Method and device for adjusting photovoltaic power generation voltage based on cloud collaboration, and electronic equipment

Abstract

The embodiment of the invention provides a method and device for adjusting photovoltaic power generation voltage based on cloud collaboration and electronic equipment, and relates to the technical field of photovoltaic power generation. The method is applied to a cloud server of a photovoltaic power generation system, and the photovoltaic power generation system at least comprises a photovoltaic string, an inverter and the cloud server. The method comprises the steps of obtaining operation data and MPPT dynamic characteristic data corresponding to a photovoltaic string, and determining a working condition type of the photovoltaic string based on the operation data and the MPPT dynamic characteristic data of the photovoltaic string; generating an MPPT strategy adjustment instruction based on the working condition type of the photovoltaic string; and sending the MPPT strategy adjustment instruction to an inverter, so that the inverter adjusts the working voltage of the photovoltaic string based on the MPPT strategy adjustment instruction. The method can improve the power generation efficiency under complex working conditions, so that the power generation capacity is improved.

Description

Technical Field

[0001] This application relates to the field of photovoltaic power generation technology, and in particular to a method, apparatus and electronic device for adjusting the voltage of photovoltaic power generation based on cloud collaboration. Background Technology

[0002] With the widespread application of photovoltaic (PV) power generation technology, the scale and application scenarios of PV power plants are becoming increasingly diversified, including large-scale ground-mounted power plants, distributed rooftop PV, floating PV systems, and building-integrated photovoltaics (BIPV). These scenarios share common characteristics: large land area occupied by the power plants, geographically dispersed (such as remote mountainous areas or offshore floating platforms), and a lack of intelligent monitoring capabilities for the PV DC-side strings and modules, making it impossible for them to proactively report status or operational data. Furthermore, due to the complex design of the power plants, the large number of devices, the uncertainty of solar resource measurements, and inconsistent data quality, it is difficult to quickly identify inefficiencies and implement targeted optimizations.

[0003] Currently, in related technologies, the inverter monitors the string status and adjusts the DC voltage using the traditional Maximum Power Point Tracking (MPPT) technology to approximate the maximum power point of the photovoltaic system.

[0004] However, traditional MPPT technology cannot achieve global maximum power point tracking under complex operating conditions such as partial shading, resulting in low power generation efficiency of photovoltaic power plants and thus power generation loss. Summary of the Invention

[0005] This application provides a cloud-based collaborative method, apparatus, and electronic device for adjusting the voltage of photovoltaic power generation, which can improve power generation efficiency under complex operating conditions, thereby increasing power generation.

[0006] Firstly, this application provides a cloud-based collaborative method for adjusting the voltage of photovoltaic power generation, applied to a cloud server of a photovoltaic power generation system. The photovoltaic power generation system includes at least: photovoltaic strings, an inverter, and a cloud server. The method includes:

[0007] Obtain the operating data and MPPT dynamic characteristic data corresponding to the photovoltaic strings;

[0008] Based on the operating data and MPPT dynamic characteristic data of the photovoltaic string, the operating condition type of the photovoltaic string is determined.

[0009] MPPT strategy adjustment instructions are generated based on the operating condition type of the photovoltaic string;

[0010] The MPPT strategy adjustment command is sent to the inverter so that the inverter can adjust the operating voltage of the photovoltaic string based on the MPPT strategy adjustment command.

[0011] In one possible implementation, the photovoltaic power generation system further includes: a data acquisition unit;

[0012] Accordingly, the MPPT dynamic characteristic data corresponding to the photovoltaic string is obtained, including:

[0013] The inverter is used to periodically perturb the photovoltaic string with large step size in order to determine the voltage jump data corresponding to the large step size perturbation.

[0014] Under non-large step size perturbation, when a power change event is detected in the photovoltaic string, the inverter performs a two-sided perturbation on the photovoltaic string to obtain the local characteristic data corresponding to the power change event under non-large step size perturbation.

[0015] The data acquisition device collects local characteristic data corresponding to voltage jump data and power surge events to obtain the MPPT dynamic characteristic data of the photovoltaic string.

[0016] In one possible implementation, the photovoltaic string is subjected to periodic large-step perturbations via an inverter to determine the corresponding voltage jump data under the large-step perturbations, including:

[0017] Acquire power change data of photovoltaic strings under large step perturbation;

[0018] The size of the disturbance step is dynamically adjusted based on power change data.

[0019] The photovoltaic string is periodically perturbed using a dynamically adjusted step size until it converges under the large step size perturbation.

[0020] In one possible implementation, the operating condition type of the photovoltaic string is determined based on its operational data and MPPT dynamic characteristic data, including:

[0021] Feature extraction is performed on the operating data and MPPT dynamic feature data of the photovoltaic string to obtain the multidimensional feature data corresponding to the photovoltaic string;

[0022] Multidimensional feature data is input into a pre-trained operating condition prediction model to obtain the current operating condition type of the photovoltaic string.

[0023] In one possible implementation, MPPT strategy adjustment instructions are generated based on the operating condition type of the photovoltaic string, including:

[0024] If the photovoltaic string is operating under a low-performance condition, the generated MPPT strategy adjustment instruction is a global scan instruction, which scans the entire voltage range corresponding to the photovoltaic string.

[0025] If the photovoltaic string is operating under continuous shading, the generated MPPT strategy adjustment command is either a range scan command or a fixed-point switching command. The range scan command scans within a preset voltage range, while the fixed-point switching command switches the operating voltage of the photovoltaic string to the predicted target voltage.

[0026] In one possible implementation, the operating data corresponding to the photovoltaic string includes the historical operating data of the photovoltaic string, and correspondingly, also includes:

[0027] Based on the historical operating data of the photovoltaic string, the historical time period in which the photovoltaic string was in a low-performance condition was determined;

[0028] If a photovoltaic string operates at low performance for several consecutive days within the same historical time period, that historical time period is marked as a shading period.

[0029] In one possible implementation, it also includes:

[0030] Obtain weather data corresponding to the photovoltaic strings;

[0031] Predict the duration of obstruction based on weather data to determine the remaining time of obstruction;

[0032] If the current time is within the shadow period and the remaining shadow time exceeds the preset duration, then the operating condition type of the photovoltaic string is determined to be continuous shadow.

[0033] In one possible implementation, it also includes:

[0034] If the photovoltaic string is operating under power limiting conditions, the temperature of the photovoltaic string will be collected.

[0035] If the temperature of the photovoltaic string exceeds the preset temperature threshold, triggering a derating power limit, the system will control the start of the photovoltaic power generation system's fan or increase the fan speed of the photovoltaic power generation system.

[0036] Secondly, this application provides a cloud-based collaborative device for adjusting the voltage of photovoltaic power generation, applied to a cloud server of a photovoltaic power generation system. The photovoltaic power generation system includes at least: photovoltaic strings, an inverter, and a cloud server. The device includes:

[0037] The acquisition module is used to acquire the operating data and MPPT dynamic characteristic data corresponding to the photovoltaic strings;

[0038] The processing module is used to determine the operating condition type of the photovoltaic string based on the operating data and MPPT dynamic characteristic data of the photovoltaic string;

[0039] The processing module is also used to generate MPPT strategy adjustment instructions based on the operating condition type of the photovoltaic string;

[0040] The processing module is also used to send MPPT strategy adjustment instructions to the inverter so that the inverter can adjust the operating voltage of the photovoltaic string based on the MPPT strategy adjustment instructions.

[0041] In one possible implementation, the photovoltaic power generation system further includes: a data acquisition unit;

[0042] Accordingly, the acquisition module is specifically used to periodically perturb the photovoltaic string with large step size through the inverter in order to determine the voltage jump data corresponding to the large step size perturbation.

[0043] The acquisition module is also specifically used to perform bilateral perturbation on the photovoltaic string through the inverter when a power mutation event is detected under non-large step perturbation, so as to obtain the local characteristic data corresponding to the power mutation event under non-large step perturbation.

[0044] The acquisition module is also used to collect local characteristic data corresponding to voltage jump data and power mutation events through a data acquisition device, so as to obtain the MPPT dynamic characteristic data corresponding to the photovoltaic string.

[0045] In one possible implementation, the acquisition module is further configured to acquire power change data of the photovoltaic string under large step-size perturbation.

[0046] The acquisition module is also used to dynamically adjust the size of the disturbance step based on power change data;

[0047] The acquisition module is also used to continuously perturb the photovoltaic string with a dynamically adjusted step size until the photovoltaic string converges under the large step size perturbation.

[0048] In one possible implementation, the processing module is specifically used to extract features from the operating data and MPPT dynamic feature data of the photovoltaic string to obtain multi-dimensional feature data corresponding to the photovoltaic string.

[0049] The processing module is also used to input multi-dimensional feature data into a pre-trained operating condition prediction model to obtain the current operating condition type of the photovoltaic string.

[0050] In one possible implementation, the processing module is further configured to generate a global scan instruction if the photovoltaic string's operating condition is a low-performance operating condition, wherein the global scan instruction scans the entire voltage range corresponding to the photovoltaic string.

[0051] The processing module is further configured to generate either an interval scanning instruction or a fixed-point switching instruction if the photovoltaic string is operating under continuous shading conditions. The interval scanning instruction scans within a preset voltage range, while the fixed-point switching instruction switches the operating voltage of the photovoltaic string to the predicted target voltage.

[0052] In one possible implementation, the operating data corresponding to the photovoltaic string includes the historical operating data of the photovoltaic string. Accordingly, the processing module is also used to determine the historical time period in which the photovoltaic string was in a low-performance condition based on the historical operating data of the photovoltaic string.

[0053] The processing module is also used to mark a historical period as a shading period if the photovoltaic string operates at low performance for several consecutive days in the same historical time period.

[0054] In one possible implementation, the processing module is also used to acquire weather data corresponding to the photovoltaic string;

[0055] The processing module is also used to predict the duration of obstruction based on weather data in order to determine the remaining time of obstruction.

[0056] The processing module is also used to determine the operating condition type of the photovoltaic string as continuous shading if the current time is within the shading period and the remaining shading time exceeds the preset duration.

[0057] In one possible implementation, the processing module is further configured to collect the temperature of the photovoltaic string if the photovoltaic string is in a power-limited operating condition.

[0058] The processing module is also used to control the start of the photovoltaic power generation system's fan or increase the fan speed of the photovoltaic power generation system if the temperature of the photovoltaic string exceeds a preset temperature threshold and triggers a derating power limit.

[0059] Thirdly, this application provides an electronic device, including: a processor, a communication interface, and a memory, wherein the processor is communicatively connected to the communication interface and the memory respectively;

[0060] The memory stores the instructions that the computer executes;

[0061] The communication interface enables communication and interaction with external devices.

[0062] The processor executes computer-executable instructions stored in memory to implement a cloud-based collaborative method for adjusting the voltage of photovoltaic power generation, as described in any of the first aspects.

[0063] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the cloud-based collaborative method for adjusting the voltage of photovoltaic power generation as described in any of the first aspects.

[0064] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, is used to implement a cloud-based collaborative method for adjusting the voltage of photovoltaic power generation as described in any of the first aspects.

[0065] This application provides a cloud-based collaborative method, apparatus, and electronic device for adjusting photovoltaic (PV) power generation voltage. By combining collected operational data and MPPT dynamic characteristic data corresponding to the PV string with a cloud server, the powerful computing capabilities of the cloud are used to analyze the operational data and MPPT dynamic characteristic data to determine the actual operating condition type of the PV string. Based on the operating condition type of the PV string, the MPPT technology is adaptively adjusted to achieve the adjustment of the PV string's operating voltage, bringing it close to the global optimum. Therefore, based on the method provided in this application, suitable operating voltages can be determined for various complex operating conditions, thereby improving power generation efficiency under complex conditions and ultimately increasing the power generation of the PV power generation system. Attached Figure Description

[0066] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0067] Figure 1 A schematic diagram illustrating an application scenario of a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in an embodiment of this application.

[0068] Figure 2 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 1 ;

[0069] Figure 3 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 2 ;

[0070] Figure 4 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 3 ;

[0071] Figure 5 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 4 ;

[0072] Figure 6 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 5 ;

[0073] Figure 7 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 6 ;

[0074] Figure 8 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 7 ;

[0075] Figure 9 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 8 ;

[0076] Figure 10 A schematic diagram of a cloud-based collaborative device for adjusting the voltage of photovoltaic power generation, provided as an embodiment of this application;

[0077] Figure 11 A schematic diagram of the structure of the electronic device provided in this application.

[0078] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0079] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0080] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0081] With the widespread application of photovoltaic (PV) power generation technology, the scale and application scenarios of PV power plants are becoming increasingly diversified, including large-scale ground-mounted power plants, distributed rooftop PV, floating PV systems, and building-integrated photovoltaics (BIPV). These scenarios share common characteristics: large land area occupied by the power plants, geographically dispersed (such as remote mountainous areas or offshore floating platforms), and a lack of intelligent monitoring capabilities for the PV DC-side strings and modules, making it impossible for them to proactively report status or operational data. Furthermore, due to the complex design of the power plants, the large number of devices, the uncertainty of solar resource measurements, and inconsistent data quality, it is difficult to quickly identify inefficiencies and implement targeted optimizations.

[0082] Currently, related technologies monitor the string status through inverters and adjust the DC voltage using traditional MPPT (Maximum Power Point Tracking) technology to approach the maximum power point. However, photovoltaic systems face complex environmental challenges, such as localized shading (e.g., tree obstruction), module dust accumulation, and hidden faults like microcracks. These factors cause the string power curve to exhibit multi-peak characteristics, making it difficult for traditional MPPT technology to accurately track the globally optimal operating point. Under complex operating conditions such as localized shading, global maximum power point tracking cannot be achieved, resulting in low power generation efficiency and power loss.

[0083] To address the aforementioned technical problems, the inventors proposed the following technical concept: by acquiring the operating data and MPPT dynamic characteristic data of the photovoltaic string, and combining the analysis of the operating data and MPPT dynamic characteristic data of the photovoltaic string with a cloud server, the operating condition of the photovoltaic string can be accurately identified, and targeted MPPT strategy adjustment commands can be issued based on the operating condition of the photovoltaic string. Finally, the MPPT strategy adjustment commands are executed through the inverter.

[0084] The following describes the application scenarios of the cloud-based collaborative method for adjusting photovoltaic power generation voltage provided in this application. Figure 1 This diagram illustrates an application scenario for a cloud-based collaborative method for adjusting photovoltaic power generation voltage, as provided in an embodiment of this application. Figure 1As shown, a photovoltaic (PV) power generation system includes PV strings, an inverter, a data acquisition unit, and a cloud server. The PV strings convert solar energy into direct current (DC) and output it to the inverter. The inverter converts the DC to alternating current (AC) and collects real-time operating data from the PV strings. The inverter incorporates an MPPT (Maximum Power Point Tracking) algorithm, which adjusts the input impedance to change the operating voltage of the PV strings and track the maximum power point. The data acquisition unit obtains operating data and MPPT dynamic characteristic data from the inverter and transmits this data to the cloud server via the network. The cloud server analyzes and processes the data to generate optimized MPPT strategy adjustment instructions. It then sends these instructions to the inverter, which updates the relevant parameters of the MPPT algorithm accordingly to adjust the operating voltage of the PV strings.

[0085] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0086] Figure 2 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 1 A cloud server is used in a photovoltaic power generation system, which includes at least: photovoltaic strings, an inverter, and a cloud server, such as... Figure 2 As shown, the method includes:

[0087] S201. Obtain the operating data and MPPT dynamic characteristic data corresponding to the photovoltaic string.

[0088] In a scenario example, a photovoltaic (PV) string consists of several PV modules connected in series. These modules can be solar panels. The operational data of the PV modules includes two parts: real-time operational data and historical operational data from a specific point in time, such as the previous week or month. This operational data includes, but is not limited to, voltage, current, and power. The inverter uses a built-in MPPT algorithm to add perturbation voltages to the PV string to determine its maximum power point (MPPT) and adjusts the PV module's operating voltage to achieve the maximum power output. MPPT dynamic characteristic data refers to the data related to the perturbation voltages generated during the process of adding perturbation voltages to the PV string to find the MPPT.

[0089] Optionally, the photovoltaic power generation system may also include a data acquisition unit. Figure 3A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 2 ,like Figure 3 As shown, in S201, the MPPT dynamic characteristic data corresponding to the photovoltaic string is obtained, including:

[0090] S301. Periodically perform large-step perturbation on the photovoltaic string through the inverter to determine the voltage jump data corresponding to the large-step perturbation.

[0091] In the context of a scenario, periodic large-step perturbation refers to performing a large-step perturbation at fixed time intervals. The fixed time interval can be determined based on actual conditions, for example, 60 seconds. Under large-step perturbation, the MPPT dynamic characteristic data can be voltage jump data, which includes information related to voltage jump events generated under large-step perturbation. This information includes, but is not limited to, the perturbation direction, step size, convergence point voltage, power value, and event type. The perturbation direction refers to the direction of actively changing the operating voltage, such as adding or subtracting the perturbation voltage from the original operating voltage. The step size refers to the magnitude of the perturbation voltage, which can be determined based on actual conditions; for example, a large step size could be 10V. The convergence point voltage refers to the final stable operating voltage after the large-step perturbation. The maximum power point refers to the voltage value corresponding to the maximum power that the photovoltaic string can achieve under the current operating conditions. Since the purpose of voltage perturbation is to find the maximum power point, the voltage value at which convergence is finally achieved can be taken as the voltage corresponding to the maximum power point.

[0092] The power value refers to the power corresponding to the convergence point voltage. The event type of voltage jump event generated under large step perturbation can be recorded as voltage jump event under large step perturbation.

[0093] For example, in the case of large-step perturbations, the condition for a voltage jump event is: the difference between the convergence point voltage and the origin voltage exceeds a preset value. The preset value is determined according to the actual situation, for example, it can be 10%. The origin voltage refers to the operating voltage before the large-step perturbation. If the difference between the convergence point voltage and the origin voltage after the large-step perturbation exceeds 10%, it is determined to be a voltage jump event. Additionally, if the convergence direction is opposite to the perturbation direction, it is also determined to be a voltage jump event. The convergence direction refers to the direction of the convergence point voltage relative to the origin voltage; for example, the convergence point voltage is less than the origin voltage, or the convergence point voltage is greater than the origin voltage. Therefore, if the perturbation direction is the superposition of a large-step perturbation voltage on the origin voltage, but the final convergence point voltage is less than the origin voltage, it can be determined to be a voltage jump event. Alternatively, if the perturbation direction is the subtraction of a large-step perturbation voltage from the origin voltage, but the final convergence point voltage is greater than the origin voltage, it can also be determined to be a voltage jump event.

[0094] Optional, Figure 4 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 3 ,like Figure 4 As shown, S301 includes:

[0095] S401. Obtain power change data of photovoltaic strings under large step-size perturbation.

[0096] With a scenario example, under periodic large-step perturbations, the operating voltage of a photovoltaic string will change in real time, which will cause a corresponding change in power. The power change data refers to the real-time change in the power of the photovoltaic string under voltage perturbations.

[0097] S402. Based on power change data, dynamically adjust the size of the disturbance step.

[0098] In a scenario example, when a photovoltaic (PV) string experiences a voltage disturbance, if the disturbance direction causes a decrease in power, the disturbance direction can be immediately adjusted to prevent further power reduction. If the disturbance direction causes an increase in power, the power growth rate will gradually decrease with further disturbances, and the step size of the disturbance voltage can be reduced accordingly. For example, if the initial step size of a large-step disturbance is 10V, the voltage of the first voltage disturbance on the PV string will be 10V. For instance, if the current operating voltage of the PV string is aV, and the current power is P0, then reducing the voltage by 10V from aV results in a decrease in power compared to before the voltage disturbance. This indicates that the disturbance direction causes a power decrease, and therefore, the disturbance direction is an increase in voltage. Thus, adding 10V to aV yields the power P1 after the first voltage disturbance, and the first power growth rate can be determined using P0 and P1. The second perturbation is achieved by adding 10V to the base a+10V, resulting in a power of P2 after the second voltage perturbation. The second power growth rate can be determined using P1 and P2. The rate of change of the power growth rate under these two perturbations can be determined based on the first and second growth rates. This rate of change is then used to adjust the initial step size; for example, multiplying the current step size by this rate of change to obtain the step size for the next voltage perturbation. Similarly, if the step size for the next voltage perturbation is bV, the third perturbation is achieved by adding bV to the base a+20V, resulting in a power of P3 after the third voltage perturbation. The third power growth rate can be determined using P2 and P3. The rate of change of the power growth rate under these two perturbations can be determined based on the second and third growth rates. This rate of change is then multiplied by the step size bV to obtain the step size for the next voltage perturbation. In this way, before the next voltage perturbation, the rate of change of the corresponding power growth rate is obtained based on the power growth rates of the previous two perturbations, allowing for dynamic adjustment of the step size.

[0099] S403. The photovoltaic string is periodically perturbed using a dynamically adjusted step size until it converges under the large step size perturbation.

[0100] Based on the scenario example, and according to the aforementioned dynamic adjustment of the step size, the perturbation step size corresponding to each perturbation is obtained. Then, the voltage of the photovoltaic string is perturbed using the obtained step size before each perturbation until the photovoltaic string reaches convergence.

[0101] Based on the method provided in this example, by dynamically adjusting the perturbation step size, the perturbation step size can be made to better reflect the actual situation of power changes, thereby improving the accuracy of determining the convergence point voltage.

[0102] S302. Under non-large step size perturbation, when a power change event is detected in the photovoltaic string, the inverter performs a two-sided perturbation on the photovoltaic string to obtain the local characteristic data corresponding to the power change event under non-large step size perturbation.

[0103] In the context of scenario examples, non-large step perturbation refers to voltage perturbation using a preset reference step size, which can be determined based on actual conditions, for example, 5V. Power mutation refers to the rate of change of the photovoltaic string's power between two consecutive moments exceeding a preset rate of change threshold, such as exceeding 10%. In the case of power mutation, the operating voltage at the time of the power mutation is used as a reference for two-sided perturbation. For example, the operating voltage at the time of the power mutation can be denoted as U1, the operating point corresponding to U1 can be denoted as point A, the operating point perturbed 5V to the left (U1 minus 5V) can be denoted as point B, and the operating point perturbed 5V to the right (U1 increases by 5V) can be denoted as point C. By analyzing the power change curves at points B, C, and B, the corresponding local characteristic data can be obtained, which can characterize the trend of the power change curve. The power change curve can be categorized into three types: First, the trough type, where point A is at a trough, and the power at points B and C both exceed that of point A. This indicates a significant jump in the new maximum power point of the photovoltaic string compared to the previous maximum power point, which can be recorded as a voltage jump event. The type of this voltage jump event can be classified as a power surge. Second, the peak type, where point A is at a peak, and the power at points B and C is lower than that of point A. This indicates that point A is close to the previous maximum power point, and the new convergence point does not show a significant jump compared to the previous maximum power point. Third, the monotonic type, where the power change curves at points B, C, and D show a monotonically increasing or decreasing trend. A monotonically increasing trend indicates that point C is closer to the convergence point; a monotonically decreasing trend indicates that point B is closer to the convergence point.

[0104] S303. The data acquisition unit collects the voltage jump data and the local characteristic data corresponding to the power change event to obtain the MPPT dynamic characteristic data of the photovoltaic string.

[0105] Based on the scenario examples and the aforementioned content, in the case of large step-size perturbation, the corresponding voltage jump events are collected, and in the case of non-step-size perturbation, the corresponding local characteristic data are collected to obtain the MPPT dynamic characteristic data of the photovoltaic string.

[0106] Based on the method provided in this example, the accuracy of identifying voltage jump points under complex operating conditions can be improved through periodic large-step perturbation and two-sided perturbation analysis.

[0107] S202. Based on the operating data and MPPT dynamic characteristic data of the photovoltaic string, determine the operating condition type of the photovoltaic string.

[0108] Based on the obtained photovoltaic string operation data and MPPT dynamic feature data, the cloud server locates the current operating condition of the photovoltaic string to obtain the current operating condition type of the photovoltaic string.

[0109] Optional, Figure 5 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 4 ,like Figure 5 As shown, S202 includes:

[0110] S501. Extract features from the operating data and MPPT dynamic feature data of the photovoltaic string to obtain multi-dimensional feature data corresponding to the photovoltaic string.

[0111] In conjunction with scenario examples, the feature data includes, but is not limited to, power deviation index, MPPT switching frequency, switching point voltage distribution, and local characteristic patterns. The power deviation index is the deviation rate between the real-time power of the photovoltaic string and the preset target power, which can be determined based on actual conditions. The MPPT switching frequency refers to the number of voltage switching events generated by the photovoltaic string within a preset time period, such as the number of voltage switching events generated by the photovoltaic string in a day. Switching point voltage distribution refers to the distribution of the operating voltage corresponding to each voltage switching event. Local characteristic patterns refer to the proportion of different types of power change curve trends corresponding to power abrupt events under non-step perturbation conditions, such as the probability of a "valley type" occurring.

[0112] S502. Input the multi-dimensional feature data into the pre-trained operating condition prediction model to obtain the current operating condition type of the photovoltaic string.

[0113] Based on the scenario example, the operating condition prediction model can be a classification or regression model. By learning from massive amounts of data, the model can accurately identify the correlation between multi-dimensional feature data and operating condition types, thereby determining the current operating condition type of the photovoltaic string. For example, if the power deviation index exceeds a preset deviation rate threshold (i.e., the deviation rate between the real-time power and the preset target power exceeds the preset deviation rate threshold), then the operating condition can be determined to be a low-performance condition. Based on the method provided in this example, the accuracy of determining the operating condition type can be improved through multi-dimensional feature extraction and model analysis.

[0114] S203. Generate MPPT strategy adjustment instructions based on the operating condition type of the photovoltaic string.

[0115] Based on scenario examples, the cloud server can adaptively determine MPPT strategy adjustment instructions according to different operating conditions.

[0116] Optional, Figure 6A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 5 ,like Figure 6 As shown, S203 includes:

[0117] S601. If the operating condition of the photovoltaic string is low performance, the generated MPPT strategy adjustment instruction is a global scan instruction, which scans the entire voltage range corresponding to the photovoltaic string.

[0118] In the context of the scenario example, the entire voltage range refers to the minimum operating voltage Vmin to the maximum operating voltage Vmax allowed by the photovoltaic string. Therefore, the global scan command refers to scanning within the entire voltage range ([Vmin, Vmax]) to find the global maximum power point.

[0119] S602. If the photovoltaic string is in a continuous shading condition, the generated MPPT strategy adjustment instruction is either an interval scanning instruction or a fixed-point switching instruction. The interval scanning instruction scans within a preset voltage range, while the fixed-point switching instruction switches the operating voltage of the photovoltaic string to the predicted target voltage.

[0120] In the context of a scenario, continuous shading refers to a situation where the photovoltaic (PV) strings will be continuously shaded for a period of time. In this case, by analyzing multi-dimensional feature data, the common voltage corresponding to the global maximum power point can be predicted to obtain the corresponding target voltage. Using this target voltage as a benchmark, the upper limit of the voltage range is obtained by increasing it by a preset percentage, and the lower limit of the voltage range is obtained by decreasing it by the same preset percentage.

[0121] S204. Send the MPPT strategy adjustment command to the inverter so that the inverter can adjust the operating voltage of the photovoltaic string based on the MPPT strategy adjustment command.

[0122] Based on scenario examples, the inverter executes corresponding actions according to the received MPPT strategy adjustment command to switch the MPPT tracking mode. For instance, if the received MPPT strategy adjustment command is a global scan command, the inverter switches the MPPT tracking mode to scan the entire voltage range ([Vmin, Vmax]) to find the global maximum power point. If the received MPPT strategy adjustment command is a range scan command, the inverter switches the MPPT tracking mode to scan within a defined voltage range to find the global maximum power point. If the received MPPT strategy adjustment command is a fixed-point switching command, the inverter directly switches the common voltage of the photovoltaic string to the predicted target voltage.

[0123] Based on the method provided in this example, an appropriate operating voltage can be determined for various complex operating conditions, thereby improving the power generation efficiency under complex operating conditions and thus increasing the power generation of the photovoltaic power generation system.

[0124] Optional, Figure 7 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 6 The operating data corresponding to the photovoltaic string includes the historical operating data of the photovoltaic string, such as... Figure 7 As shown, it also includes:

[0125] S701. Based on the historical operating data of the photovoltaic string, determine the historical time period during which the photovoltaic string was in a low-performance condition.

[0126] Based on scenario examples and historical operating data of the photovoltaic strings, the times when low-performance conditions occur each day are marked to obtain the historical time periods of low-performance conditions.

[0127] S702. If the photovoltaic string operates under low performance conditions for several consecutive days within the same historical time period, then that historical time period shall be marked as a shading period.

[0128] In a scenario example, if the photovoltaic (PV) modules operate at low performance levels for several consecutive days, such as a week, within the same historical timeframe—for instance, between 3:00 PM and 4:00 PM—it can be determined that the PV modules are under shade, or have issues such as edge dust accumulation or microcracks in the modules during that period. In this case, the cloud server can generate a manual work order and send it to the relevant maintenance personnel's terminals to address issues like shading, edge dust accumulation, or microcracks in the modules.

[0129] Based on the method provided in this example, the efficiency and accuracy of photovoltaic string condition confirmation can be improved by marking historical time periods of low-performance conditions to clarify the conditions of fixed time periods.

[0130] Optional, Figure 8 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 7 ,like Figure 8 As shown, it also includes:

[0131] S801. Obtain the weather data corresponding to the photovoltaic string.

[0132] Based on scenario examples, a weather instrument can be introduced into the photovoltaic power generation system to predict weather conditions, and a data acquisition device can collect the corresponding weather data from the weather instrument.

[0133] S802. Based on weather data, predict the duration of obstruction to determine the remaining obstruction time.

[0134] Using scenario examples, predict the remaining obstruction time based on weather data, for example, determine that the remaining obstruction time is 2 hours based on weather data.

[0135] S803. If the current time is within the shadow shading period and the remaining shading time exceeds the preset duration, then the operating condition type of the photovoltaic string is determined to be continuous shadow shading.

[0136] Based on the scenario example, the preset duration can be determined according to the actual situation. For example, it can be 1 hour. So when the remaining time of shading exceeds 1 hour, it means that the photovoltaic string will be continuously shaded for a period of time in the future. Therefore, the operating condition type of the photovoltaic string can be determined to be continuous shading.

[0137] The method provided in this example, combined with actual weather data, can improve the accuracy of confirming the operating conditions of photovoltaic strings.

[0138] Optional, Figure 9 A flowchart illustrating a cloud-based collaborative method for adjusting photovoltaic power generation voltage, provided in this application embodiment. Figure 8 ,like Figure 9 As shown, it also includes:

[0139] S901. If the photovoltaic string is under power-limited operation, the temperature of the photovoltaic string is collected.

[0140] In a scenario example, when the temperature of the photovoltaic (PV) string exceeds a certain threshold, the system will proactively reduce its output power to prevent overheating damage. In this case, the PV string will be in an active power-limiting mode. When power limiting is detected, it's important to first rule out overheating as the cause of the derating protection. Therefore, the actual operating temperature of the PV string can be collected using a temperature sensor.

[0141] S902. If the temperature of the photovoltaic string exceeds the preset temperature threshold and causes a derating power limit, then control the start of the photovoltaic power generation system's fan or increase the fan speed of the photovoltaic power generation system.

[0142] In a scenario example, if the temperature of the photovoltaic (PV) string does exceed the preset temperature threshold, the derating will be lifted and normal power output restored by activating or enhancing fan cooling to lower the equipment temperature. If the temperature of the PV string does not exceed the preset temperature threshold, the cloud server can generate a manual troubleshooting work order and send it to the relevant maintenance personnel's terminals. This allows for a combined human investigation of potential power limiting factors, enabling accurate identification of the cause.

[0143] Based on the method provided in this example, power-limited operating conditions can be addressed to increase the power output of photovoltaic power generation systems.

[0144] This application combines the collected operational data and MPPT dynamic characteristic data of the photovoltaic (PV) string with a cloud server. Utilizing the powerful computing capabilities of the cloud, the operational data and MPPT dynamic characteristic data are analyzed to determine the actual operating condition of the PV string. Based on this operating condition, the MPPT technology is adaptively adjusted to regulate the PV string's operating voltage, bringing it closer to the global optimum. Therefore, based on the method provided in this application, suitable operating voltages can be determined for various complex operating conditions, thereby improving power generation efficiency under complex conditions and ultimately increasing the power output of the photovoltaic power generation system.

[0145] Figure 10 This application provides a schematic diagram of a cloud-based collaborative device for adjusting the voltage of a photovoltaic power generation system. The device is applied to a cloud server in a photovoltaic power generation system, which includes at least: photovoltaic strings, an inverter, and a cloud server. Figure 10 As shown, the device includes:

[0146] The acquisition module 101 is used to acquire the operating data and MPPT dynamic characteristic data corresponding to the photovoltaic string;

[0147] The processing module 102 is used to determine the operating condition type of the photovoltaic string based on the operating data and MPPT dynamic characteristic data of the photovoltaic string.

[0148] Processing module 102 is also used to generate MPPT strategy adjustment instructions based on the operating condition type of the photovoltaic string;

[0149] The processing module 102 is also used to send MPPT strategy adjustment instructions to the inverter so that the inverter adjusts the operating voltage of the photovoltaic string based on the MPPT strategy adjustment instructions.

[0150] Optionally, the photovoltaic power generation system may also include: a data acquisition unit;

[0151] Accordingly, the acquisition module 101 is specifically used to perform periodic large-step perturbation on the photovoltaic string through the inverter in order to determine the voltage jump data corresponding to the large-step perturbation.

[0152] The acquisition module 101 is also specifically used to perform double-sided perturbation on the photovoltaic string through the inverter when a power change event is detected under non-large step perturbation, so as to obtain the local characteristic data corresponding to the power change event under non-large step perturbation.

[0153] The acquisition module 101 is also used to acquire local characteristic data corresponding to voltage jump data and power mutation events through a data acquisition device, so as to obtain the MPPT dynamic characteristic data corresponding to the photovoltaic string.

[0154] Optionally, the acquisition module 101 is further used to acquire power change data of the photovoltaic string under large step perturbation;

[0155] The acquisition module 101 is also specifically used to dynamically adjust the size of the disturbance step based on the power change data;

[0156] The acquisition module 101 is also used to continuously perturb the photovoltaic string with a dynamically adjusted step size until the photovoltaic string reaches convergence under the large step size perturbation.

[0157] Optionally, the processing module 102 is specifically used to extract features from the operating data and MPPT dynamic feature data of the photovoltaic string to obtain multi-dimensional feature data corresponding to the photovoltaic string.

[0158] The processing module 102 is further used to input multidimensional feature data into a pre-trained operating condition prediction model to obtain the current operating condition type of the photovoltaic string.

[0159] Optionally, the processing module 102 is further configured to generate a global scan instruction if the photovoltaic string's operating condition is a low-performance operating condition, wherein the global scan instruction scans the entire voltage range corresponding to the photovoltaic string.

[0160] The processing module 102 is further configured to generate an MPPT strategy adjustment instruction as an interval scanning instruction or a fixed-point switching instruction if the photovoltaic string is in a continuous shading condition. The interval scanning instruction scans within a preset voltage range, while the fixed-point switching instruction switches the operating voltage of the photovoltaic string to the predicted target voltage.

[0161] Optionally, the operating data corresponding to the photovoltaic string includes the historical operating data of the photovoltaic string. Accordingly, the processing module 102 is also used to determine the historical time period in which the photovoltaic string was in a low-performance condition based on the historical operating data of the photovoltaic string.

[0162] The processing module 102 is also used to mark the historical period as a shading period if the photovoltaic string is in a low-performance condition for several consecutive days in the same historical period.

[0163] Optionally, the processing module 102 is also used to acquire weather data corresponding to the photovoltaic string;

[0164] The processing module 102 is also used to predict the obstruction time based on weather data in order to determine the remaining obstruction time;

[0165] The processing module 102 is also used to determine the operating condition type of the photovoltaic string as continuous shading if the current time is within the shading period and the remaining shading time exceeds the preset duration.

[0166] Optionally, the processing module 102 is also used to collect the temperature of the photovoltaic string if the photovoltaic string is in a power-limited operating condition;

[0167] The processing module 102 is also used to control the start of the fan of the photovoltaic power generation system or increase the fan speed of the photovoltaic power generation system if the temperature of the photovoltaic string exceeds the preset temperature threshold and causes a derating power limit.

[0168] The cloud-based photovoltaic power generation voltage adjustment device provided in this application embodiment can execute the cloud-based photovoltaic power generation voltage adjustment method in the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0169] Figure 11 A schematic diagram of the structure of the electronic device provided in this application. Figure 11 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus.

[0170] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0171] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0172] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0173] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0174] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0175] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0176] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0177] The aforementioned readable storage medium 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 readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0178] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0179] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0180] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0181] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0182] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to related technologies, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0183] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0184] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for adjusting the voltage of photovoltaic power generation based on cloud collaboration, applied to a cloud server of a photovoltaic power generation system, characterized in that, The photovoltaic power generation system includes at least: photovoltaic strings, an inverter, and a cloud server; the method includes: Obtain the operating data and MPPT dynamic characteristic data corresponding to the photovoltaic string; Based on the operating data and MPPT dynamic characteristic data of the photovoltaic string, the operating condition type of the photovoltaic string is determined; MPPT strategy adjustment instructions are generated based on the operating condition type of the photovoltaic string; The MPPT strategy adjustment command is sent to the inverter so that the inverter adjusts the operating voltage of the photovoltaic string based on the MPPT strategy adjustment command.

2. The method according to claim 1, characterized in that, The photovoltaic power generation system also includes: a data acquisition unit; Accordingly, obtaining the MPPT dynamic feature data corresponding to the photovoltaic string includes: The inverter is used to periodically perform large-step perturbations on the photovoltaic string in order to determine the voltage jump data corresponding to the large-step perturbation. Under non-large step size perturbation, when a power change event is detected in the photovoltaic string, the inverter performs a two-sided perturbation on the photovoltaic string to obtain the local characteristic data corresponding to the power change event under non-large step size perturbation. The data acquisition device collects the voltage jump data and the local characteristic data corresponding to the power change events to obtain the MPPT dynamic characteristic data corresponding to the photovoltaic string.

3. The method according to claim 2, characterized in that, The step of periodically subjecting the photovoltaic string to large-step perturbations via the inverter to determine the corresponding voltage jump data under the large-step perturbations includes: Obtain the power change data of the photovoltaic string under large step perturbation; Based on the power change data, the size of the disturbance step is dynamically adjusted. The photovoltaic string is periodically perturbed using a dynamically adjusted step size until it converges under the large step size perturbation.

4. The method according to claim 1, characterized in that, The determination of the operating condition type of the photovoltaic string based on its operating data and MPPT dynamic characteristic data includes: Feature extraction is performed on the operating data and MPPT dynamic feature data of the photovoltaic string to obtain the multidimensional feature data corresponding to the photovoltaic string; The multidimensional feature data is input into a pre-trained operating condition prediction model to obtain the current operating condition type of the photovoltaic string.

5. The method according to claim 1, characterized in that, The generation of MPPT strategy adjustment instructions based on the operating condition type of the photovoltaic string includes: If the photovoltaic string operates under a low-performance condition, the generated MPPT strategy adjustment instruction is a global scan instruction, wherein the global scan instruction scans the entire voltage range corresponding to the photovoltaic string. If the photovoltaic string is operating under continuous shading, the generated MPPT strategy adjustment instruction is either an interval scanning instruction or a fixed-point switching instruction. The interval scanning instruction scans within a preset voltage range, and the fixed-point switching instruction switches the operating voltage of the photovoltaic string to the predicted target voltage.

6. The method according to claim 5, characterized in that, The operating data corresponding to the photovoltaic string includes the historical operating data of the photovoltaic string, and correspondingly also includes: Based on the historical operating data of the photovoltaic string, the historical time period in which the photovoltaic string was in a low-performance condition was determined; If the photovoltaic string operates under low performance conditions for several consecutive days within the same historical time period, then that historical time period is marked as a shading period.

7. The method according to claim 6, characterized in that, Also includes: Obtain the weather data corresponding to the photovoltaic string; The duration of obstruction is predicted based on the weather data to determine the remaining time of obstruction. If the current time is within a shadow occlusion period and the remaining occlusion time exceeds a preset duration, then the operating condition type of the photovoltaic string is determined to be continuous shadow occlusion.

8. The method according to claim 5, characterized in that, Also includes: If the photovoltaic string is under power-limited operation, the temperature of the photovoltaic string is collected; If the temperature of the photovoltaic string exceeds a preset temperature threshold, triggering a derating power limit, the system will control the start of the photovoltaic power generation system's fan or increase the fan speed of the photovoltaic power generation system.

9. A cloud-based collaborative device for adjusting the voltage of photovoltaic power generation, applied to a cloud server of a photovoltaic power generation system, characterized in that, The photovoltaic power generation system includes at least: photovoltaic strings, an inverter, and a cloud server; the device includes: The acquisition module is used to acquire the operating data and MPPT dynamic feature data corresponding to the photovoltaic string; The processing module is used to determine the operating condition type of the photovoltaic string based on the operating data and MPPT dynamic characteristic data of the photovoltaic string; The processing module is also used to generate MPPT strategy adjustment instructions based on the operating condition type of the photovoltaic string; The processing module is further configured to send the MPPT strategy adjustment command to the inverter, so that the inverter adjusts the operating voltage of the photovoltaic string based on the MPPT strategy adjustment command.

10. An electronic device, characterized in that, include: The processor includes a communication interface and a memory, wherein the processor is communicatively connected to the communication interface and the memory, respectively. The memory stores computer-executed instructions; The communication interface communicates and interacts with external devices. The processor executes computer execution instructions stored in the memory to implement the cloud-based collaborative method for adjusting photovoltaic power generation voltage as described in any one of claims 1 to 8.

Images