Monitoring methods, devices and systems for photovoltaic power generation systems

Abstract

This disclosure relates to a monitoring method, apparatus, and system for a photovoltaic power generation system. The monitoring method acquires the current operating parameters of each photovoltaic module and the residual values ​​of the photovoltaic modules at multiple historical time points within a preset time period prior to the current time. Based on the dynamic residual threshold, it can accurately screen out photovoltaic modules with abnormal operation. Furthermore, when it is determined that a photovoltaic module is operating abnormally based on the dynamic residual threshold and the current operating parameters, it can display a first fault prompt message including a first fault type identifier and a photovoltaic module identifier. This effectively improves the efficiency of locating faulty photovoltaic modules, shortens the time required for troubleshooting photovoltaic system faults, and further improves the maintenance efficiency of the photovoltaic system and reduces operation and maintenance costs.

Description

Technical Field

[0001] This disclosure relates to the field of photovoltaic power generation technology, and more specifically, to a monitoring method, device, and system for a photovoltaic power generation system. Background Technology

[0002] As an important form of clean energy, photovoltaic power generation has seen its installed capacity continue to expand. However, due to the wide distribution of photovoltaic power plants and the large number of photovoltaic modules, traditional operation and maintenance methods struggle to quickly and accurately pinpoint the fault when a module malfunctions. This often leads to high operation and maintenance costs due to the broad scope and lengthy troubleshooting process. Summary of the Invention

[0003] The first aspect of this disclosure provides a monitoring method for a photovoltaic power generation system, the photovoltaic power generation system including multiple photovoltaic modules, the method comprising: For each photovoltaic module, the current operating parameters of the photovoltaic module and the residual values ​​of the photovoltaic module at multiple historical time points within a preset time period before the current time are obtained. The residual value is the difference between the expected value and the detected value of the specified parameter. The current dynamic residual threshold is determined based on the residual values ​​at the multiple historical time points; If the photovoltaic module is determined to be operating abnormally based on the dynamic residual threshold and the current operating parameters, a first fault prompt message is displayed. The first fault prompt message includes a first fault type identifier and a photovoltaic module identifier.

[0004] In some embodiments, determining the current dynamic residual threshold based on the residual values ​​at the plurality of historical time points includes: Determine the mean and standard deviation of the residuals at the multiple historical time points; Obtain the product of the current sensitivity coefficient and the standard deviation; The dynamic residual threshold is determined based on the average value and the product.

[0005] In some embodiments, the dynamic residual threshold includes an upper limit and a lower limit, and determining the dynamic residual threshold based on the average value and the product includes: The sum of the average value and the product is used as the upper limit of the dynamic residual threshold; The difference between the average value and the product is used as the lower limit of the dynamic residual threshold.

[0006] In some embodiments, the method further includes: Obtain first confirmation result information for the first fault prompt information input by the user, wherein the first confirmation result information includes a confirmation identifier or a false alarm identifier; If it is determined that the first confirmation result information includes a confirmation identifier, the sensitivity coefficient remains unchanged; If it is determined that the first confirmation result information includes a false alarm identifier, the sensitivity coefficient is increased to obtain an updated sensitivity coefficient.

[0007] In some embodiments, the plurality of photovoltaic modules form at least one photovoltaic string, and the method further includes: The target residual value of each photovoltaic module is determined based on the current operating parameters of each photovoltaic module to obtain the residual sequence of the photovoltaic string at the current time; Determine the standard distance between each target residual value in the residual sequence and the mean of the residual sequence; Obtain the preset outlier detection threshold; Identify the target identifiers of photovoltaic modules in the photovoltaic string whose standard distance is greater than the preset outlier determination threshold; Generate and display a second fault message including the target identifier and the second fault type identifier.

[0008] In some embodiments, the method further includes: Obtain second confirmation result information for the second fault prompt information input by the user, the second confirmation result information including a confirmation identifier or a false alarm identifier; If it is determined that the second confirmation result information includes a confirmation identifier, the preset outlier determination threshold remains unchanged; If it is determined that the second confirmation result information includes a false alarm identifier, the preset outlier determination threshold is increased to obtain an updated preset outlier determination threshold.

[0009] In some embodiments, the method further includes: If the user inputs information about missed faults, the sensitivity coefficient and / or the preset outlier determination threshold are reduced.

[0010] In some embodiments, determining that the photovoltaic module is operating abnormally based on the dynamic residual threshold and the current operating parameters includes: Determine the target residual value of the photovoltaic module based on the current operating parameters; The normal residual range is determined based on the dynamic residual threshold. If it is determined that the target residual value does not belong to the normal residual range, the number of anomalies of the photovoltaic module is incremented by one; if it is determined that the target residual value belongs to the normal residual range, the number of anomalies is reset to zero to obtain the updated number of anomalies. If the current number of anomalies exceeds a preset threshold, the photovoltaic module is determined to be malfunctioning.

[0011] In some embodiments, the current operating parameters include rated values ​​and target detection values ​​of specified parameters, backsheet temperature, and irradiance. Determining the target residual value of the photovoltaic module based on the current operating parameters includes: Based on the rated values ​​of the specified parameters, the backplate temperature and the irradiance determine the target expected value of the specified parameters; The target residual value is determined based on the target expected value and the target detected value.

[0012] In some embodiments, determining the target expected value of the specified parameter based on the rated value of the specified parameter, the backsheet temperature, and the irradiance includes: Obtain the target prediction model corresponding to the specified parameter. The target prediction model is used to characterize the expected value of the specified parameter under different rated values ​​at different backsheet temperatures and irradiances. The rated value, the backplate temperature, and the irradiance are input into the target prediction model to obtain the target expected value output by the target prediction model.

[0013] A second aspect of this disclosure provides a monitoring device for a photovoltaic power generation system, comprising: The data acquisition module is configured to acquire, for each photovoltaic module, the current operating parameters of the photovoltaic module and the residual values ​​of the photovoltaic module at multiple historical time points within a preset time period before the current time, wherein the residual value is the difference between the expected value and the detected value of the specified parameter; The determination module is configured to determine the current dynamic residual threshold based on the residual values ​​at the multiple historical time points; The operation and maintenance module is configured to display a first fault prompt message when the photovoltaic module is determined to be operating abnormally based on the dynamic residual threshold and the current operating parameters. The first fault prompt message includes a first fault type identifier and a photovoltaic module identifier.

[0014] In some embodiments, the determining module is configured to: determine the average and standard deviation of the residual values ​​at the plurality of historical time points; take the product of the current sensitivity coefficient and the standard deviation; and determine the dynamic residual threshold based on the average and the product.

[0015] In some embodiments, the dynamic residual threshold includes an upper limit and a lower limit, and the determining module is configured to: use the sum of the average value and the product as the upper limit of the dynamic residual threshold; and use the difference between the average value and the product as the lower limit of the dynamic residual threshold.

[0016] In some embodiments, the data acquisition module is further configured to acquire first confirmation result information input by the user for the first fault prompt information, wherein the first confirmation result information includes a confirmation identifier or a false alarm identifier; The operation and maintenance module is further configured to keep the sensitivity coefficient unchanged when it is determined that the first confirmation result information includes a confirmation identifier; and to increase the sensitivity coefficient to obtain an updated sensitivity coefficient when it is determined that the first confirmation result information includes a false alarm identifier.

[0017] In some embodiments, the plurality of photovoltaic modules form at least one photovoltaic string. The determining module is configured to determine the target residual value of the photovoltaic module based on the current operating parameters of each photovoltaic module, so as to obtain the residual sequence of the photovoltaic string at the current time; and determine the standard distance between each target residual value in the residual sequence and the mean of the residual sequence. The data acquisition module is configured to acquire a preset outlier determination threshold. The determining module is further configured to determine the target identifier of a photovoltaic module in the photovoltaic string whose standard distance is greater than the preset outlier determination threshold; The operation and maintenance module is configured to generate and display a second fault prompt message that includes the target identifier and the second fault type identifier.

[0018] In some embodiments, the operation and maintenance module is further configured to obtain second confirmation result information for the second fault prompt information input by the user, the second confirmation result information including a confirmation identifier or a false alarm identifier; if it is determined that the second confirmation result information includes a confirmation identifier, the preset outlier determination threshold is kept unchanged; if it is determined that the second confirmation result information includes a false alarm identifier, the preset outlier determination threshold is increased to obtain an updated preset outlier determination threshold.

[0019] In some embodiments, the operation and maintenance module is further configured to reduce the sensitivity coefficient and / or the preset outlier determination threshold when it is determined that fault missed reporting information input by the user has been obtained.

[0020] In some embodiments, the operation and maintenance module is configured to: determine the target residual value of the photovoltaic module based on the current operating parameters; and determine the normal residual range based on the dynamic residual threshold. If it is determined that the target residual value does not belong to the normal residual range, the number of anomalies of the photovoltaic module is incremented by one; if it is determined that the target residual value belongs to the normal residual range, the number of anomalies is reset to zero to obtain the updated number of anomalies. If the current number of anomalies exceeds a preset threshold, the photovoltaic module is determined to be malfunctioning.

[0021] In some embodiments, the current operating parameters include the rated value and target detection value of the specified parameter, backplane temperature and irradiance. The operation and maintenance module is configured to: determine the target expected value of the specified parameter based on the rated value of the specified parameter, the backplane temperature and the irradiance; and determine the target residual value based on the target expected value and the target detection value.

[0022] In some embodiments, the operation and maintenance module is configured to: obtain a target prediction model corresponding to the specified parameter, wherein the target prediction model is used to characterize the expected value of the specified parameter corresponding to different rated values ​​under different backplane temperatures and irradiances; input the rated value, the backplane temperature and the irradiance into the target prediction model to obtain the target expected value output by the target prediction model.

[0023] A third aspect of this disclosure provides a photovoltaic system including the monitoring device described in the second aspect above.

[0024] A fourth aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0025] The fifth aspect of this disclosure provides an electronic device comprising: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method described in the first aspect above.

[0026] A sixth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0027] The above technical solution, by acquiring the current operating parameters of each photovoltaic module and the residual values ​​of multiple historical time points of the photovoltaic module within a preset time period before the current time, can accurately filter out photovoltaic modules with abnormal operation based on the dynamic residual threshold. Furthermore, when it is determined that the photovoltaic module is operating abnormally based on the dynamic residual threshold and the current operating parameters, it can display a first fault prompt message including a first fault type identifier and a photovoltaic module identifier. This can effectively improve the efficiency of locating faulty photovoltaic modules, shorten the time required for troubleshooting photovoltaic system faults, and thus further improve the maintenance efficiency of photovoltaic systems and reduce operation and maintenance costs.

[0028] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0029] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a monitoring method for a photovoltaic power generation system according to an exemplary embodiment of this disclosure; Figure 2 It is based on Figure 1 The illustrated embodiment presents a flowchart of a monitoring method for a photovoltaic power generation system; Figure 3 Based on this disclosure Figure 1 The illustrated embodiment shows a flowchart of another monitoring method for a photovoltaic power generation system; Figure 4 Based on this disclosure Figure 1 The illustrated embodiment shows a flowchart of another monitoring method for a photovoltaic power generation system; Figure 5 Based on this disclosure Figure 1 The illustrated embodiment shows a flowchart of another monitoring method for a photovoltaic power generation system; Figure 6 Based on this disclosure Figure 1 The illustrated embodiment shows a flowchart of another monitoring method for a photovoltaic power generation system; Figure 7 It is based on Figure 6 The illustrated embodiment presents a flowchart of a monitoring method for a photovoltaic power generation system; Figure 8 This is a block diagram illustrating a monitoring device for a photovoltaic power generation system according to an exemplary embodiment of the present disclosure; Figure 9 This is a block diagram illustrating an electronic device according to an exemplary embodiment; Figure 10 This is a block diagram illustrating another electronic device according to an exemplary embodiment. Detailed Implementation

[0030] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0031] Before detailing the specific embodiments of this disclosure, the application scenarios of this disclosure are first described below. This disclosure can be applied to photovoltaic power generation systems, which may include one or more photovoltaic strings. Each photovoltaic string may include multiple photovoltaic modules, and each photovoltaic module can be understood as an independent power generation unit composed of multiple photovoltaic cells connected in series or parallel. The photovoltaic power generation system may also include module-level data acquisition equipment, environmental monitoring equipment, data communication equipment, and a cloud server.

[0032] The component-level data acquisition equipment can be a power optimizer. Each optimizer can be installed on the back of a photovoltaic module to collect data such as voltage, current, power, and operating temperature of each photovoltaic module. The collected data is then uploaded to the photovoltaic inverter, which in turn uploads the data to the data communication equipment via RS485 communication. Environmental monitoring equipment may include sensors for irradiance, ambient temperature, humidity, wind speed, wind direction, and atmospheric pressure. In addition, this disclosure also requires the installation of a backsheet temperature sensor on the back of the photovoltaic module to collect data such as temperature, humidity, wind speed, wind direction, module backsheet temperature, tilt radiation, and atmospheric pressure in real time. Data communication equipment may include a data gateway for connecting field devices (optimizers, sensors) to a cloud server. This data communication equipment is responsible for data aggregation, protocol conversion, edge computing, and remote communication. It can have multiple physical interfaces (such as RS485, RS232, DI / DO, Ethernet) and wireless interfaces (4G / 5G, Wi-Fi, LoRaWAN), enabling simultaneous connection and polling of data from devices of different manufacturers and using different protocols. It also features data caching and breakpoint resume capabilities to ensure no data loss during network interruptions. The cloud server can deploy an intelligent analysis module and an operation and maintenance management module. The intelligent analysis module may include an environmental compensation model and multi-dimensional anomaly detection algorithms to achieve intelligent analysis and fault diagnosis of component-level data. The operation and maintenance management module provides alarm management, fault diagnosis, and operation and maintenance decision support.

[0033] It should be noted that the optimizer in this component-level data acquisition device can be installed on the back end of each photovoltaic module in a one-to-one manner. The input end of the optimizer is connected to the photovoltaic module, and the output ends are connected in series and finally fed into the inverter. Each component-level data acquisition device acts as an intelligent data acquisition node, monitoring and reporting the core operating parameters (including but not limited to voltage, current, power, and temperature) of its associated component in real time. The optimizer uploads data such as voltage, current, power, and operating temperature of each component to the photovoltaic inverter via power line carrier communication, and the photovoltaic inverter then uploads the data to the data communication module via RS485 communication. The irradiance sensor in the environmental monitoring equipment is installed parallel to the plane of the photovoltaic module, and the installation height is consistent with the average height of the photovoltaic module array to ensure no shading, and it is regularly calibrated on-site.

[0034] In related technologies, due to the large number and wide distribution of photovoltaic modules in photovoltaic systems, when a photovoltaic module fails, traditional operation and maintenance methods are difficult to quickly and accurately locate the fault point, which easily leads to high operation and maintenance costs due to the wide scope of troubleshooting and the long troubleshooting time.

[0035] To address the aforementioned technical issues, this disclosure provides a monitoring method, device, and system for a photovoltaic power generation system. This monitoring method acquires the current operating parameters of each photovoltaic module and the residual values ​​of the photovoltaic modules at multiple historical time points within a preset time period prior to the current time. Based on this dynamic residual threshold, it can accurately filter out photovoltaic modules with operational anomalies. Furthermore, when an abnormal operation of a photovoltaic module is determined based on the dynamic residual threshold and the current operating parameters, it can display a first fault warning message including a first fault type identifier and a photovoltaic module identifier. This effectively improves the efficiency of locating faulty photovoltaic modules, shortens the time required for troubleshooting photovoltaic system faults, and further enhances the maintenance efficiency of the photovoltaic system while reducing operation and maintenance costs.

[0036] The specific embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0037] Figure 1 This is a flowchart illustrating a monitoring method for a photovoltaic power generation system according to an exemplary embodiment of this disclosure, such as... Figure 1 As shown, the monitoring method for this photovoltaic power generation system may include: Step 101: For each photovoltaic module, obtain the current operating parameters of the photovoltaic module and the residual values ​​of the photovoltaic module at multiple historical time points within a preset time period before the current time.

[0038] The residual value is the difference between the expected value and the detected value of a specified parameter, which can be current and / or voltage. The expected value can be predicted based on current operating parameters, which may include the rated value and target detected value of the specified parameter, backplane temperature, and irradiance. The preset time period can be 15 minutes, half an hour, one hour, or two hours. The parameter values ​​corresponding to the specified parameter can be collected at a preset frequency; for example, voltage and current can be collected every 2 seconds. Multiple voltage and current detection values ​​can be collected within one hour prior to the current time.

[0039] It should be noted that the rated and target detection values ​​of the specified parameters, as well as the backsheet temperature and irradiance, can all be obtained by the module-level data acquisition equipment in the photovoltaic power generation system. The residual value at each time point can be stored in a preset storage unit. This step can obtain the residual values ​​at multiple historical time points by accessing this preset storage unit; the process of obtaining the residual value at each time point can be as follows: Figure 2 ( Figure 2 It is based on Figure 1 The flowchart shown in the embodiment illustrates a monitoring method for a photovoltaic power generation system, which includes: S11, Based on the rated values ​​of the specified parameters, the backplate temperature and the irradiance are used to determine the target expected value of the specified parameters.

[0040] In this step, a target prediction model corresponding to the specified parameter can be obtained. The target prediction model is used to characterize the expected value of the specified parameter under different rated values ​​at different backsheet temperatures and irradiances. The rated value, the backsheet temperature, and the irradiance are input into the target prediction model to obtain the target expected value output by the target prediction model.

[0041] For example, when the specified parameter is current, the calculation process corresponding to the target prediction model can be as follows: I_expected = (Irradiance / 1000) I_rated [1 +γ [(T_backplate - 25)]; In the above formula, I_expected is the expected photovoltaic module current, Irradiance is the real-time irradiance, I_rated is the rated current of the photovoltaic module, γ is the photovoltaic module current temperature coefficient, and T_backplate is the photovoltaic module backsheet temperature. Different backsheet temperatures correspond to different photovoltaic module current temperature coefficients.

[0042] When the specified parameter is voltage, the calculation process for the target prediction model can be shown as follows: V_expected = V_rated + (T_backplate - 25) TC_V; Where V_expected is the expected voltage of the photovoltaic module, V_rated is the rated voltage of the photovoltaic module, T_backplate is the backsheet temperature of the photovoltaic module, and TC_V is the voltage temperature coefficient of the photovoltaic module. Different backsheet temperatures correspond to different voltage temperature coefficients for the photovoltaic module.

[0043] S12, determine the target residual value based on the target expected value and the target detected value.

[0044] The difference between the expected value of the target and the detected value of the target can be used as the residual value of the target.

[0045] By using S11 and S12 above, the residual value at each time point can be effectively obtained, thus providing a reliable data basis for the subsequent dynamic residual threshold.

[0046] Step 102: Determine the current dynamic residual threshold based on the residual values ​​at the multiple historical time points.

[0047] This step can be done Figure 3 Perform the steps shown. Figure 3 Based on this disclosure Figure 1 The flowchart of another monitoring method for a photovoltaic power generation system shown in the embodiment is as follows: Figure 3 As shown, step 102 may include: Step 1021: Determine the average and standard deviation of the residual values ​​at the multiple historical time points.

[0048] Step 1022: Obtain the product of the current sensitivity coefficient and the standard deviation.

[0049] Step 1023: Determine the dynamic residual threshold based on the average value and the product.

[0050] The dynamic residual threshold includes an upper limit and a lower limit. In this step, the sum of the average value and the product can be used as the upper limit of the dynamic residual threshold, and the difference between the average value and the product can be used as the lower limit of the dynamic residual threshold.

[0051] For example, if the mean of a specified parameter within the moving window is MA, the moving standard deviation is MSD, and the preset sensitivity coefficient is k, then this upper limit value can be expressed as: This lower limit can be expressed as , where the sensitivity coefficient k is an adjustable parameter.

[0052] Step 103: If the photovoltaic module is found to be operating abnormally based on the dynamic residual threshold and the current operating parameters, a first fault prompt message is displayed. The first fault prompt message includes a first fault type identifier and a photovoltaic module identifier.

[0053] The first fault type identifier can be identification information used to characterize that the current fault belongs to a fault determined based on a dynamic residual threshold.

[0054] In this step, the implementation method for determining the photovoltaic module's operational anomaly based on the dynamic residual threshold and the current operating parameters can be as follows: Figure 4 ( Figure 4 Based on this disclosure Figure 1 As shown in the flowchart of another photovoltaic power generation system monitoring method illustrated in the embodiment, the implementation process of step 103 may include: Step 1031: Determine the target residual value of the photovoltaic module based on the current operating parameters.

[0055] The implementation method for this step can be found in [reference needed]. Figure 2 The relevant descriptions of S11 to S12 are not repeated here.

[0056] Step 1032: Determine the normal residual range based on the dynamic residual threshold.

[0057] The dynamic parameter threshold can include an upper limit and a lower limit. The normal residual range can be an interval formed by the upper and lower limits. For example, if the upper limit is 'a' and the lower limit is 'b', then the normal parameter range is... .

[0058] Step 1033: If it is determined that the target residual value does not belong to the normal residual range, the number of anomalies of the photovoltaic module is incremented by one; if it is determined that the target residual value belongs to the normal residual range, the number of anomalies is reset to zero to obtain the updated number of anomalies.

[0059] Step 1034: If the current number of anomalies is greater than a preset threshold, the photovoltaic module is determined to be malfunctioning.

[0060] Through steps 1031 to 1034, photovoltaic modules with abnormal operation can be effectively identified. Since the photovoltaic module is identified as having abnormal operation when the current number of abnormalities exceeds a preset threshold, it can be alerted when the abnormality exceeds the normal residual range for N consecutive times. This effectively filters out the instantaneous interference caused by passing clouds and improves the accuracy of fault detection results.

[0061] The above technical solution can accurately screen out photovoltaic modules with abnormal operation based on the dynamic residual threshold. Furthermore, when it is determined that the photovoltaic module is operating abnormally based on the dynamic residual threshold and the current operating parameters, it can display a first fault prompt message including a first fault type identifier and a photovoltaic module identifier. This can effectively improve the efficiency of locating faulty photovoltaic modules, which is conducive to further improving the maintenance efficiency of photovoltaic systems, shortening the time required for troubleshooting photovoltaic system faults, and thus reducing operation and maintenance costs.

[0062] Figure 5 Based on this disclosure Figure 1 The flowchart shown in the embodiment illustrates another monitoring method for a photovoltaic power generation system, as follows: Figure 5 As shown, the method is in Figure 1 After displaying the first fault message as described in step 103, the method may further include: Step 104: Obtain the first confirmation result information input by the user for the first fault prompt information. The first confirmation result information includes a confirmation identifier or a false alarm identifier.

[0063] The confirmation identifier can be a user-input character (such as letters, numbers, Chinese characters, etc.), icon (such as an arrow, exclamation mark, etc.), color, or pattern design used to indicate that the first fault prompt is a correct fault prompt. The false alarm identifier can be a different character, icon, color, or pattern design than the confirmation identifier. For example, "1", "Y", or "Confirm" can be used as the confirmation identifier, and "0", "F", or "N" can be used as the false alarm identifier.

[0064] Step 105: If it is determined that the first confirmation result information includes a confirmation identifier, the sensitivity coefficient remains unchanged.

[0065] Step 106: If it is determined that the first confirmation result information includes a false alarm identifier, the sensitivity coefficient is increased to obtain an updated sensitivity coefficient.

[0066] Specifically, after increasing the sensitivity coefficient, the upper limit of the dynamic residual threshold, with the mean value MA and the standard deviation MSD remaining unchanged, is... Increase, lower limit value The normal residual range becomes smaller. Increase. As the normal residual range increases, the probability of false alarms will decrease, thereby enabling the automatic adjustment of the accuracy of the fault detection process.

[0067] Figure 6 Based on this disclosure Figure 1 The flowchart shown in the embodiment illustrates another monitoring method for a photovoltaic power generation system, as follows: Figure 6As shown, the method may further include: Step 201: Determine the target residual value of the photovoltaic module based on the current operating parameters of each photovoltaic module to obtain the residual sequence of the photovoltaic string at the current time.

[0068] Multiple photovoltaic modules can form at least one photovoltaic string.

[0069] It should be noted that the specific implementation method for determining the target residual value of each photovoltaic module based on its current operating parameters in this step can be found in [link to relevant documentation]. Figure 2 The relevant descriptions of S11 to S12 are not repeated here. Having obtained the target residual value corresponding to each photovoltaic module in the photovoltaic string, the target residual value corresponding to each photovoltaic module in the photovoltaic string can be used as an element in the residual sequence to form the residual sequence of the photovoltaic string.

[0070] Step 202: Determine the standard distance between each target residual value in the residual sequence and the mean of the residual sequence.

[0071] In this step, the data in the residual sequence can be assumed to follow a normal distribution (or approximately a normal distribution). The Z-score (standard score) of each data point (i.e., each target residual value) can be calculated to obtain the standard distance. The formula for calculating the Z-score can be: In the formula, x is the target residual value, μ is the mean of the residual sequence, i.e., the mean of the data in the residual sequence, and σ is the standard deviation of the data in the residual sequence.

[0072] Step 203: Obtain the preset outlier determination threshold.

[0073] Step 204: Determine the target identifier of the photovoltaic module in the photovoltaic string whose standard distance is greater than the preset outlier determination threshold.

[0074] The purpose of this step is to identify outliers using the standard distance (i.e., Z-score) between the data point and the mean. For example, if the preset outlier detection threshold is 3σ, then when... If the i-th element in the residual sequence is determined to be an outlier, the target identifier of the outlier is determined, and a second fault message is generated based on the target identifier.

[0075] Step 205: Generate and display a second fault prompt message including the target identifier and the second fault type identifier.

[0076] The second fault type identifier can be identification information used to indicate that the current fault belongs to a fault determined based on a preset outlier determination threshold. For example, when the first fault type identifier is the text "type 1", the second fault type identifier can be the text "type 2"; when the first fault type identifier is the text "vertical fault", the second fault type identifier can be the text "lateral fault".

[0077] The above technical solution can perform a horizontal comparison of photovoltaic modules in the photovoltaic string based on the residual sequence corresponding to the photovoltaic string, and screen out faults that are not sensitive to uniform environmental changes (such as a decrease in overall irradiance) but are more sensitive to sudden faults (such as the breakage of a single module or the detachment of wiring), thereby helping to further improve the efficiency of determining sudden fault points.

[0078] Figure 7 It is based on Figure 6 The illustrated embodiment presents a flowchart of a monitoring method for a photovoltaic power generation system, as shown in the figure. Figure 7 As shown, in Figure 6 After generating and displaying the second fault indication information including the target identifier and the second fault type identifier as described in step 205, the method may further include: Step 206: Obtain the second confirmation result information for the second fault prompt information input by the user. The second confirmation result information includes a confirmation identifier or a false alarm identifier.

[0079] The confirmation identifier can be a user-input character (such as letters, numbers, Chinese characters, etc.), icon (such as an arrow, exclamation mark, etc.), color, or pattern design used to indicate that the first fault prompt is a correct fault prompt. The false alarm identifier can be a different character, icon, color, or pattern design than the confirmation identifier. For example, "1", "Y", or "Confirm" can be used as the confirmation identifier, and "0", "F", or "N" can be used as the false alarm identifier.

[0080] Step 207: If it is determined that the second confirmation result information includes a confirmation identifier, the preset outlier determination threshold remains unchanged.

[0081] Step 208: If it is determined that the second confirmation result information includes a false alarm identifier, the preset outlier determination threshold is increased to obtain an updated preset outlier determination threshold.

[0082] In this case, the preset outlier detection threshold is increased (e.g., from 2σ to 3σ), and the allowable deviation range is reduced. Therefore, only more extreme data points will be identified as outliers. Thus, after increasing the preset outlier detection threshold, the number of photovoltaic modules in the photovoltaic string with a standard distance greater than the preset outlier detection threshold decreases, the probability of false alarms will decrease, and the accuracy of the fault detection process can be automatically adjusted.

[0083] In some embodiments, the method further includes: Step 209: If the user inputs fault missed reporting information, reduce the sensitivity coefficient and / or the preset outlier determination threshold.

[0084] In this step, when a user discovers a fault that was not detected by the maintenance system, the user can manually report the fault omission information. Upon receiving the manually reported fault omission information, the sensitivity coefficient and / or the preset outlier judgment threshold are reduced to narrow the normal residual range and increase the allowable deviation range, thereby making more data points judged as outliers, so as to tighten the judgment criteria and improve the fault detection sensitivity.

[0085] The above technical solutions can effectively improve the efficiency of locating faulty photovoltaic modules and shorten the time required for troubleshooting photovoltaic system faults, thereby improving the maintenance efficiency of photovoltaic systems and reducing operation and maintenance costs.

[0086] Figure 8 This is a block diagram illustrating a monitoring device for a photovoltaic power generation system, as shown in an exemplary embodiment of this disclosure. Figure 8 As shown, the device may include: The data acquisition module 801 is configured to acquire, for each photovoltaic module, the current operating parameters of the photovoltaic module and the residual values ​​of the photovoltaic module at multiple historical time points within a preset time period before the current time, wherein the residual value is the difference between the expected value and the detected value of the specified parameter; The determination module 802 is configured to determine the current dynamic residual threshold based on the residual values ​​at the plurality of historical time points; The operation and maintenance module 803 is configured to display a first fault prompt message when the photovoltaic module is determined to be operating abnormally based on the dynamic residual threshold and the current operating parameters. The first fault prompt message includes a first fault type identifier and a photovoltaic module identifier.

[0087] The above technical solution can accurately screen out photovoltaic modules with abnormal operation based on the dynamic residual threshold. Furthermore, when it is determined that the photovoltaic module is operating abnormally based on the dynamic residual threshold and the current operating parameters, it can display a first fault prompt message including a first fault type identifier and a photovoltaic module identifier. This can effectively improve the efficiency of locating faulty photovoltaic modules, which is conducive to further improving the maintenance efficiency of photovoltaic systems, shortening the time required for troubleshooting photovoltaic system faults, and thus reducing operation and maintenance costs.

[0088] In some embodiments, the determining module 802 is configured to: Determine the mean and standard deviation of the residuals at the multiple historical time points; Obtain the product of the current sensitivity coefficient and the standard deviation; The dynamic residual threshold is determined based on the average value and the product.

[0089] In some embodiments, the dynamic residual threshold includes an upper limit and a lower limit, and the determining module is configured to: The sum of the average value and the product is used as the upper limit of the dynamic residual threshold; The difference between the average value and the product is used as the lower limit of the dynamic residual threshold.

[0090] In some embodiments, the data acquisition module 801 is further configured to acquire first confirmation result information input by the user for the first fault prompt information, wherein the first confirmation result information includes a confirmation identifier or a false alarm identifier; The operation and maintenance module 803 is further configured to keep the sensitivity coefficient unchanged when it is determined that the first confirmation result information includes a confirmation identifier; and to increase the sensitivity coefficient to obtain an updated sensitivity coefficient when it is determined that the first confirmation result information includes a false alarm identifier.

[0091] In some embodiments, the plurality of photovoltaic modules form at least one photovoltaic string. The determining module 802 is configured to determine the target residual value of the photovoltaic module based on the current operating parameters of each photovoltaic module, so as to obtain the residual sequence of the photovoltaic string at the current time; and determine the standard distance between each target residual value in the residual sequence and the mean of the residual sequence. The data acquisition module 801 is configured to acquire a preset outlier determination threshold. The determining module 802 is further configured to determine the target identifier of a photovoltaic module in the photovoltaic string whose standard distance is greater than the preset outlier determination threshold; The operation and maintenance module 803 is configured to generate and display a second fault prompt message including the target identifier and the second fault type identifier.

[0092] In some embodiments, the operation and maintenance module 803 is further configured to obtain second confirmation result information for the second fault prompt information input by the user, the second confirmation result information including a confirmation identifier or a false alarm identifier; if it is determined that the second confirmation result information includes a confirmation identifier, the preset outlier determination threshold is kept unchanged; if it is determined that the second confirmation result information includes a false alarm identifier, the preset outlier determination threshold is increased to obtain an updated preset outlier determination threshold.

[0093] In some embodiments, the operation and maintenance module 803 is further configured to reduce the sensitivity coefficient and / or the preset outlier determination threshold when it is determined that fault missed reporting information input by the user has been obtained.

[0094] In some embodiments, the operation and maintenance module 803 is configured to: determine the target residual value of the photovoltaic module based on the current operating parameters; determine the normal residual range based on the dynamic residual threshold; and determine that the photovoltaic module is operating abnormally if the target residual value does not belong to the normal residual range.

[0095] In some embodiments, the current operating parameters include the rated values ​​of specified parameters and target detection values, backplane temperature and irradiance, and the maintenance module 803 is configured as follows: Based on the rated values ​​of the specified parameters, the backplate temperature and the irradiance are used to determine the target expected value of the specified parameters; based on the target expected value and the target detected value, the target residual value is determined.

[0096] In some embodiments, the operation and maintenance module 803 is configured as follows: Obtain the target prediction model corresponding to the specified parameter. The target prediction model is used to characterize the expected value of the specified parameter under different rated values ​​at different backsheet temperatures and irradiances. Input the rated value, the backsheet temperature and the irradiance into the target prediction model to obtain the target expected value output by the target prediction model.

[0097] Another exemplary embodiment of this disclosure illustrates a photovoltaic system, which includes the above-mentioned components. Figure 8 The monitoring device shown.

[0098] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0099] Figure 9This is a block diagram illustrating an electronic device according to an exemplary embodiment. Figure 9 As shown, the electronic device 700 may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0100] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the aforementioned photovoltaic power generation system monitoring method. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 703 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof; therefore, the corresponding communication component 705 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0101] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the aforementioned monitoring method for the photovoltaic power generation system.

[0102] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the photovoltaic power generation system monitoring method described above. For example, the computer-readable storage medium may be the memory 702 including program instructions described above, which may be executed by the processor 701 of the electronic device 700 to complete the photovoltaic power generation system monitoring method described above.

[0103] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the steps of the above-described monitoring method for a photovoltaic power generation system.

[0104] Figure 10 This is a block diagram illustrating another electronic device according to an exemplary embodiment. For example, electronic device 1900 may be provided as a server. (Refer to...) Figure 10 The electronic device 1900 includes a processor 1922, which may be one or more, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 1922 may be configured to execute the computer program to perform the aforementioned monitoring method for the photovoltaic power generation system.

[0105] Additionally, the electronic device 1900 may also include a power supply component 1926 and a communication component 1950. The power supply component 1926 can be configured to perform power management of the electronic device 1900, and the communication component 1950 can be configured to enable communication of the electronic device 1900, such as wired or wireless communication. Furthermore, the electronic device 1900 may also include an input / output (I / O) interface 1958. The electronic device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM Mac OS X TM Unix TM Linux TM etc.

[0106] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the photovoltaic power generation system monitoring method described above. For example, the computer-readable storage medium may be the memory 1932 including program instructions, which may be executed by the processor 1922 of the electronic device 1900 to complete the photovoltaic power generation system monitoring method described above.

[0107] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the steps of the above-described monitoring method for a photovoltaic power generation system.

[0108] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0109] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0110] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A monitoring method for a photovoltaic power generation system, wherein the photovoltaic power generation system comprises multiple photovoltaic modules, characterized in that, The method includes: For each photovoltaic module, the current operating parameters of the photovoltaic module and the residual values ​​of the photovoltaic module at multiple historical time points within a preset time period before the current time are obtained. The residual value is the difference between the expected value and the detected value of the specified parameter. The current dynamic residual threshold is determined based on the residual values ​​at the multiple historical time points; If the photovoltaic module is determined to be operating abnormally based on the dynamic residual threshold and the current operating parameters, a first fault prompt message is displayed. The first fault prompt message includes a first fault type identifier and a photovoltaic module identifier.

2. The method according to claim 1, characterized in that, Determining the current dynamic residual threshold based on the residual values ​​at the multiple historical time points includes: Determine the mean and standard deviation of the residuals at the multiple historical time points; Obtain the product of the current sensitivity coefficient and the standard deviation; The dynamic residual threshold is determined based on the average value and the product.

3. The method according to claim 2, characterized in that, The dynamic residual threshold includes an upper limit and a lower limit. Determining the dynamic residual threshold based on the average value and the product includes: The sum of the average value and the product is used as the upper limit of the dynamic residual threshold; The difference between the average value and the product is used as the lower limit of the dynamic residual threshold.

4. The method according to claim 2, characterized in that, The method further includes: Obtain first confirmation result information for the first fault prompt information input by the user, wherein the first confirmation result information includes a confirmation identifier or a false alarm identifier; If it is determined that the first confirmation result information includes a confirmation identifier, the sensitivity coefficient remains unchanged; If it is determined that the first confirmation result information includes a false alarm identifier, the sensitivity coefficient is increased to obtain an updated sensitivity coefficient.

5. The method according to claim 2, characterized in that, The plurality of photovoltaic modules form at least one photovoltaic string, and the method further includes: The target residual value of each photovoltaic module is determined based on the current operating parameters of each photovoltaic module to obtain the residual sequence of the photovoltaic string at the current time; Determine the standard distance between each target residual value in the residual sequence and the mean of the residual sequence; Obtain the preset outlier detection threshold; Identify the target identifiers of photovoltaic modules in the photovoltaic string whose standard distance is greater than the preset outlier determination threshold; Generate and display a second fault message including the target identifier and the second fault type identifier.

6. The method according to claim 5, characterized in that, The method further includes: Obtain second confirmation result information for the second fault prompt information input by the user, the second confirmation result information including a confirmation identifier or a false alarm identifier; If it is determined that the second confirmation result information includes a confirmation identifier, the preset outlier determination threshold remains unchanged; If it is determined that the second confirmation result information includes a false alarm identifier, the preset outlier determination threshold is increased to obtain an updated preset outlier determination threshold.

7. The method according to claim 5, characterized in that, The method further includes: If the user inputs information about missed faults, the sensitivity coefficient and / or the preset outlier determination threshold are reduced.

8. The method according to claim 1, characterized in that, Determining the photovoltaic module's operational anomaly based on the dynamic residual threshold and the current operating parameters includes: Determine the target residual value of the photovoltaic module based on the current operating parameters; The normal residual range is determined based on the dynamic residual threshold. If it is determined that the target residual value does not belong to the normal residual range, the number of anomalies of the photovoltaic module is incremented by one; if it is determined that the target residual value belongs to the normal residual range, the number of anomalies is reset to zero to obtain the updated number of anomalies. If the current number of anomalies exceeds a preset threshold, the photovoltaic module is determined to be malfunctioning.

9. A monitoring device for a photovoltaic power generation system, characterized in that, include: The data acquisition module is configured to acquire, for each photovoltaic module, the current operating parameters of the photovoltaic module and the residual values ​​of the photovoltaic module at multiple historical time points within a preset time period before the current time, wherein the residual value is the difference between the expected value and the detected value of the specified parameter; The determination module is configured to determine the current dynamic residual threshold based on the residual values ​​at the multiple historical time points; The operation and maintenance module is configured to display a first fault prompt message when the photovoltaic module is determined to be operating abnormally based on the dynamic residual threshold and the current operating parameters. The first fault prompt message includes a first fault type identifier and a photovoltaic module identifier.

10. A photovoltaic system, characterized in that, Includes the monitoring device as described in claim 9.

Images