A power generation control method and device based on active and reactive power adjustment of photovoltaic power generation

Abstract

The present application discloses a power generation control method and device based on active and reactive power adjustment of photovoltaic power generation. The method includes obtaining a planned power generation curve assigned to a photovoltaic power plant by the power grid side and a predicted power generation curve generated by the photovoltaic power plant; judging whether the predicted power generation curve fits the planned power generation curve, and if it cannot fit, modifying the planned power generation curve by deep learning and resending it to the photovoltaic power plant; if it fits, judging whether the measured power generation curve of the active power and reactive power of the photovoltaic power plant fits the predicted power generation curve. If it cannot fit, modify the panel cleaning plan of the photovoltaic power plant; if it fits, the photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the planned power generation curve. Through two fitting judgments, the planned power generation curve is close to the predicted power generation curve, and the measured power generation curve is close to the predicted power generation curve, thereby improving the certainty of photovoltaic power generation control. The equipment life and equipment working performance are guaranteed, and the difficulties in power generation control of photovoltaic power plants are broken through.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a power generation control method and device based on active and reactive power adjustment of photovoltaic power generation. Background Art

[0002] In the power system, the grid controls the frequency through active power and the voltage through reactive power. Power plants are often required to cooperate in power generation according to the needs of the grid side. Among them, there are many requirements for power plants to cooperate in generating more active power or more reactive power. Due to the strong uncertainty of the power generation of some types of power plants (such as photovoltaic power plants), and the characteristics of the equipment used in different types of power plants are different. These factors also further increase the difficulty of power generation control in the power system. If the control is improper, it is very likely to cause damage to the power plant equipment, the power generated will not meet the needs of the grid, or the controllability of power generation costs or electricity costs will be reduced. At present, for photovoltaic power generation scenarios with strong uncertainty, how to achieve effective power generation control is a technical problem that needs to be solved urgently in the power system. Summary of the invention

[0003] Based on the above problems, the present application provides a power generation control method and device based on active and reactive power adjustment of photovoltaic power generation, with the aim of providing a power generation control solution for photovoltaic power plants, which effectively overcomes the difficulties in power generation control.

[0004] The embodiments of the present application disclose the following technical solutions:

[0005] The first aspect of the present application provides a power generation control method based on active and reactive power adjustment of photovoltaic power generation, the method comprising:

[0006] Obtaining a planned power generation curve of active power and reactive power allocated to the photovoltaic power plant by the grid side, and obtaining a predicted power generation curve of active power and reactive power generated by the photovoltaic power plant itself;

[0007] Determining whether the predicted power generation curve fits the planned power generation curve;

[0008] If the predicted power generation curve cannot fit the planned power generation curve, the grid side modifies the planned power generation curve through deep learning and resends it to the photovoltaic power plant after the modification is completed; if the predicted power generation curve fits the planned power generation curve, it is determined whether the measured power generation curves of active power and reactive power of the photovoltaic power plant fit the predicted power generation curve;

[0009] If the measured power generation curve cannot fit the predicted power generation curve, the panel cleaning plan of the photovoltaic power plant is modified; if the measured power generation curve fits the predicted power generation curve, the photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve.

[0010] In an optional implementation, the photovoltaic power plant performs power generation control based on safety requirements of power plant equipment and a received planned power generation curve, including:

[0011] Determine whether the photovoltaic power plant meets the safety requirements of power plant equipment if the photovoltaic power plant performs conversion control of active power and reactive power during power generation according to the planned power generation curve;

[0012] If the safety requirement is met, the photovoltaic power plant performs power generation control based on the planned power generation curve; if the safety requirement is not met, the photovoltaic power plant performs power generation control based on the planned power generation curve through peak shaving technology.

[0013] In an optional implementation, the determining whether the safety requirements of power plant equipment of the photovoltaic power plant are met if the photovoltaic power plant performs conversion control of active power and reactive power during power generation according to the planned power generation curve, includes:

[0014] Determine whether the current and temperature of the equipment of the photovoltaic power plant meet the safety requirements if the photovoltaic power plant performs conversion control of active power and reactive power during power generation according to the planned power generation curve, and whether the operating voltage of the equipment of the photovoltaic power plant is normal.

[0015] In an optional implementation, the photovoltaic power plant controls power generation based on the planned power generation curve by using peak shaving technology, including:

[0016] The conduction angle of the thyristor of the photovoltaic power plant is adjusted to perform peak shaving.

[0017] In an optional implementation, before performing power generation control, the method further includes:

[0018] Analyze the change characteristics of active power and reactive power of the inverter of the photovoltaic power plant under the influence of voltage factors, and determine the inflection point information in the change characteristic curve of active power and reactive power under different voltages, wherein the inflection point information includes the value on the reactive power coordinate axis and the value on the active power coordinate axis;

[0019] Perform power generation control, including:

[0020] The reactive power value of the inverter is controlled to be smaller than the value of the reactive power coordinate axis in the inflection point information.

[0021] In an optional implementation, the grid side modifies the planned power generation curve through deep learning, including:

[0022] The grid side deeply learns the difference between the actual daily power generation of the photovoltaic power plant and the historical daily power generation, and learns the difference between the comprehensive efficiency of the photovoltaic power plant and the comprehensive efficiency of the same period in history, combines the panel cleaning degree data of the photovoltaic power plant to identify the impact of fog, and adjusts the planned power generation curve.

[0023] In an optional implementation, the modifying of the panel cleaning scheme of the photovoltaic power plant includes:

[0024] Analyze the difference between the measured daily power generation and the historical daily power generation of the photovoltaic power plant;

[0025] Analyzing the corresponding relationship between panel cleaning degree data and power generation efficiency in each partition of the photovoltaic power plant;

[0026] Based on the difference in power generation, the corresponding relationship obtained by analyzing the difference between the comprehensive efficiency of each sub-area of ​​the photovoltaic power plant and the comprehensive efficiency of each sub-area in the same period in history, and the difference between the overall comprehensive efficiency of the photovoltaic power plant and the overall comprehensive efficiency in the same period in history, obtain the degree of influence of fog on each sub-area;

[0027] Modify the current panel cleaning plan based on the degree of impact of fog on each zone.

[0028] In an optional implementation, modifying the current panel cleaning solution based on the degree of influence of the mist on each partition includes:

[0029] Generate panel cleaning suggestion information based on the degree of influence of fog on each partition; the panel cleaning suggestion information includes at least one of the following: area cleaning suggestion information, cleaning frequency suggestion information, cleaning speed suggestion information, and cleaning manpower allocation suggestion information;

[0030] The current panel cleaning plan is modified based on the panel cleaning suggestion information.

[0031] In an optional implementation, the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant by the grid side is generated by:

[0032] The grid side determines the load curve to be allocated to each power plant based on the characteristic production factor data of each power plant and the control production factor data of the grid side, including the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant, among which the frequency is controlled by active power and the voltage is controlled by reactive power.

[0033] In an optional implementation, the photovoltaic power plant generates a predicted power generation curve of active power and reactive power, including:

[0034] The photovoltaic power plant generates a predicted power generation curve of active power and reactive power based on equipment performance, weather data and historical power generation in the same period. The equipment performance includes the change characteristics of active power and reactive power of the inverter under the influence of voltage factors.

[0035] In an optional implementation, before the photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve, the method further includes:

[0036] The photovoltaic power plant sends the power quantity data and cost data of the photovoltaic power abandonment auxiliary function to the power grid side;

[0037] If the photovoltaic power plant receives a control instruction from the power grid, it performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve; the control instruction is sent by the power grid after reaching a transaction intention with the photovoltaic power plant based on the power data and the cost data.

[0038] The second aspect of the present application provides a power generation control device based on active and reactive power adjustment of photovoltaic power generation, the device comprising:

[0039] A curve acquisition module is used to acquire the planned power generation curve of the active power and reactive power allocated to the photovoltaic power plant by the grid side, and to acquire the predicted power generation curve of the active power and reactive power generated by the photovoltaic power plant itself;

[0040] A fitting judgment module, used to judge whether the predicted power generation curve fits the planned power generation curve;

[0041] A curve modification module, used for modifying the planned power generation curve by deep learning on the grid side if the predicted power generation curve cannot fit the planned power generation curve, and resending it to the photovoltaic power plant after the modification is completed;

[0042] The fitting judgment module is further used to judge whether the measured power generation curve of active power and reactive power of the photovoltaic power plant fits the predicted power generation curve if the predicted power generation curve fits the planned power generation curve;

[0043] A cleaning scheme modification module, used for modifying the panel cleaning scheme of the photovoltaic power plant if the measured power generation curve cannot fit the predicted power generation curve;

[0044] A power generation control module is used to control power generation of the photovoltaic power plant based on safety requirements of power plant equipment and the received planned power generation curve if the measured power generation curve fits the predicted power generation curve.

[0045] Compared with the prior art, this application has the following beneficial effects:

[0046] The present application discloses a power generation control method and device based on active and reactive power adjustment of photovoltaic power generation. The method includes: obtaining the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant by the power grid side, and obtaining the predicted power generation curve of active power and reactive power generated by the photovoltaic power plant itself; judging whether the predicted power generation curve fits the planned power generation curve, if it cannot fit, modifying the planned power generation curve by deep learning and resending it to the photovoltaic power plant; if it fits, judging whether the measured power generation curve of active power and reactive power of the photovoltaic power plant fits the predicted power generation curve. If the measured power generation curve cannot fit the predicted power generation curve, modify the panel cleaning plan of the photovoltaic power plant; if the measured power generation curve fits the predicted power generation curve, the photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve. In the technical solution of the present application, by analyzing whether the predicted power generation curve fits the planned power generation curve, and in the case of failure to fit, the power grid side continues to perform deep learning to adjust the planned power generation curve and resend it to the photovoltaic power plant, the load plan on the power grid side can be more stably tended to the power generation trend predicted by the photovoltaic power plant itself. By analyzing whether the measured power generation curve fits the predicted power generation curve, and adjusting the panel cleaning plan of the photovoltaic power plant accordingly, the measured situation can be improved, so that the subsequent measured power generation curve can be close to the predicted power generation curve, greatly improving the certainty of photovoltaic power generation control in the power system. Photovoltaic power plants control power generation based on the safety requirements of power plant equipment, which also guarantees the life of the equipment and the performance of the equipment. It can be seen that this application takes into account the needs of both the power plant side and the grid side, and effectively breaks through the difficulties in power generation control of photovoltaic power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0048] Figure 1 A schematic diagram of a power system scenario provided in an embodiment of the present application;

[0049] Figure 2 A flow chart of a power generation control method based on active and reactive power adjustment of photovoltaic power generation provided in an embodiment of the present application;

[0050] Figure 3 is a schematic diagram of an inverter characteristic curve;

[0051] Figure 4 A curve comparison diagram provided for an embodiment of the present application;

[0052] Figure 5 A schematic diagram of the variation of the comprehensive efficiency of a photovoltaic power plant with the amount of radiation provided in an embodiment of the present application;

[0053] Figure 6 An example flow chart for modifying a panel cleaning program for a photovoltaic power plant;

[0054] Figure 7 A flow chart of another power generation control method based on active and reactive power adjustment of photovoltaic power generation provided in an embodiment of the present application;

[0055] Figure 8 Signaling diagram for overall power control of the power system;

[0056] Fig.9A Schematic diagram for setting up segmented power factor control;

[0057] Fig. 9B This is a comparison diagram of the peak shaving effect;

[0058] Fig.10 A schematic diagram of the structure of a power generation control device based on active and reactive power adjustment of photovoltaic power generation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] Figure 1 Figure 1 is a schematic diagram of a power system scenario. Figure 1 As shown, power plants of various different power generation types (such as photovoltaic, thermal power, wind power, nuclear power, hydropower, etc.) may communicate with the grid side and transmit electricity. These different types of power supply points can be collectively referred to as the power plant side. In the embodiment of the present application, the power plant side can report its own data to the grid side and give timely feedback; the grid side can dispatch the power plant side, such as voltage, frequency, power, etc. In the actual power production process, the grid side and the power plant side need to be closely dispatched to better and more stably realize the power supply and maintain the cost demands of both parties. In actual scenarios, the configuration of the power plant side is not limited to Figure 1 There are several types of power plants shown in the figure. Due to the differences in the level of power development, basic power facilities, and abundance of natural resources in each country, the power system structure of some countries may only include Figure 1 Some types of power plants are shown in .

[0060] As mentioned above, the power generation of photovoltaic power plants is affected by factors such as weather and seasons, with strong uncertainty and great difficulty in power generation control. At present, there is a lack of effective power generation control solutions. In this regard, in the technical solution of this application, the inventor proposes to first obtain the planned power generation curve assigned to the photovoltaic power plant by the power grid side and the predicted power generation curve generated by the photovoltaic power plant; determine whether the predicted power generation curve fits the planned power generation curve (the first fitting judgment), if it cannot fit, deep learning modifies the planned power generation curve and resends it to the photovoltaic power plant; if it fits, it determines whether the measured power generation curve of the active power and reactive power of the photovoltaic power plant fits the predicted power generation curve (the second fitting judgment). If it cannot fit, modify the panel cleaning plan of the photovoltaic power plant; if it fits, the photovoltaic power plant controls power generation based on the safety requirements of the power plant equipment and the planned power generation curve. There are two fitting judgments before and after. The first fitting judgment, if it does not fit, the power grid side makes changes: modify the planned power generation curve through deep learning, so that the planned power generation curve is close to the predicted power generation curve, and promotes the two parties to reach a consensus on the subsequent photovoltaic power generation. The second fitting judgment, by changing the cleaning plan of the photovoltaic panels, makes the measured power generation curve close to the predicted power generation curve. The above measures will improve the certainty of photovoltaic power generation control, ensure the equipment life and equipment performance, break through the difficulties in photovoltaic power plant power generation control, and effectively solve the current technical problems.

[0061] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] Figure 2 The flowchart of a power generation control method based on active and reactive power adjustment of photovoltaic power generation is provided in an embodiment of the present application. Figure 2 As shown, the power generation control method based on active and reactive power adjustment of photovoltaic power generation provided by the present application includes:

[0063] S201. Obtain a planned power generation curve of active power and reactive power allocated to a photovoltaic power plant by a power grid, and obtain a predicted power generation curve of active power and reactive power generated by the photovoltaic power plant itself.

[0064] In an embodiment of the present application, the grid side can determine the load curve to be allocated to each power plant based on the characteristic production factor data of each power plant and the control production factor data of the grid side, including the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant, wherein the frequency is controlled by active power and the voltage is controlled by reactive power.

[0065] The basis for dividing the production factors on the power plant side is called the characteristic production factor group; the basis for dividing the production factors on the power grid side is called the controlling production factor group.

[0066] The characteristic production factor group includes characteristic production factors of multiple levels. Specifically, these characteristic production factors can be subdivided into: primary characteristic production factors, secondary characteristic production factors and tertiary characteristic production factors. Among them, the primary characteristic production factors are natural characteristic production factors (or called: natural indicators), which are production factors that can directly reflect natural characteristics. The secondary characteristic production factors are single-system characteristic production factors (or called: single-system indicators), which are production factors involving individual systems in the power system. The tertiary characteristic production factors are plant system characteristic production factors (or called: plant system indicators), which are production factors involving the entire system in the power system. Combined with Figure 1 As shown, there are various types of power plants, such as thermal power plants, photovoltaic power plants, wind power plants, hydropower plants, etc., which use different power generation methods, and the natural resources used and the internal system structures are also different. In order to more accurately realize digital power analysis, in the technical solution of this application, for various types of power generation, the first-level characteristic production factors, second-level characteristic production factors and tertiary characteristic production factors can be subdivided. Therefore, for each type of power plant, the data of the characteristic production factors of the corresponding level can be subsequently extracted.

[0067] In the embodiments of the present application, the introduction is mainly oriented to photovoltaic power plants. The characteristic production factor data of photovoltaic power plants based on the grid side mainly involves the data of primary characteristic production factors and the data of tertiary characteristic production factors. Taking photovoltaic power generation as an example, the primary characteristic production factor may include photovoltaic illumination, and the tertiary characteristic production factor may include photovoltaic efficiency.

[0068] The control production factor group includes multiple aspects of control production factors. Control production factors are production factors that reflect the performance of the power grid, which are composed of some key physical quantities in the power system. Control production factors help to provide an effective theoretical basis for power system control. In the embodiment of the present application, the control production factors involved may include the relationship between active power, reactive power and voltage. The control production factor data format can be (voltage, active power, reactive power). In the power system, voltage and frequency have no direct relationship, but they are related to power (active power and reactive power, respectively), resulting in an indirect relationship. When reactive power is insufficient, the voltage drops, and when reactive power is excessive, the voltage rises; when active power is insufficient, the frequency drops, and when active power is excessive, the frequency rises.

[0069] The characteristic production factor data of the power plant can be transmitted to the grid side, so that the grid side can timely understand the specific values ​​of the characteristic production factor data of the power plant. In addition, the data can be processed into vector form through digital processing for deep learning and use. For photovoltaic power plants, the grid side can determine the load curve to be allocated to the photovoltaic power plant based on the characteristic production factor data of the photovoltaic power plant (photovoltaic illumination, photovoltaic efficiency, etc.) and the control production factor data of the grid side, that is, the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant.

[0070] As an example, the grid side establishes an illumination data vector based on the photovoltaic illumination data in 2023 provided by the power plant side, and constructs a mapping function based on the vector and the control production factor data, and uses the mapping function to predict the power grid electricity. In addition, based on data-driven incentives and digital processing of data provided by the power plant side, the trend of active and reactive power in the power grid is predicted. Based on the mechanism of the power grid and power generation equipment, the power generation control logic on the grid side is formed. For example, when the voltage decreases, the reactive power on the power plant side is increased, and when the frequency decreases, the active power on the power plant side is increased. In addition, there may be a certain connection between the capacity and frequency of different types of power generation equipment. The grid side can also combine this connection to comprehensively consider the planned power generation curves allocated to each power plant.

[0071] In addition, the grid side can also generate a planned power generation curve in combination with the equipment mechanism (or equipment characteristics). Taking a photovoltaic power plant as an example, in the characteristic curve (PQ curve) of the inverter's active power and reactive power, the horizontal axis represents reactive power and the vertical axis represents active power. Figure 3 Figure 1 is a schematic diagram of an inverter characteristic curve. Figure 3 As shown in the figure, different curves represent the trend of active power changing with reactive power of the same inverter at different voltages. In the figure, Un represents voltage, PU is per unit value, dimensionless, Q represents reactive power, unit kVar, and P represents active power, unit kW. It can be seen from the figure that in the first quadrant, as the horizontal axis increases, the vertical axis tends to gradually decrease. And after reaching a certain position, the trend of the vertical axis decreasing with the increase of the horizontal axis is too obvious (it can be understood as the slope is too large, or the slope exceeds a certain threshold). For this reason, the turning point on the curve with significant changes is called the inflection point. The grid side can determine that the active power reduction caused by the increase in reactive power is too large, and give the corresponding planned power generation curve according to the equipment mechanism of different power plants. During this period, the influence of voltage and frequency can be taken into account, and the characteristics of the equipment can be taken into account, so that the generated planned power generation curve controls reactive power without excessively affecting active power.

[0072] The power plant also combines equipment performance and historical power generation data to generate a forecast power generation curve. For a photovoltaic power plant, the photovoltaic power plant can optionally generate a forecast power generation curve for active power and reactive power based on equipment performance, weather data, and historical power generation. Among them, the equipment performance also includes the change characteristics of the active power and reactive power of the inverter used in the photovoltaic power plant under the influence of voltage factors, which can be seen in Figure 3 .

[0073] For ease of understanding, examples of planned power generation curves and predicted power generation curves are shown in the accompanying drawings. Figure 4 A curve comparison chart provided for an embodiment of the present application. In the figure, the horizontal axis represents time, and the vertical axis represents power generation (unit: kW·h). Among them, the red curve represents the planned power generation curve generated by the power grid, the green curve represents the predicted power generation curve generated by the photovoltaic power plant, and the blue curve represents the measured power generation curve of the photovoltaic power plant. A point on the curve represents the power generation on a certain day in a certain month.

[0074] It is understandable that the planned power generation curve represents the planning expectations of the grid side, and the predicted power generation curve represents the achievable expectations of the power plant side. In order to better complete the power generation control of the photovoltaic power plant, it is also necessary for the grid side and the power plant side to reach a common understanding. For example, if the deviation between the planned power generation curve and the predicted power generation curve is too large, on the one hand, the power plant may not be able to respond to the dispatch of the grid side, and the two parties cannot reach a consensus on electricity prices, electricity, etc. to facilitate transactions. On the other hand, even if the requirements of the grid side are responded to, they will not be met in the end. In some cases, it may even damage the equipment of the power plant, resulting in a significant reduction in equipment life and an increase in power generation costs. To this end, the two curves can be analyzed by fitting judgment to see if they are fitting, and then corresponding measures can be taken according to the judgment. The following is an introduction in conjunction with S202~S204.

[0075] S202, judging whether the predicted power generation curve fits the planned power generation curve. If the predicted power generation curve does not fit the planned power generation curve, proceed to S203; if the predicted power generation curve fits the planned power generation curve, proceed to S204.

[0076] In the embodiment of the present application, the fitting judgment of the predicted power generation curve and the planned power generation curve can be referred to as the first fitting judgment in the technical solution process of the embodiment of the present application. The first fitting judgment mainly analyzes whether the difference between the predicted power generation curve and the planned power generation curve is too large. If the fitting cannot be performed, it means that the curve difference is too large. If the fitting can be performed, it means that the curve difference is within an acceptable range.

[0077] In addition to visually analyzing whether the two curves fit, other fitting evaluation methods that can be implemented automatically can also be used to make judgments in this step. For example, the fitting effect of the two curves can be evaluated by statistical means such as residual analysis, R square value, least squares method, root mean square error, and mean absolute error. The statistical tools and comparison methods used for judgment are not limited here.

[0078] If the predicted power generation curve fits the planned power generation curve, it means that the planned power generation curve on the power grid side is feasible. Then the subsequent operation process can be executed to enter S204, and the power plant side will make a second fitting judgment. If the predicted power generation curve does not fit the planned power generation curve, it means that the planned power generation curve on the power grid side lacks feasibility. In this case, by implementing S203, the power grid side can actively modify the planned power generation curve to improve the feasibility of the modified planned power generation curve. The following introduces and explains the two processing branches after the first fitting judgment in combination with S203 and S204.

[0079] S203: The grid side modifies the planned power generation curve through deep learning, and resends it to the photovoltaic power plant after the modification is completed.

[0080] When this step is implemented specifically, the grid side can deeply learn the difference between the actual daily power generation of the photovoltaic power plant and the historical daily power generation, and learn the difference between the comprehensive efficiency of the photovoltaic power plant and the comprehensive efficiency of the same period in history, combine the panel cleaning degree data of the photovoltaic power plant to identify the impact of fog, and adjust the planned power generation curve.

[0081] The measured daily power generation of a photovoltaic power plant can be obtained through actual measurement and data collection. The historical daily power generation can be obtained by collecting historical data. For example, the historical daily power generation data of the photovoltaic power plant in 2022 and 2023 are collected into a historical data database. In response to the deep learning needs of the power grid side, such historical daily power generation data are retrieved from the database and sent to the power grid side. Alternatively, the power grid side also has the authority to query the historical daily power generation data of the photovoltaic power plant from the database. When the power grid side needs to perform deep learning, it can directly query and retrieve data from the database to complete its deep learning purpose. Similarly, in addition to the relevant data on daily power generation, the comprehensive efficiency of photovoltaic power plants can also be compared over the same period. Figure 5 A schematic diagram of the variation of the comprehensive efficiency of a photovoltaic power plant with the amount of radiation provided in an embodiment of the present application. Figure 5 The horizontal axis represents the radiation, in kW·h / m 2; The vertical axis represents the comprehensive efficiency, which is dimensionless. Data points of the same color represent the same month. The dashed lines of different colors in the figure are regression lines formed by aggregating the data points of the corresponding colors. It can be seen from the dashed lines in the figure that there are differences in the regression lines fitted in different months, which means that the trend of comprehensive efficiency changing with radiation in different months may be different.

[0082] In the embodiment of the present application, data points with a large deviation from the regression line can be eliminated. The elimination of some data points can ensure the simulation reliability of the overall data, and at the same time, the comparison of historical efficiency, current efficiency, and efficiency trend can provide good guidance and correction for power forecasting and intraday trading.

[0083] Similar to Figure 5 , the grid side can compare the comprehensive efficiency of the photovoltaic power plant this year with the comprehensive efficiency of the same period in history, and then learn the differences in comprehensive efficiency.

[0084] In the embodiment of the present application, the degree of panel cleaning is also taken into consideration during the process of deep learning on the grid side to modify the planned power generation curve. Figure 4 As shown, the planned power generation curve at certain times deviates too much from the predicted power generation curve. In addition, the measured daily power generation on certain dates is very different from the daily power generation in the same historical period, or the comprehensive efficiency of the photovoltaic power plant on certain dates is very different from the photovoltaic efficiency in the same historical period. The reason for the huge difference in data for the same period may be the impact of haze weather. Generally speaking, haze lasts for a long time and has a greater impact on photovoltaic power generation, and haze particles cover the surface of the panels, which may still have a lasting impact on the photovoltaic panels after the haze ends. In this regard, the power grid side can identify the impact of haze in combination with the panel cleaning degree data of the photovoltaic power plant. For ease of understanding, the following example introduces the impact of panel cleaning on power generation efficiency.

[0085] The photovoltaic power plant is equipped with box transformer unit T01 and box transformer unit T02. Table 1 shows the radiation on multiple dates, T01 power generation, T01 cumulative cleaning ratio, T01 unit system efficiency, T02 power generation, T02 cumulative cleaning ratio, T02 unit system efficiency, the system efficiency gap between T01 and T02, and the power generation efficiency of two sets of inverters (T01-I26 and T01-I27) of T01.

[0086] In this example, statistics are collected from December 1, 2020 to January 4, 2021. Since December 1, 2020, the system efficiency has gradually decreased from 80% to about 75%. On December 6, 2020, the backend network cable was accidentally knocked off by the Internet company, resulting in the loss of some radiation data and distortion of the system efficiency. From December 9 to December 15, 2020, there was heavy fog in the week, and there was garbage and waste burning around the project site at night. The system efficiency during this period was inaccurate. As can be seen from Table 1, since December 22, 2020, the T01 box transformer unit has been cleaned, and the cumulative cleaning ratio of T01 has begun to appear. From December 22, 2020, when the component cleaning started, to January 4, 2021, the system efficiency of the T01 unit gradually increased from 76% to 89%, an increase of about 13%. T02 has not been cleaned during the statistical period, so the cumulative cleaning ratio of T02 is always 0.00%. Before the cleaning of the components in the T01 box-type transformer area (before December 22), the power generation efficiency of T01 and T02 was equivalent, and the weighted average of the efficiency difference was only about 1.6%. After the components were cleaned, the power generation efficiency difference between T01 and T02 box-type transformers gradually increased from 1.16% to 11.81%. After the cleaning of the T01-I26 inverter (cleaned 11 days ago) and the T01-I27 inverter (cleaned 12 days ago), the power generation efficiency did not fluctuate much. However, it can still be seen that the T01-I26 inverter has a small advantage in power generation efficiency because it was cleaned one day later than the T01-I27 inverter.

[0087] By comparing the data in Table 1, we can draw the following conclusions:

[0088] According to the comparison of the power generation efficiency of T01 and T02 units, it can be seen that the cleaning of photovoltaic modules will greatly improve the power generation efficiency of the system, with an efficiency increase of about 10%. According to the power generation of T01-I26 and T01-I27 inverters more than 10 days after cleaning, it can be seen that the power generation efficiency has not dropped significantly, and the small amount of dust after cleaning has little effect on the power generation efficiency in a short period of time. After the haze weather from December 9 to December 15, 2020, the system efficiency showed a large fluctuation. The main reason was that the haze caused the difference between the measured radiation data of the meteorological station and the actual radiation received by the photovoltaic panels. At the same time, after the weather turned clear on December 16, 2020, the haze adhered to the photovoltaic module panel solidified due to exposure to the sun, which is also a possible reason for the further decline in system efficiency.

[0089] Through the above examples, it is not difficult to see that by analyzing the panel cleaning degree data of photovoltaic power plants, the impact of fog can be better and more accurately identified. The grid side can also use multi-source data to drive the modification and adjustment of the planned power generation curve through deep learning.

[0090] Table 1

[0091]

[0092] S204, judging whether the measured power generation curve of the active power and reactive power of the photovoltaic power plant fits the predicted power generation curve. If the measured power generation curve cannot fit the predicted power generation curve, proceed to S205; if the measured power generation curve fits the predicted power generation curve, proceed to S206.

[0093] Combined with the introduction of S202 above, if the result of the first fitting judgment is yes, it means that the planned power generation curve on the grid side is feasible. To this end, it is also necessary to analyze whether the measured situation of the photovoltaic power plant matches the expectation. Then, the second fitting judgment is continued through S204. The specific judgment content is: determine whether the measured power generation curve of the active power and reactive power of the photovoltaic power plant fits the predicted power generation curve. For more information about the measured power generation curve and the predicted power generation curve, please refer to Figure 4 As shown, it should be understood. Figure 4 In the example, the green curve represents the predicted power generation curve of the photovoltaic power plant, and the blue curve represents the measured power generation curve of the photovoltaic power plant. The fitting effect of the two curves can be evaluated by statistical means such as residual analysis, R square value, least squares method, root mean square error, and mean absolute error. In a possible implementation, the analysis method used in the first fitting judgment is consistent with the analysis method used in the second fitting judgment.

[0094] If the measured power generation curve fits the predicted power generation curve, it means that the deviation between the actual power generation of the photovoltaic power plant and the expected power generation is within an acceptable range. Then, the process can proceed to S206 to implement the power generation process in combination with safety requirements.

[0095] However, if the measured power generation curve cannot fit the predicted power generation curve, this means that the actual power generation of the photovoltaic power plant deviates greatly from the expected power generation. In this case, if power generation is still carried out according to the received planned power generation curve, it is obvious that the power generation effect planned on the grid side cannot be achieved. In order to promote the successful and stable completion of transactions between grid power plants, it is also necessary to implement corresponding solutions on the power plant side to improve the actual power generation of photovoltaic power plants. Then, enter S205 and start processing from the aspect of panel cleaning of the photovoltaic power plant itself. The following introduces and explains the two processing branches after the first fitting judgment in combination with S205 and S206.

[0096] S205: modifying the panel cleaning plan of the photovoltaic power plant.

[0097] The modification of the panel cleaning scheme is mainly due to the fact that the currently used panel cleaning scheme may not meet the requirements of high-efficiency power generation in terms of speed, frequency or coverage, which in turn leads to a large deviation between the measured power generation curve and the predicted power generation curve of the photovoltaic power plant. To this end, the embodiment of this application proposes to use data as a driving force to analyze the difference in power generation, the relationship between panel cleaning and power generation efficiency, and the difference in comprehensive efficiency over the same period, obtain the degree of influence of fog on each partition, and then modify the current panel cleaning scheme based on the degree of influence. Figure 6 This is an example flow chart for modifying the panel cleaning plan of a photovoltaic power plant. Figure 6 As shown, this process may include:

[0098] S2051. Analyze the difference between the actual daily power generation of the photovoltaic power plant and the historical daily power generation.

[0099] S2052: Analyze the corresponding relationship between the panel cleaning degree data and the power generation efficiency of each partition of the photovoltaic power plant.

[0100] In the embodiment of the present application, the photovoltaic power plant can collect the measured daily power generation and historical daily power generation in the power plant, and can also obtain the panel cleaning degree data and corresponding power generation efficiency data of each partition. Through data statistics and processing, it is possible to analyze the difference between the measured daily power generation and the historical daily power generation of the photovoltaic power plant, and analyze the corresponding relationship between the panel cleaning degree data and the power generation efficiency of each partition of the photovoltaic power plant.

[0101] S2053. Based on the difference in power generation, the corresponding relationship obtained by analysis is the difference between the comprehensive efficiency of each zone of the photovoltaic power plant and the comprehensive efficiency of each zone in the same period in history, and the difference between the overall comprehensive efficiency of the photovoltaic power plant and the overall comprehensive efficiency in the same period in history, to obtain the degree of influence of fog on each zone.

[0102] In order to analyze the degree of influence of fog on each partition, this step also analyzes the difference between the comprehensive efficiency of each partition and the comprehensive efficiency of each partition in the same period of history, as well as the difference between the overall comprehensive efficiency of the photovoltaic power plant and the overall comprehensive efficiency in the same period of history. Thus, the degree of influence of fog on a single partition is analyzed from the dimension of the partition and the overall dimension of the photovoltaic power plant. For example, if the power generation efficiency of a partition is low and the cleaning ratio is low, it is very likely that the low power generation efficiency is caused by inadequate cleaning and untimely cleaning. The degree of influence of fog on the partition represents the degree of interference of the partition's unsatisfactory power generation efficiency with fog.

[0103] S2054. Modify the current panel cleaning plan based on the degree of impact of the fog on each partition.

[0104] Generating panel cleaning suggestion information based on the degree of influence of fog on each partition; then, modifying the current panel cleaning plan based on the panel cleaning suggestion information. The panel cleaning suggestion information includes at least one of the following: regional cleaning suggestion information, cleaning frequency suggestion information, cleaning speed suggestion information, and cleaning manpower allocation suggestion information.

[0105] The regional cleaning suggestion information may be a suggestion for a cleaning ratio or a cleaning priority for certain specific partitions.

[0106] The cleaning frequency recommendation information may provide a recommended cleaning frequency, for example, it is recommended to clean once every two months, and in months with frequent haze, the cleaning frequency may be increased to once every half a month, etc.

[0107] The cleaning speed recommendation information may provide a recommended cleaning speed, for example, it is recommended to complete the cleaning of all panels in the partition within 10 days.

[0108] The cleaning manpower allocation suggestion information may be a suggested manpower allocation scale, for example, each zone is originally responsible for cleaning by 15 people, and after increasing the cleaning manpower allocation, it is changed to 25 people responsible for cleaning. In this way, the power generation of the zone can be restored to an ideal state more quickly.

[0109] S206: The photovoltaic power plant performs power generation control based on safety requirements of power plant equipment and the received planned power generation curve.

[0110] If the result of the second fitting judgment is yes, the actual power generation of the photovoltaic power plant can approach the power plant's own prediction, and because the first fitting judgment is performed and the result of the first fitting judgment is yes, the second fitting judgment will be entered, so the premise of executing S206 is that the results of both fitting judgments are yes. Under this premise, it means that the actual power generation can also match the grid's plan for the photovoltaic power plant. Next, the photovoltaic power plant can control power generation based on the safety requirements of the power plant equipment and the received planned power generation curve, so that the final power generation effect can not only meet the planning and needs of the grid side, but also maintain the operating needs of the power plant equipment and the demand for equipment safety.

[0111] Specifically, this step can first make the following judgment:

[0112] Determine whether the photovoltaic power plant meets the safety requirements of the power plant equipment of the photovoltaic power plant if it performs conversion control of active power and reactive power during power generation according to the planned power generation curve; if the safety requirements are met, the photovoltaic power plant performs power generation control based on the planned power generation curve; if the safety requirements are not met, the photovoltaic power plant performs power generation control based on the planned power generation curve through peak shaving technology.

[0113] Among them, the judgment on safety requirements can specifically be: judging whether the current and temperature of the equipment of the photovoltaic power plant meet the safety requirements if the photovoltaic power plant performs conversion control of active power and reactive power during the power generation process according to the planned power generation curve, and whether the working voltage of the equipment of the photovoltaic power plant is normal.

[0114] Current, temperature and operating voltage are conventional parameters that can be collected when the equipment of a photovoltaic power plant is working. If a photovoltaic power plant is operated, but the impact of the fluctuations of these parameters on the safety performance of the equipment is ignored, a safety accident is likely to occur, and the ecological environment may even be damaged. In addition, the guarantee of performance safety corresponds to the power generation cost of the power plant. If you only consider power generation without considering the safety performance of the equipment, it is likely to cause frequent equipment failures, resulting in frequent replacement of equipment and unnecessary equipment losses. Data on rated power, rated current and rated operating temperature can be obtained from the factory configuration or user guide of the equipment. In the embodiment of the present application, by analyzing the current, temperature and operating voltage of the equipment of the photovoltaic power plant, it is determined whether the conversion control of active power and reactive power during the power generation process according to the planned power generation curve meets the safety requirements. So that the stability and reliability of photovoltaic power generation in the power system are guaranteed.

[0115] In the embodiment of the present application, if the safety requirements are not met, the photovoltaic power plant controls power generation based on the planned power generation curve through peak shaving technology. Generally speaking, some photovoltaic power plants consider peak shaving to be achieved by disabling devices. However, according to the terms of the take-or-pay and PPA contracts (Power Purchase Agreement, a long-term power purchase contract signed between the power generator and the power purchaser), a certain amount of reactive power needs to be emitted. In low-voltage scenarios, the emission of reactive power will directly and significantly affect the active power according to the inverter characteristic curve, thereby affecting the power generation and electricity bills. Therefore, artificial intelligence is used to digitally analyze its physical process, adjust the reactive power in the time period of maximum output capacity, convert the excess active peak shaving into reactive power to meet the contract requirements, and reduce the usual reactive power generation to a minimum, and generate as much active power as possible. In specific implementation, the conduction angle of the thyristor of the photovoltaic power plant can be adjusted to perform peak shaving. In this way, in this solution, the current can be controlled and the safety and life of the equipment can be enhanced.

[0116] Before performing power generation control, the method further includes: analyzing the change characteristics of active power and reactive power of the inverter of the photovoltaic power plant under the influence of voltage factors, and determining the inflection point information in the change characteristic curve of active power and reactive power under different voltages;

[0117] The power generation control includes: controlling the reactive power value of the inverter to be smaller than the value of the reactive power coordinate axis in the inflection point information. The reactive power is controlled before reaching the inflection point to avoid the active power being seriously affected.

[0118] In the technical solution of the present application, by analyzing whether the predicted power generation curve fits the planned power generation curve, and in the case of failure to fit, the grid side is allowed to continue deep learning to adjust the planned power generation curve and resend it to the photovoltaic power plant, the load plan on the grid side can be more stably tended to the power generation trend predicted by the photovoltaic power plant itself. By analyzing whether the measured power generation curve fits the predicted power generation curve, and adjusting the panel cleaning plan of the photovoltaic power plant accordingly, the measured situation can be improved, so that the subsequent measured power generation curve can be close to the predicted power generation curve, greatly improving the certainty of photovoltaic power generation control in the power system. Photovoltaic power plants control power generation based on the safety requirements of power plant equipment, and also ensure the life of the equipment and the working performance of the equipment. It can be seen that this application takes into account the needs of both the power plant side and the grid side, and effectively breaks through the difficulties in power generation control of photovoltaic power plants.

[0119] Below through Figure 7 The power generation control method based on active and reactive power adjustment of photovoltaic power generation provided by the technical solution of the embodiment of the present application is generally described. Figure 7 Involving Figure 2 The steps shown are different from Figure 2 ,exist Figure 7 It also shows the process of generating the planned power generation curve and the predicted power generation curve on the grid side and the power plant side respectively before obtaining the planned power generation curve and the predicted power generation curve.

[0120] In addition, after completing the second fitting judgment (i.e., judging whether the measured power generation curve fits the predicted power generation curve), Figure 7 It also shows the steps of the photovoltaic power plant sending the electricity data and cost data of the abandoned light auxiliary function to the grid side, and the steps of the photovoltaic power plant receiving the control instructions from the grid side. The control instruction is sent by the grid side after reaching a transaction intention with the photovoltaic power plant based on the electricity data and the cost data. Therefore, if the photovoltaic power plant receives the control instruction, it means that the photovoltaic power plant and the grid side have reached a transaction agreement based on the electricity data and the cost data. In this way, real-time power generation control can be carried out according to the specific requirements of active power and reactive power in the planned power generation curve. In this control process, the safety requirements of the power plant equipment still need to be considered, and the reactive power generated should be controlled in combination with the changing characteristics of the active power and reactive power of the inverter.

[0121] In the embodiment of the present application, combined with the above introduction to photovoltaic power plant power generation control, a process of overall power control of a power system is also provided. Figure 8As shown in the figure, this is a signaling diagram for the overall power control of the power system. This figure shows the power plant side structure including photovoltaic power plants: photovoltaic power plants, hydropower plants and thermal power plants. The process for photovoltaic power plants has been introduced in detail above and will not be repeated here. Figure 2 and Figure 7 The power generation control process of hydropower plants and thermal power plants is similar to that of photovoltaic power plants, and both of them need to compare their respective production factor data with the corresponding data of the same period in history. For hydropower plants, some constraints on the production factor data of the power plants must also be specifically considered. Figure 8 As shown in the figure, whether it is a photovoltaic power plant, a hydropower plant or a thermal power plant, in order to achieve stable and accurate control, two fitting judgments need to be made: whether the predicted power generation of the power plant fits the planned power generation on the grid side, and whether the measured power generation of the power plant fits the predicted power generation of the power plant. The generator set acts according to the power generation control instruction, and the data generated will be included in the historical database through digital analysis, and serve as a digital asset for the subsequent dispatch and control of the power system.

[0122] The following is a further introduction to segmented control. Segmented control is used, that is, in different time periods, through the instructions issued by the grid dispatch (instructions generated by the weather and the digital twin of the grid), the virtual power plant function is realized for each photovoltaic power plant, the relevant power factors of active and reactive power are given, the maximum power limit value in each photovoltaic power plant is adjusted, and a specific power factor and active and reactive output value are generated, and finally each photovoltaic power plant is controlled to convert excess active power into reactive power. The significance of segmented control is: 1. Maintaining the stability of the power system, abandoning the way that photovoltaic power plants generate reactive power through SVG, and increasing the utilization of equipment; 2. Active power is converted into reactive power, so that excess active power can be utilized; 3. Virtual power plants aggregate and integrate resources to strengthen the coordination between photovoltaic power plants and other power types; 4. Segmented control makes the control flexible, and the application of data twins makes it possible to give a predetermined segmented function in advance according to the load, weather and working conditions, and dispatching has an additional handle for active and reactive power during the day; 5. Considering the safety of the power grid and power plants, photovoltaic power can be effectively controlled as an object of virtual power plants for system collapse or too low or too high voltage of the power grid, realizing the combination of artificial intelligence and power grid. Segmented control is conducive to the realization of peak shaving.

[0123] When performing segmented control, as an example, the power factor in the segmented function used from 5:30 to 9:30 is 0.95, and the power factor in the segmented function used from 9:30 to 14:00 is 0.97. Fig.9A The schematic diagram for setting the power factor in sections. Fig. 9B You can see the peak clipping effect. Fig. 9B The left side is before the segmented control peak clipping. Fig. 9B The right side shows the segmented control after peak clipping.

[0124] Under the given power requirement, a constant power factor of 0.95 is set to compensate reactive power from 05:30 to 09:30 and from 14:00 to 19:00 to achieve the required power factor value of 0.95.

[0125] To reduce active power loss, set the power factor to 0.97 from 09:30 to 14:00 PM, and pay attention to the inverter port voltage.

[0126] Here are some things to note about segment control:

[0127] 1. When the rated voltage value of the inverter output is ≥800Vac, the real-time reactive value should not exceed 26MVar; 2. If the inverter output voltage drops, pay attention to the change in the voltage value of the inverter port, and pay attention to the change in the reactive value of the entire power station, appropriately adjust the power factor value, and increase the reactive output; 3. The night reactive function of the inverter is turned off by default, and it needs to be set through management tools such as APP or data collector before it can be used. Calculate the reactive power that needs to be compensated in the power station to see how many inverters need to output reactive power at night. It is recommended that the number of inverters that need to output reactive power at night should be as small as possible. 4. When the night reactive compensation function needs to be enabled, the PID module must be used in the system, and the night PID protection parameter setting must be enabled. 5. It is necessary to confirm with the main transformer manufacturer whether the voltage regulating mechanism can be adjusted frequently under load conditions greater than 80%.

[0128] When the output voltage drops, whether the active output needs to be increased depends on the cause of the voltage drop and the specific conditions of the power system. The following are some logics and principles:

[0129] 1. Relationship between active power and voltage: In the power system, the relationship between active power (P) and voltage (U) and current (I) can be expressed by the formula P = UIcosφ (where cosφ is the power factor). If the load increases, the current I increases, and in order to keep the active power P unchanged, the voltage U must increase accordingly. If the voltage U decreases, then in order to maintain the same active power output, the current I must increase, which may lead to increased line losses and further voltage drops.

[0130] 2. Causes of voltage drop: Voltage drop may be caused by a variety of reasons, such as a sudden increase in grid load, a reduction in the output of a generator set, a failure in a transmission line, etc. If the voltage drop is caused by an increase in load, then it may be necessary to increase the active output of the generator to maintain grid voltage stability.

[0131] 3. Effect of reactive power: Reactive power has a more direct effect on voltage. Insufficient reactive power will lead to a decrease in voltage, because the inductance consumes reactive power, causing direct-axis demagnetization armature reaction in the synchronous generator, reducing the magnetic flux, thereby reducing the induced electromotive force and voltage. Therefore, increasing reactive output can help maintain or restore voltage levels.

[0132] 4. Grid stability: The stability of the grid depends not only on active power but also on reactive power. When the voltage drops, it may be necessary to consider the adjustment of both active and reactive power to ensure the stable operation of the grid.

[0133] 5. Dynamic Voltage Restorer (DVR): In some cases, the use of devices such as DVR can provide temporary voltage support when the voltage drops, reducing the reliance on active power output.

[0134] In summary, whether it is necessary to increase active output when the output voltage drops needs to be analyzed based on specific circumstances. Generally, the handling of voltage drops requires comprehensive consideration of the adjustment of active and reactive power, as well as the stability and security of the power grid. In actual operation, power grid operators will decide how to adjust power generation and power grid operating parameters based on real-time data and prediction models to cope with voltage drops.

[0135] Based on the method described in the above embodiment, the present application also provides a power generation control device based on active and reactive power adjustment of photovoltaic power generation. Fig.10 Make an introduction.

[0136] Fig.10 This is a schematic diagram of the structure of a power generation control device based on photovoltaic power generation active and reactive power adjustment provided in an embodiment of the present application. Fig.10 As shown, the device comprises:

[0137] A curve acquisition module is used to acquire the planned power generation curve of the active power and reactive power allocated to the photovoltaic power plant by the grid side, and to acquire the predicted power generation curve of the active power and reactive power generated by the photovoltaic power plant itself;

[0138] A fitting judgment module, used to judge whether the predicted power generation curve fits the planned power generation curve;

[0139] A curve modification module, used for modifying the planned power generation curve by deep learning on the grid side if the predicted power generation curve cannot fit the planned power generation curve, and resending it to the photovoltaic power plant after the modification is completed;

[0140] The fitting judgment module is further used to judge whether the measured power generation curve of active power and reactive power of the photovoltaic power plant fits the predicted power generation curve if the predicted power generation curve fits the planned power generation curve;

[0141] A cleaning scheme modification module, used for modifying the panel cleaning scheme of the photovoltaic power plant if the measured power generation curve cannot fit the predicted power generation curve;

[0142] A power generation control module is used to control power generation of the photovoltaic power plant based on safety requirements of power plant equipment and the received planned power generation curve if the measured power generation curve fits the predicted power generation curve.

[0143] In an optional implementation, the power generation control module is specifically used to:

[0144] Determine whether the photovoltaic power plant meets the safety requirements of power plant equipment if the photovoltaic power plant performs conversion control of active power and reactive power during power generation according to the planned power generation curve;

[0145] If the safety requirement is met, the photovoltaic power plant performs power generation control based on the planned power generation curve; if the safety requirement is not met, the photovoltaic power plant performs power generation control based on the planned power generation curve through peak shaving technology.

[0146] In an optional implementation, the power generation control module is specifically used to:

[0147] Determine whether the current and temperature of the equipment of the photovoltaic power plant meet the safety requirements if the photovoltaic power plant performs conversion control of active power and reactive power during power generation according to the planned power generation curve, and whether the operating voltage of the equipment of the photovoltaic power plant is normal.

[0148] In an optional implementation, the power generation control module is specifically used to:

[0149] The conduction angle of the thyristor of the photovoltaic power plant is adjusted to perform peak shaving.

[0150] In an optional implementation, the power generation control device based on active and reactive power adjustment of photovoltaic power generation further includes an inflection point information determination module, which is used to analyze the change characteristics of active power and reactive power of the inverter of the photovoltaic power plant under the influence of voltage factors before power generation control, and determine the inflection point information in the change characteristic curve of active power and reactive power under different voltages, wherein the inflection point information includes the value on the reactive power coordinate axis and the value on the active power coordinate axis;

[0151] The power generation control module is specifically used for:

[0152] The reactive power value of the inverter is controlled to be smaller than the value of the reactive power coordinate axis in the inflection point information.

[0153] In an optional implementation, the curve modification module is specifically used for:

[0154] The grid side deeply learns the difference between the actual daily power generation of the photovoltaic power plant and the historical daily power generation, and learns the difference between the comprehensive efficiency of the photovoltaic power plant and the comprehensive efficiency of the same period in history, combines the panel cleaning degree data of the photovoltaic power plant to identify the impact of fog, and adjusts the planned power generation curve.

[0155] In an optional implementation, the cleaning scheme modification module is specifically used to:

[0156] Analyze the difference between the measured daily power generation and the historical daily power generation of the photovoltaic power plant;

[0157] Analyzing the corresponding relationship between panel cleaning degree data and power generation efficiency in each partition of the photovoltaic power plant;

[0158] Based on the difference in power generation, the corresponding relationship obtained by analyzing the difference between the comprehensive efficiency of each sub-area of ​​the photovoltaic power plant and the comprehensive efficiency of each sub-area in the same period in history, and the difference between the overall comprehensive efficiency of the photovoltaic power plant and the overall comprehensive efficiency in the same period in history, obtain the degree of influence of fog on each sub-area;

[0159] Modify the current panel cleaning plan based on the degree of impact of fog on each zone.

[0160] In an optional implementation, the cleaning scheme modification module is specifically used to:

[0161] Generate panel cleaning suggestion information based on the degree of influence of fog on each partition; the panel cleaning suggestion information includes at least one of the following: area cleaning suggestion information, cleaning frequency suggestion information, cleaning speed suggestion information, and cleaning manpower allocation suggestion information;

[0162] The current panel cleaning plan is modified based on the panel cleaning suggestion information.

[0163] In an optional implementation, the power generation control device based on active and reactive power adjustment of photovoltaic power generation further includes a first curve generation module, which is used for the grid side to generate a planned power generation curve of active power and reactive power allocated to the photovoltaic power plant. The first curve generation module is specifically used to:

[0164] The grid side determines the load curve to be allocated to each power plant based on the characteristic production factor data of each power plant and the control production factor data of the grid side, including the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant, among which the frequency is controlled by active power and the voltage is controlled by reactive power.

[0165] In an optional implementation, the power generation control device based on active and reactive power adjustment of photovoltaic power generation further includes a second curve generation module, which is used for the photovoltaic power plant to generate a predicted power generation curve of active power and reactive power. The second curve generation module is specifically used for:

[0166] The photovoltaic power plant generates a predicted power generation curve of active power and reactive power based on equipment performance, weather data and historical power generation in the same period. The equipment performance includes the change characteristics of active power and reactive power of the inverter under the influence of voltage factors.

[0167] In an optional implementation, the power generation control device based on active and reactive power adjustment of photovoltaic power generation further includes a sending module, which is used for the photovoltaic power plant to send the power data and cost data of the abandoned light auxiliary function to the grid side before the photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve;

[0168] The power generation control module is specifically used to perform power generation control based on the safety requirements of power plant equipment and the received planned power generation curve if the photovoltaic power plant receives a control instruction from the power grid side; the control instruction is sent by the power grid side after reaching a transaction intention with the photovoltaic power plant based on the power data and the cost data.

[0169] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely schematic, in which the unit described as a separate component may or may not be physically separated, and the component prompted as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0170] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A power generation control method based on active and reactive power adjustment of photovoltaic power generation, characterized in that: include: Obtaining a planned power generation curve of active power and reactive power allocated to the photovoltaic power plant by the grid side, and obtaining a predicted power generation curve of active power and reactive power generated by the photovoltaic power plant itself; Determining whether the predicted power generation curve fits the planned power generation curve; If the predicted power generation curve cannot fit the planned power generation curve, the grid side modifies the planned power generation curve through deep learning and resends it to the photovoltaic power plant after the modification is completed; if the predicted power generation curve fits the planned power generation curve, it is determined whether the measured power generation curves of active power and reactive power of the photovoltaic power plant fit the predicted power generation curve; If the measured power generation curve cannot fit the predicted power generation curve, the panel cleaning plan of the photovoltaic power plant is modified; if the measured power generation curve fits the predicted power generation curve, the photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve; The modification of the panel cleaning scheme of the photovoltaic power plant comprises: Analyze the difference between the measured daily power generation and the historical daily power generation of the photovoltaic power plant; Analyzing the corresponding relationship between panel cleaning degree data and power generation efficiency in each partition of the photovoltaic power plant; Based on the difference in power generation, the corresponding relationship obtained by analyzing the difference between the comprehensive efficiency of each sub-area of ​​the photovoltaic power plant and the comprehensive efficiency of each sub-area in the same period in history, and the difference between the overall comprehensive efficiency of the photovoltaic power plant and the overall comprehensive efficiency in the same period in history, obtain the degree of influence of fog on each sub-area; Modify the current panel cleaning plan based on the degree of impact of fog on each zone; The modification of the current panel cleaning scheme based on the degree of influence of fog on each partition includes: Generate panel cleaning suggestion information based on the degree of influence of fog on each partition; the panel cleaning suggestion information includes at least one of the following: area cleaning suggestion information, cleaning frequency suggestion information, cleaning speed suggestion information, and cleaning manpower allocation suggestion information; The current panel cleaning plan is modified based on the panel cleaning suggestion information.

2. The method according to claim 1, characterized in that The photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve, including: Determine whether the photovoltaic power plant meets the safety requirements of power plant equipment if the photovoltaic power plant performs conversion control of active power and reactive power during power generation according to the planned power generation curve; If the safety requirement is met, the photovoltaic power plant performs power generation control based on the planned power generation curve; if the safety requirement is not met, the photovoltaic power plant performs power generation control based on the planned power generation curve through peak shaving technology.

3. The method according to claim 2, characterized in that The judging whether the photovoltaic power plant meets the safety requirements of power plant equipment of the photovoltaic power plant if the photovoltaic power plant performs conversion control of active power and reactive power in the power generation process according to the planned power generation curve includes: Determine whether the current and temperature of the equipment of the photovoltaic power plant meet the safety requirements if the photovoltaic power plant performs conversion control of active power and reactive power during power generation according to the planned power generation curve, and whether the operating voltage of the equipment of the photovoltaic power plant is normal.

4. The method according to claim 2, characterized in that: The photovoltaic power plant controls power generation based on the planned power generation curve by using peak shaving technology, including: The conduction angle of the thyristor of the photovoltaic power plant is adjusted to perform peak shaving.

5. The method according to claim 1, characterized in that Before performing power generation control, the method further includes: Analyze the change characteristics of active power and reactive power of the inverter of the photovoltaic power plant under the influence of voltage factors, and determine the inflection point information in the change characteristic curve of active power and reactive power under different voltages, wherein the inflection point information includes the value on the reactive power coordinate axis and the value on the active power coordinate axis; Perform power generation control, including: The reactive power value of the inverter is controlled to be smaller than the value of the reactive power coordinate axis in the inflection point information.

6. The method according to claim 1, characterized in that The grid side modifies the planned power generation curve through deep learning, including: The grid side deeply learns the difference between the actual daily power generation of the photovoltaic power plant and the historical daily power generation, and learns the difference between the comprehensive efficiency of the photovoltaic power plant and the comprehensive efficiency of the same period in history, combines the panel cleaning degree data of the photovoltaic power plant to identify the impact of fog, and adjusts the planned power generation curve.

7. The method according to claim 1, characterized in that The planned power generation curve of active power and reactive power allocated to the photovoltaic power plant by the grid side is generated in the following way: The grid side determines the load curve to be allocated to each power plant based on the characteristic production factor data of each power plant and the control production factor data of the grid side, including the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant, among which the frequency is controlled by active power and the voltage is controlled by reactive power.

8. The method according to claim 1, characterized in that The photovoltaic power plant generates a predicted power generation curve of active power and reactive power, including: The photovoltaic power plant generates a predicted power generation curve of active power and reactive power based on equipment performance, weather data and historical power generation in the same period. The equipment performance includes the change characteristics of active power and reactive power of the inverter under the influence of voltage factors.

9. The method according to claim 1, characterized in that: Before the photovoltaic power plant performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve, the method further includes: The photovoltaic power plant sends the power quantity data and cost data of the photovoltaic power abandonment auxiliary function to the power grid side; If the photovoltaic power plant receives a control instruction from the power grid, it performs power generation control based on the safety requirements of the power plant equipment and the received planned power generation curve; the control instruction is sent by the power grid after reaching a transaction intention with the photovoltaic power plant based on the power data and the cost data.

10. A power generation control device based on active and reactive power adjustment of photovoltaic power generation, characterized in that: include: A curve acquisition module, used to acquire the planned power generation curve of active power and reactive power allocated to the photovoltaic power plant by the grid side, and to acquire the predicted power generation curve of active power and reactive power generated by the photovoltaic power plant itself; A fitting judgment module, used to judge whether the predicted power generation curve fits the planned power generation curve; A curve modification module, for modifying the planned power generation curve by deep learning on the grid side if the predicted power generation curve cannot fit the planned power generation curve, and resending the modified curve to the photovoltaic power plant after the modification is completed; The fitting judgment module is further used to judge whether the measured power generation curve of active power and reactive power of the photovoltaic power plant fits the predicted power generation curve if the predicted power generation curve fits the planned power generation curve; A cleaning scheme modification module, used for modifying the panel cleaning scheme of the photovoltaic power plant if the measured power generation curve cannot fit the predicted power generation curve; A power generation control module, configured to control power generation of the photovoltaic power plant based on safety requirements of power plant equipment and the received planned power generation curve if the measured power generation curve fits the predicted power generation curve; The cleaning scheme modification module is specifically used for: Analyze the difference between the measured daily power generation and the historical daily power generation of the photovoltaic power plant; Analyzing the corresponding relationship between panel cleaning degree data and power generation efficiency in each partition of the photovoltaic power plant; Based on the difference in power generation, the corresponding relationship obtained by analyzing the difference between the comprehensive efficiency of each sub-area of ​​the photovoltaic power plant and the comprehensive efficiency of each sub-area in the same period in history, and the difference between the overall comprehensive efficiency of the photovoltaic power plant and the overall comprehensive efficiency in the same period in history, obtain the degree of influence of fog on each sub-area; Modify the current panel cleaning plan based on the degree of impact of fog on each zone; The cleaning scheme modification module modifies the current panel cleaning scheme based on the degree of influence of fog on each partition in the following manner: Generate panel cleaning recommendation information based on the impact of fog on each partition; The panel cleaning suggestion information includes at least one of the following: area cleaning suggestion information, cleaning frequency suggestion information, cleaning speed suggestion information, and cleaning manpower allocation suggestion information; The current panel cleaning plan is modified based on the panel cleaning suggestion information.

Images