multiple operational data and the target photovoltaic array model; The processing module includes: The first determining submodule is used to perform chaotic mapping processing on each particle in the flower pollination algorithm to determine the initial particle position corresponding to each particle, wherein each particle is used to describe a set of model parameters, and the particle position is used to describe the model parameter solution of the corresponding model parameters. The second determining submodule is used to determine the initial fitness value corresponding to the initial particle position; The third determining submodule is used to determine the maximum fitness value from the plurality of initial fitness values; and to use the initial particle position corresponding to the maximum fitness value as the reference particle position; The first processing submodule is used to obtain the current pollination probability; In response to the current pollination probability being greater than a preset pollination probability, a cross-pollination method combining wind disturbance is employed to process the particles, thereby determining the current particle position corresponding to the particle. The cross-pollination method combining wind disturbance is as follows: Where, θ i X represents the wind direction acting on the i-th particle. * For the reference particle position, Initial particle position, W represents the current particle position. i (t) represents the distance Lévy traveled, where t is a function variable; or In response to the current pollination probability being less than or equal to the preset pollination probability, the particle is processed using a self-pollination method incorporating a mutation mechanism to determine the current particle position corresponding to the particle. The self-pollination method incorporating a mutation mechanism is as follows: in, Initial particle position, This indicates the current particle position, and `pop` indicates the number of particles. This represents the initial particle position of another particle, where ε is a Gaussian random number between 0 and 1, and α is a random number between 0 and 1. The second processing submodule is used to determine the current fitness value corresponding to the current particle position; if the current fitness value is greater than the initial fitness value, then the model parameter solution corresponding to the current particle position is used as the target model parameter solution.

6. The apparatus as claimed in claim 5, characterized in that, The initial photovoltaic array model includes: multiple photovoltaic module models; The building module includes: The acquisition submodule is used to acquire multiple photovoltaic module parameters; A submodule is constructed to build the photovoltaic module model based on multiple photovoltaic module parameters; A generation submodule is used to generate the initial photovoltaic array model based on the output parameters of the photovoltaic module model and multiple photovoltaic module parameters.

7. The apparatus as claimed in claim 6, characterized in that, The photovoltaic module model includes: multiple solar cells, each solar cell having a corresponding single diode model. The construction submodule is further configured to: Obtain multiple solar cell parameters of the solar cell; The single diode model is constructed based on multiple solar cell parameters; Multiple single-diode models are connected in series and / or in parallel to obtain the photovoltaic module model.

8. The apparatus as claimed in claim 5, characterized in that, The determining module is further configured to: Determine reference operating data from the plurality of operating data; The initial operating data is input into the target photovoltaic array model to obtain the initial operating results output by the target photovoltaic array model; The reference operating data is input into the target photovoltaic array model to obtain the reference operating results output by the target photovoltaic array model; Determine whether the reference running results and the initial running results meet the matching conditions; If the reference operating results and the initial operating results do not meet the matching conditions, then it is determined that the photovoltaic array has an operating abnormality.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

Images