Distributed photovoltaic grid-connected voltage stabilization method, device and equipment and storage medium

Abstract

The invention relates to the field of photovoltaic technology, and discloses a distributed photovoltaic grid-connected voltage stabilization method, device and equipment and a storage medium, and the method comprises the steps: determining the corrected power generation power based on the current power generation power data, the current environment parameters and the environment factor weight; determining predicted power generation power according to the reduction coefficient and the corrected power generation power; and determining a target grid-connected node voltage according to the predicted generated power. Through the above mode, based on the current power generation power data, each current environment parameter and the environment factor weight, the influence of various factors on the power generation power is integrated, the corrected power generation power is accurately determined, the predicted power generation power is obtained through quantification of the preset reduction coefficient, and the target grid-connected node voltage is determined through the predicted power generation power. The grid-connected node voltage is reasonably planned, it is guaranteed that the grid-connected node voltage is stabilized in a safe interval, voltage out-of-limit caused by power generation power fluctuation is avoided, and the voltage stability of the distributed photovoltaic system during grid connection is improved.

Description

Technical Field

[0001] The present application relates to the field of photovoltaic technology, and in particular to a distributed photovoltaic grid-connected voltage stabilization method, device, equipment, and storage medium. Background Art

[0002] As the global energy structure shifts towards cleaner and lower-carbon energy, distributed photovoltaic power generation systems have been widely used in distribution networks due to their flexibility, environmental friendliness, and local consumption. According to data from the International Energy Agency, global distributed photovoltaic installed capacity exceeded 400GW in 2023, and the penetration rate continued to rise. However, the intermittent and volatile nature of photovoltaic power generation poses severe challenges to the power balance, voltage stability, and power quality of the power grid. In particular, in areas with high photovoltaic penetration, problems such as power reverse transmission, voltage over-limit, and harmonic distortion are frequent. Traditional distributed photovoltaic systems typically use MPPT (Maximum Power Point Tracking) control strategies to maximize power generation efficiency, but do not fully consider the dynamic needs of the power grid.

[0003] Existing technologies maximize energy conversion efficiency by adjusting the operating voltage or current of photovoltaic arrays in real time to keep them operating at their maximum power point. The core of the MPPT algorithm lies in dynamically tracking the peak of the photovoltaic cell's power-voltage (PV) curve to overcome power losses caused by light intensity, temperature fluctuations, and partial shading. However, it only pursues maximum power output and ignores grid power balance requirements. Furthermore, its reliance on high-speed communication poses the risk of regulation lag in the event of communication failures. Therefore, improving the voltage stability of distributed photovoltaic systems when connected to the grid has become a pressing technical challenge. Summary of the Invention

[0004] The present application provides a distributed photovoltaic grid-connected voltage stabilization method, device, equipment and storage medium to improve the voltage stability of a distributed photovoltaic system when it is connected to the grid.

[0005] In a first aspect, the present application provides a distributed photovoltaic grid-connected voltage stabilization method, the method comprising:

[0006] Performing weighted synthesis of each current environmental parameter by using environmental factor weights to generate a weighted environmental parameter, and determining at least one corrected power generation based on current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameter;

[0007] Calculating a corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and obtaining a pre-configured time series weight and a preset power error parameter corresponding to each corrected power generation power difference;

[0008] Determining the preset restoration coefficient according to the terminal corrected power generation, the time series weight, the preset power error parameter, and each corrected power generation difference, wherein the terminal corrected power generation is the last corrected power generation within the preset period;

[0009] Determining the predicted power generation power according to the preset reduction coefficient and the corrected power generation power;

[0010] A target grid-connected node voltage of the distributed photovoltaic system is determined according to the predicted generated power.

[0011] In a second aspect, the present application further provides a distributed photovoltaic grid-connected voltage stabilization device, the device comprising:

[0012] a modified power generation determination module, configured to perform weighted synthesis of current environmental parameters using environmental factor weights to generate weighted environmental parameters, and determine at least one modified power generation based on current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameters;

[0013] a weight parameter acquisition module, configured to calculate a corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and to obtain a pre-configured time series weight and a preset power error parameter corresponding to each corrected power generation power difference;

[0014] a preset restoration coefficient determination module, configured to determine the preset restoration coefficient based on the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference, wherein the terminal corrected generated power is the last corrected generated power within the preset period;

[0015] A predicted power generation determination module, configured to determine the predicted power generation according to a preset reduction coefficient and the corrected power generation;

[0016] The target grid-connected node voltage determination module is used to determine the target grid-connected node voltage of the distributed photovoltaic system according to the predicted generated power.

[0017] In a third aspect, the present application also provides a computer device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the distributed photovoltaic grid-connected voltage stabilization method as described above when executing the computer program.

[0018] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to implement the above-mentioned distributed photovoltaic grid-connected voltage stabilization method.

[0019] The present application discloses a distributed photovoltaic grid-connected voltage stabilization method, apparatus, equipment and storage medium. The distributed photovoltaic grid-connected voltage stabilization method includes weighting and synthesizing each current environmental parameter by environmental factor weights to generate weighted environmental parameters, and determining at least one corrected power generation power based on the current power generation power data of the distributed photovoltaic system within a preset period and the weighted environmental parameters; calculating the corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and obtaining the pre-configured time series weights and preset power error parameters corresponding to each corrected power generation power difference; determining the preset restoration coefficient according to the terminal corrected power generation power, the time series weight, the preset power error parameter and each corrected power generation power difference, wherein the terminal corrected power generation power is the last corrected power generation power within the preset period; determining the predicted power generation power according to the preset restoration coefficient and the corrected power generation power; and determining the target grid-connected node voltage of the distributed photovoltaic system according to the predicted power generation power. Through the above method, this application is based on the current power generation data of the distributed photovoltaic system within a preset period, the current environmental parameters and the weights of environmental factors, and comprehensively considers the influence of multiple factors on the power generation, accurately determines the corrected power generation, and then quantifies the predicted power generation through the preset reduction coefficient. The target grid-connected node voltage is determined by the predicted power generation, and the grid-connected node voltage is reasonably planned to ensure its stability within a safe range, avoid voltage exceeding the limit caused by power generation fluctuations, and improve the voltage stability of the distributed photovoltaic system when it is connected to the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 This is a schematic flow chart of a distributed photovoltaic grid-connected voltage stabilization method provided by the first embodiment of the present application;

[0022] Figure 2 is a schematic flow chart of a distributed photovoltaic grid-connected voltage stabilization method provided in the second embodiment of the present application;

[0023] Figure 3 A schematic block diagram of a distributed photovoltaic grid-connected voltage stabilizing device provided in an embodiment of the present application;

[0024] Figure 4 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0027] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0029] The embodiments of the present application provide a distributed photovoltaic grid-connected voltage stabilization method, apparatus, device, and storage medium. The distributed photovoltaic grid-connected voltage stabilization method can be applied to a server. Based on the current power generation data of the distributed photovoltaic system within a preset period, various current environmental parameters, and environmental factor weights, the method integrates the impact of multiple factors on power generation, accurately determines the corrected power generation, and then quantifies the predicted power generation through a preset reduction coefficient. The target grid-connected node voltage is determined based on the predicted power generation, and the grid-connected node voltage is rationally planned to ensure that it remains stable within a safe range, avoiding voltage over-limit problems caused by power generation fluctuations, thereby improving the voltage stability of the distributed photovoltaic system when connected to the grid. The server can be a standalone server or a server cluster.

[0030] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0031] See also Figure 1 , Figure 1This is a schematic flow chart of a distributed photovoltaic grid-connected voltage stabilization method provided in the first embodiment of the present application. This distributed photovoltaic grid-connected voltage stabilization method can be applied to a server and is used to accurately determine the corrected power generation based on the current power generation data of the distributed photovoltaic system within a preset period, various current environmental parameters, and environmental factor weights, and to comprehensively consider the impact of multiple factors on the power generation. The predicted power generation is then quantified using a preset reduction coefficient. The target grid-connected node voltage is determined based on the predicted power generation, and the grid-connected node voltage is rationally planned to ensure its stability within a safe range, avoiding voltage over-limit problems caused by power generation fluctuations, thereby improving the voltage stability of the distributed photovoltaic system when connected to the grid.

[0032] like Figure 1 As shown, the distributed photovoltaic grid-connected voltage stabilization method specifically includes steps S10 to S30.

[0033] Step S10: performing weighted synthesis of the current environmental parameters using environmental factor weights to generate weighted environmental parameters, and determining at least one corrected power generation based on the current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameters;

[0034] Specifically, the weights of environmental factors can be determined by historical data or obtained through calculation based on relevant data.

[0035] In the preset period, the power monitoring equipment installed in the distributed photovoltaic system collects the current power generation data at a certain time interval (such as 15 minutes) and records it as a set of time series data sets, denoted as P = {P1, P2, ..., P n}, where n is the number of sampling points in the preset period.

[0036] The current environmental parameter data are collected synchronously, including light intensity G, ambient temperature T, humidity H, wind speed W, etc., and are also recorded in the form of time series, which are recorded as G = {G1, G2, ..., G n}、T={T1,T2,…,T n}、H={H1,H2,…,H n}、W={W1,W2,…,W n}.

[0037] The collected current power generation data and various environmental parameter data are normalized to eliminate the impact of different dimensions and dimension ranges on subsequent calculations.

[0038] Based on the normalized current power generation data and various environmental parameter data, as well as the determined environmental factor weights, a revised power generation calculation model is constructed. The model can be expressed as: Among them, P j is the jth power measurement value, ωi is the environmental factor weight, and specific data is substituted into it. The corrected power generation power of each sampling point in the preset period is calculated according to the above model to obtain at least one corrected power generation power value.

[0039] Step S20: Calculate the corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and obtain the pre-configured time series weight and preset power error parameter corresponding to each corrected power generation power difference;

[0040] In a specific embodiment, for example, the corrected power generation of four data points in the past hour (i.e., the preset period is 1 hour) is calculated with a step length of 15 minutes to generate a nearby data set S:

[0041] S={P1',P2',P3',P4',}

[0042] Then, the difference between adjacent corrected power generation powers is calculated in sequence to form a corrected power difference data set:

[0043]

[0044] The three corrected power differences are then assigned different weights α1, α2, and α3 according to the time series, ensuring that data closer to the predicted point has a higher weight. The following three weight reference values are given: α1 = 0.2, α2 = 0.30, and α3 = 0.50. Considering equipment errors and random errors, the power forecast process is subject to numerous unavoidable errors. Therefore, an error term ε is introduced, with a reference value of ε = 0.01P4', which varies dynamically with the error between the historical power forecast and the actual value.

[0045] Step S30: determining the preset restoration coefficient based on the terminal corrected power generation, the time series weight, the preset power error parameter, and each corrected power generation difference, wherein the terminal corrected power generation is the last corrected power generation within the preset period;

[0046] Specifically, when the error between the two is greater than 1%, ε is adjusted in steps of 0.001 until the error between the two is within 1%. Then, a weighted synthesis is performed to correct the power prediction value P. f ':

[0047]

[0048] Where P'4 is the terminal corrected power generation (i.e. the fourth data point), and then the corrected power prediction value is restored to the actual power prediction value. The preset restoration coefficient is Then calculate the product of the preset reduction coefficient and the terminal corrected power generation to obtain the predicted power generation.

[0049] Step S40: determining the predicted power generation power according to the preset reduction coefficient and the corrected power generation power;

[0050] Specifically, the corrected power generation in this embodiment does not meet the user's demand for actual power generation, so the "corrected power generation" needs to be restored to the "predicted power generation", that is, the corrected power generation needs to be restored to the predicted power generation through a preset restoration coefficient.

[0051] From the data records or real-time monitoring of the distributed photovoltaic system, the corrected power generation is obtained after correction processing, and the preset reduction coefficient is obtained according to the system configuration or the results of the previous calculation. The preset reduction coefficient can also be set according to historical data or experience.

[0052] Each corrected power generation value is multiplied by a preset reduction coefficient to obtain a predicted power generation value. The above calculation is performed on the corrected power generation of all sampling points to obtain a complete predicted power generation sequence.

[0053] Step S50: determining a target grid-connected node voltage of the distributed photovoltaic system according to the predicted generated power.

[0054] Specifically, in actual grid operation, it is necessary to ensure that the grid node voltage is stable within the safe range, usually meeting the real-time grid node voltage u r ∈(1±5%)u 额 Considering the strong fluctuation of nodes in photovoltaic power generation, (1±4%)u 额 is the threshold. The control steps are as follows:

[0055] First, the real-time grid-connected node voltage u r , real-time power P r , predict actual power P f Calculate and predict the grid-connected node voltage uf:

[0056]

[0057] Where δ is the current change factor, and its value can be determined by the power generation change value and the current change value. Considering that the photovoltaic system operates at the rated current in practice, δ can be I 额 , and its value can also be dynamically adjusted according to the actual operating conditions.

[0058] When u f ∈(1±4%)u 额 When the node voltage is within the controllable range, considering the economic benefits of actual photovoltaic power generation, the inverter can be adjusted to appropriately increase the power generation without exceeding the safety range to increase the power generation capacity.

[0059] when At this time, it is necessary to adjust the inverter to reduce the node voltage to a safe range.

[0060] In a specific embodiment, power monitoring equipment installed in the distributed photovoltaic system collects current power generation data periodically (e.g., every 15 minutes) within a predetermined period. This power generation data is organized into a time series dataset, and current environmental parameter data within this predetermined period is collected, including, for example, light intensity G, ambient temperature T, humidity H, wind speed W, and so on.

[0061] Normalization is performed on the collected current power generation data and various environmental parameter data. This removes the effects of different dimensions and dimensional ranges, bringing the data to a consistent dimensional level for subsequent calculations. Similarly, a similar normalization process is performed on the various environmental parameters.

[0062] Obtain historical power generation data, explore the impact of environmental factors such as light intensity, ambient temperature, humidity, and wind speed on power generation, calculate the environmental factor weights between each environmental factor and power generation, and quantify the contribution of each environmental factor to power generation at different time points.

[0063] The correction value of the power generation due to environmental factors can be obtained by fitting historical data or calculating related physical models. The corrected power generation at each sampling point within the preset period is calculated. The preset restoration coefficient is read from the pre-configured parameters of the system, and the corrected power generation at the last data collection point within the preset period is restored using the preset restoration coefficient to obtain the predicted power generation.

[0064] According to the electrical characteristics of the distributed photovoltaic system and the operation requirements of the power grid, a mapping relationship model between the predicted power generation and the grid-connected node voltage is established. The predicted power generation is compared with the rated power generation, and the target grid-connected node voltage is further determined based on the error between the two.

[0065] It should be noted that the current environmental factors, environmental factor weights, preset reduction coefficients, and other parameters in this embodiment can all be calculated according to the above-mentioned method, or directly read from the database built into the distributed photovoltaic power generation system using historical data. For example, based on the current month, the environmental factor weights or preset reduction coefficients corresponding to the same month in history can be directly obtained. Furthermore, based on a large number of samples, the average of the environmental factor weights or historical reduction coefficients for the same month in history can be calculated and used as the environmental factor weight or preset reduction coefficient for the current month.

[0066] The present embodiment discloses a distributed photovoltaic grid-connected voltage stabilization method, apparatus, equipment and storage medium. The distributed photovoltaic grid-connected voltage stabilization method includes weighted synthesis of various current environmental parameters through environmental factor weights to generate weighted environmental parameters, and determining at least one corrected power generation based on the current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameters; calculating the corrected power generation difference between two adjacent corrected power generation data within the preset period, and obtaining the pre-configured time series weights and preset power error parameters corresponding to each corrected power generation difference; determining the preset restoration coefficient based on the terminal corrected power generation, the time series weight, the preset power error parameter and each corrected power generation difference, wherein the terminal corrected power generation is the last corrected power generation within the preset period; determining the predicted power generation based on the preset restoration coefficient and the corrected power generation; and determining the target grid-connected node voltage of the distributed photovoltaic system based on the predicted power generation. Through the above method, this application is based on the current power generation data of the distributed photovoltaic system within a preset period, the current environmental parameters and the weights of environmental factors, and comprehensively considers the influence of multiple factors on the power generation, accurately determines the corrected power generation, and then quantifies the predicted power generation through the preset reduction coefficient. The target grid-connected node voltage is determined by the predicted power generation, and the grid-connected node voltage is reasonably planned to ensure its stability within a safe range, avoid voltage exceeding the limit caused by power generation fluctuations, and improve the voltage stability of the distributed photovoltaic system when it is connected to the grid.

[0067] See also Figure 2 , Figure 2 This is a schematic flow chart of a distributed photovoltaic grid-connected voltage stabilization method provided in the second embodiment of the present application. The distributed photovoltaic grid-connected voltage stabilization method can be applied to a server, and is used to perform weighted synthesis of each current environmental parameter through environmental factor weights to generate weighted environmental parameters, which fully considers the differentiated effects of different environmental factors on power generation, so that the weighted environmental parameters can better reflect the comprehensive impact of the actual environment on power generation, and determine the target grid-connected node voltage based on the accurate prediction of power generation. The impact of power generation changes on the grid voltage is predicted in advance, and the grid-connected node voltage is reasonably planned and controlled to ensure that it is stable within a safe range. It effectively avoids problems such as voltage exceeding the limit caused by power generation fluctuations, thereby improving the voltage stability of the distributed photovoltaic system when it is grid-connected.

[0068] based on Figure 1 The embodiment shown, this embodiment Figure 2 As shown, step S30 includes steps S301 to S302.

[0069] Step S301, calculating weighted predicted power based on the terminal corrected generated power, the time series weight, the preset power error parameter and each corrected generated power difference;

[0070] Step S302: Calculate the ratio of the weighted predicted power to the terminal corrected generated power, and determine the ratio as the preset restoration coefficient.

[0071] Further,

[0072] Among them, P f ' is the weighted predicted power, P n ' is the terminal corrected power generation, α i is the time series weight, S i ' is the corrected power generation difference, ε is the preset power error parameter, and n is the number of the corrected power generation difference.

[0073] This embodiment discloses a distributed photovoltaic grid-connected voltage stabilization method, which includes weighting and synthesizing each current environmental parameter through environmental factor weights to generate weighted environmental parameters, and determining at least one corrected power generation power based on the current power generation power data of the distributed photovoltaic system within a preset period and the weighted environmental parameters; calculating the corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and obtaining the pre-configured time series weights and preset power error parameters corresponding to each corrected power generation power difference; calculating the weighted predicted power based on the terminal corrected power generation power, the time series weights, the preset power error parameters and each corrected power generation power difference; calculating the ratio of the weighted predicted power to the terminal corrected power generation power, and determining the ratio as the preset reduction coefficient; determining the predicted power generation power according to the preset reduction coefficient and the corrected power generation power; and determining the target grid-connected node voltage of the distributed photovoltaic system according to the predicted power generation power. Through the above-mentioned method, the present application is based on the current power generation data of the distributed photovoltaic system within a preset period, each current environmental parameter and the weight of the environmental factor, and comprehensively considers the influence of multiple factors on the power generation, accurately determines the corrected power generation, and then quantifies the predicted power generation through the preset reduction coefficient. The target grid-connected node voltage is determined by the predicted power generation, and the grid-connected node voltage is reasonably planned to ensure that it is stable within a safe range, avoiding problems such as voltage exceeding the limit caused by power generation fluctuations, thereby improving the voltage stability of the distributed photovoltaic system when it is grid-connected. Through the above-mentioned method, the present application weights and synthesizes each current environmental parameter by the environmental factor weight to generate weighted environmental parameters, fully considering the differentiated influence of different environmental factors on power generation, so that the weighted environmental parameters can better reflect the comprehensive influence of the actual environment on power generation, and determines the target grid-connected node voltage based on the accurate predicted power generation, predicts the influence of power generation changes on the grid voltage in advance, and reasonably plans and controls the grid-connected node voltage to ensure that it is stable within a safe range. It effectively avoids problems such as voltage exceeding the limit caused by power generation fluctuations, thereby improving the voltage stability of the distributed photovoltaic system when it is grid-connected.

[0074] based on Figure 1 In the embodiment shown, in this embodiment, before step S10, the following steps are included:

[0075] Obtain historical power generation data and historical environmental parameters;

[0076] The environmental factor weight of each of the historical environmental parameters affecting the historical power generation data is determined according to the historical power generation data and the historical environmental parameters.

[0077] Specifically, for example, this embodiment uses a data acquisition layer device to continuously record the following data during the daytime (8:00-18:00) for the previous 15 days in a 15-minute cycle: light intensity G, ambient temperature, humidity, wind speed, and photovoltaic array output power to form a time series data set:

[0078] G={G1,G2…G n}

[0079] T={T1,T2…T n}

[0080] H={H1,H2…H n}

[0081] W={W1,W2…W n}

[0082] P={P1,P2…P n}

[0083] Then, the data is preprocessed and normalized to eliminate the dimension difference. The specific method is as follows: for the i-th environmental parameter X in the acquisition period, i,j (i∈{G,T,H,W,P,},j∈(1,15×40)), the following formula is used for calculation:

[0084]

[0085] Ensure that all parameters are mapped to the [0,1] interval. Normalization effectively suppresses the weight calculation deviation caused by sensor range differences. Then optimize the data processing, specifically to deal with data mutation and loss. In the case of data loss, the mean method is used for interpolation. i,m 'Calculate the missing points by the same calculation as above and below for the three data points on the left and right:

[0086]

[0087] In the case of data mutation, for the mth data in the i-th factor, if the following conditions are met:

[0088] (Where 0.4 is a given reference value, and its size can be adjusted according to the sensor accuracy. The higher the sensor accuracy, the smaller the value. There is no restriction here, and its value falls within [0.1, 0.5]) then the data is considered to be a mutation value and should be removed. Subsequently, the missing data is treated as a data loss problem.

[0089] In a specific embodiment, determining the environmental factor weight of each historical environmental parameter affecting the historical power generation data based on the historical power generation data and the historical environmental parameters includes:

[0090] Constructing a data set matrix of the historical power generation data and each of the historical environmental parameters, and calculating the environmental factor contribution of each of the historical environmental parameters to the historical power generation data through the data set matrix;

[0091] Normalizing the contribution of each environmental factor based on a preset entropy weight method to generate environmental parameter information entropy corresponding to each historical environmental parameter;

[0092] The weight of each environmental factor is determined based on the information entropy of each environmental parameter.

[0093] Furthermore, the weight of each environmental factor is determined by a preset formula and the environmental parameter information entropy, and the preset formula is:

[0094] Among them, e i is the environmental parameter information entropy, is the preset normalization coefficient, a is the preset period, b is the number of the preset periods, and p i,m is the contribution of the environmental factors, ω i is the weight of the environmental factor.

[0095] In a specific embodiment, this embodiment uses the preprocessed data to construct a data set matrix and performs the following calculations on the environmental factors G, T, H, and W:

[0096]

[0097] The contribution p i,j is the proportion of the impact of the i-th environmental factor on the j-th indicator on the power generation power; P j is the jth power measurement value.

[0098] Then the p of the i-th environmental parameter i,j Normalization is performed to obtain the improved information entropy e that reflects the degree of data dispersion. i :

[0099]

[0100] in is the normalization coefficient, so that e i Falls within [0, 1]; information entropy e i Satisfy e i The larger it is, the more uniform the data is, and the less information the indicator provides; i The smaller it is, the more discrete the data is and the greater the amount of information is. i,m Used to measure the data point p i,m The amount of information about power, p i,mThe smaller it is, the more discrete it is and the greater the amount of information; i,m lnp i,m That is the weighted information amount.

[0101] Then based on the normalized information entropy e i Generate environmental factor weight ω i :

[0102]

[0103] ω i That is, the weight of the i-th environmental factor in the collection period.

[0104] Then, according to the weight of each environmental factor, a linear weighted synthesis is performed to generate a power correction value P considering environmental factors. j ', the calculation formula is as follows:

[0105]

[0106] Among them, P j is the jth power measurement value.

[0107] Based on any of the above embodiments, in this embodiment, step S50 includes:

[0108] Obtain rated grid-connected node voltage, real-time grid-connected node voltage, real-time generated power and current change factor;

[0109] Calculating a predicted grid-connected node voltage based on the current change factor, the real-time grid-connected node voltage, the real-time generated power, and the predicted generated power;

[0110] In a case where a voltage error value between the predicted grid-connected node voltage and the rated grid-connected node voltage is less than or equal to a preset voltage error parameter, determining the predicted grid-connected node voltage as the target grid-connected node voltage;

[0111] When the voltage error value between the predicted grid-connected node voltage and the rated grid-connected node voltage is greater than the preset voltage error parameter, the target grid-connected node voltage is determined according to the rated grid-connected node voltage and the preset voltage error parameter.

[0112] See also Figure 3 , Figure 3 The embodiment of the present application provides a schematic block diagram of a distributed photovoltaic grid-connected voltage stabilization device, which is used to perform the aforementioned distributed photovoltaic grid-connected voltage stabilization method. The distributed photovoltaic grid-connected voltage stabilization device can be configured on a server.

[0113] like Figure 3 As shown, the distributed photovoltaic grid-connected voltage stabilizing device 400 includes:

[0114] A modified power generation determination module 410 is configured to perform a weighted synthesis of the current environmental parameters using environmental factor weights to generate weighted environmental parameters, and determine at least one modified power generation based on the current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameters;

[0115] The weight parameter acquisition module 420 is used to calculate the difference between the two adjacent corrected power generation powers within the preset period, and obtain the pre-configured time series weight and preset power error parameter corresponding to each corrected power generation difference;

[0116] a preset restoration coefficient determination module 430, configured to determine the preset restoration coefficient based on the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference, wherein the terminal corrected generated power is the last corrected generated power within the preset period;

[0117] A predicted power generation determination module 440 is configured to determine the predicted power generation according to a preset reduction coefficient and the corrected power generation;

[0118] The target grid-connected node voltage determination module 450 is configured to determine the target grid-connected node voltage of the distributed photovoltaic system according to the predicted generated power.

[0119] Furthermore, the preset restoration coefficient determination module 430 includes:

[0120] A weighted predicted power calculation module, configured to calculate the weighted predicted power based on the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference;

[0121] The preset restoration coefficient determination module is used to calculate the ratio of the weighted predicted power to the terminal corrected generated power, and determine the ratio as the preset restoration coefficient.

[0122] Furthermore, the distributed photovoltaic grid-connected voltage stabilizing device 400 includes:

[0123] A historical data acquisition module is used to obtain historical power generation data and historical environmental parameters;

[0124] The environmental factor weight determination module is used to determine the environmental factor weight of each historical environmental parameter affecting the historical power generation data based on the historical power generation data and the historical environmental parameters.

[0125] Furthermore, the environmental factor weight determination module includes:

[0126] an environmental factor contribution calculation unit, configured to construct a data set matrix of the historical power generation data and each of the historical environmental parameters, and calculate the environmental factor contribution of each of the historical environmental parameters to the historical power generation data using the data set matrix;

[0127] An environmental parameter information entropy determination unit is configured to normalize the contribution of each environmental factor based on a preset entropy weight method to generate environmental parameter information entropy corresponding to each historical environmental parameter;

[0128] The environmental factor weight determination unit is used to determine the weight of each environmental factor based on the information entropy of each environmental parameter.

[0129] Furthermore, the target grid-connected node voltage determination module 450 includes:

[0130] Rated data acquisition unit, used to obtain rated grid-connected node voltage, real-time grid-connected node voltage, real-time generated power and current change factor;

[0131] a predicted grid-connected node voltage calculation unit, configured to calculate the predicted grid-connected node voltage based on the current variation factor, the real-time grid-connected node voltage, the real-time generated power, and the predicted generated power;

[0132] a grid-connected node voltage determining unit, configured to determine the predicted grid-connected node voltage as the target grid-connected node voltage if a voltage error between the predicted grid-connected node voltage and the rated grid-connected node voltage is less than or equal to a preset voltage error parameter;

[0133] The grid-connected node voltage adjustment unit is used to determine the target grid-connected node voltage according to the rated grid-connected node voltage and the preset voltage error parameter when the voltage error value between the predicted grid-connected node voltage and the rated grid-connected node voltage is greater than the preset voltage error parameter.

[0134] It should be noted that those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0135] The above-mentioned device can be realized in the form of a computer program. The computer program can be used in Figure 4 Runs on the computer equipment shown.

[0136] See also Figure 4 , Figure 4 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0137] See Figure 4 The computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0138] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can cause the processor to execute any distributed photovoltaic grid-connected voltage stabilization method.

[0139] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0140] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any distributed photovoltaic grid-connected voltage stabilization method.

[0141] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0142] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0143] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0144] Performing weighted synthesis of each current environmental parameter by using environmental factor weights to generate a weighted environmental parameter, and determining at least one corrected power generation based on current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameter;

[0145] Calculating a corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and obtaining a pre-configured time series weight and a preset power error parameter corresponding to each corrected power generation power difference;

[0146] Determining the preset restoration coefficient according to the terminal corrected power generation, the time series weight, the preset power error parameter, and each corrected power generation difference, wherein the terminal corrected power generation is the last corrected power generation within the preset period;

[0147] Determining the predicted power generation power according to the preset reduction coefficient and the corrected power generation power;

[0148] A target grid-connected node voltage of the distributed photovoltaic system is determined according to the predicted generated power.

[0149] In one embodiment, the preset restoration coefficient is determined based on the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference, to achieve:

[0150] Calculating a weighted predicted power based on the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference;

[0151] The ratio of the weighted predicted power to the terminal corrected generated power is calculated, and the ratio is determined as the preset reduction coefficient.

[0152] In one embodiment, each current environmental parameter is weighted and synthesized by the environmental factor weight to generate a weighted environmental parameter, and before determining at least one corrected power generation based on the current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameter, it is used to achieve:

[0153] Obtain historical power generation data and historical environmental parameters;

[0154] The environmental factor weight of each of the historical environmental parameters affecting the historical power generation data is determined according to the historical power generation data and the historical environmental parameters.

[0155] In one embodiment, based on the historical power generation data and the historical environmental parameters, the weight of the environmental factor affecting the historical power generation data by each of the historical environmental parameters is determined, so as to achieve:

[0156] Constructing a data set matrix of the historical power generation data and each of the historical environmental parameters, and calculating the environmental factor contribution of each of the historical environmental parameters to the historical power generation data through the data set matrix;

[0157] Normalizing the contribution of each environmental factor based on a preset entropy weight method to generate environmental parameter information entropy corresponding to each historical environmental parameter;

[0158] The weight of each environmental factor is determined based on the information entropy of each environmental parameter.

[0159] In one embodiment, a target grid-connected node voltage of the distributed photovoltaic system is determined based on the predicted generated power to achieve:

[0160] Obtain rated grid-connected node voltage, real-time grid-connected node voltage, real-time generated power and current change factor;

[0161] Calculating a predicted grid-connected node voltage based on the current change factor, the real-time grid-connected node voltage, the real-time generated power, and the predicted generated power;

[0162] In a case where a voltage error value between the predicted grid-connected node voltage and the rated grid-connected node voltage is less than or equal to a preset voltage error parameter, determining the predicted grid-connected node voltage as the target grid-connected node voltage;

[0163] When the voltage error value between the predicted grid-connected node voltage and the rated grid-connected node voltage is greater than the preset voltage error parameter, the target grid-connected node voltage is determined according to the rated grid-connected node voltage and the preset voltage error parameter.

[0164] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. The processor executes the program instructions to implement any distributed photovoltaic grid-connected voltage stabilization method provided in the embodiment of the present application.

[0165] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0166] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A distributed photovoltaic grid-connected voltage stabilization method, characterized in that: include: Performing weighted synthesis of each current environmental parameter by using environmental factor weights to generate a weighted environmental parameter, and determining at least one corrected power generation based on current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameter; Calculating a corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and obtaining a pre-configured time series weight and a preset power error parameter corresponding to each corrected power generation power difference; Determining the preset restoration coefficient according to the terminal corrected power generation, the time series weight, the preset power error parameter, and each corrected power generation difference, wherein the terminal corrected power generation is the last corrected power generation within the preset period; Determining the predicted power generation power according to the preset reduction coefficient and the corrected power generation power; A target grid-connected node voltage of the distributed photovoltaic system is determined according to the predicted generated power.

2. The distributed photovoltaic grid-connected voltage stabilization method according to claim 1, characterized in that: The step of determining the preset restoration coefficient according to the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference includes: Calculating a weighted predicted power based on the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference; The ratio of the weighted predicted power to the terminal corrected generated power is calculated, and the ratio is determined as the preset reduction coefficient.

3. The distributed photovoltaic grid-connected voltage stabilization method according to claim 2, characterized in that: The weighted predicted power is calculated based on the terminal corrected generated power, the time series weight, the preset power error parameter and each corrected generated power difference. include: Among them, P f ' is the weighted predicted power, P n ' is the terminal corrected power generation, α i is the time series weight, S i ' is the corrected power generation difference, ε is the preset power error parameter, and n is the number of the corrected power generation difference.

4. The distributed photovoltaic grid-connected voltage stabilization method according to claim 1, characterized in that: The step of weighting and synthesizing the current environmental parameters by the environmental factor weights to generate weighted environmental parameters, and determining at least one corrected power generation based on the current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameters, includes: Obtain historical power generation data and historical environmental parameters; The environmental factor weight of each of the historical environmental parameters affecting the historical power generation data is determined according to the historical power generation data and the historical environmental parameters.

5. The distributed photovoltaic grid-connected voltage stabilization method according to claim 4, characterized in that: The determining, based on the historical power generation data and the historical environmental parameters, the environmental factor weight of each historical environmental parameter affecting the historical power generation data includes: Constructing a data set matrix of the historical power generation data and each of the historical environmental parameters, and calculating the environmental factor contribution of each of the historical environmental parameters to the historical power generation data through the data set matrix; Normalizing the contribution of each environmental factor based on a preset entropy weight method to generate environmental parameter information entropy corresponding to each historical environmental parameter; The weight of each environmental factor is determined based on the information entropy of each environmental parameter.

6. The distributed photovoltaic grid-connected voltage stabilization method according to claim 5, characterized in that: The determining of the weight of each environmental factor based on the information entropy of each environmental parameter includes: The weight of each environmental factor is determined by a preset formula and the environmental parameter information entropy, and the preset formula is: Among them, e i is the environmental parameter information entropy, is the preset normalization coefficient, a is the preset period, b is the number of the preset periods, and p i,m is the contribution of the environmental factors, ω i is the weight of the environmental factor.

7. The distributed photovoltaic grid-connected voltage stabilization method according to any one of claims 1 to 6, characterized in that: Determining a target grid-connected node voltage of the distributed photovoltaic system according to the predicted generated power includes: Obtain rated grid-connected node voltage, real-time grid-connected node voltage, real-time generated power and current change factor; Calculating a predicted grid-connected node voltage based on the current change factor, the real-time grid-connected node voltage, the real-time generated power, and the predicted generated power; In a case where a voltage error value between the predicted grid-connected node voltage and the rated grid-connected node voltage is less than or equal to a preset voltage error parameter, determining the predicted grid-connected node voltage as the target grid-connected node voltage; When the voltage error value between the predicted grid-connected node voltage and the rated grid-connected node voltage is greater than the preset voltage error parameter, the target grid-connected node voltage is determined according to the rated grid-connected node voltage and the preset voltage error parameter.

8. A distributed photovoltaic grid-connected voltage stabilizing device, characterized in that: include: a modified power generation determination module, configured to perform weighted synthesis of current environmental parameters using environmental factor weights to generate weighted environmental parameters, and determine at least one modified power generation based on current power generation data of the distributed photovoltaic system within a preset period and the weighted environmental parameters; a weight parameter acquisition module, configured to calculate a corrected power generation power difference between two adjacent corrected power generation powers within the preset period, and to obtain a pre-configured time series weight and a preset power error parameter corresponding to each corrected power generation power difference; a preset restoration coefficient determination module, configured to determine the preset restoration coefficient based on the terminal corrected generated power, the time series weight, the preset power error parameter, and each corrected generated power difference, wherein the terminal corrected generated power is the last corrected generated power within the preset period; A predicted power generation determination module, configured to determine the predicted power generation according to a preset reduction coefficient and the corrected power generation; The target grid-connected node voltage determination module is used to determine the target grid-connected node voltage of the distributed photovoltaic system according to the predicted generated power.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the distributed photovoltaic grid-connected voltage stabilization method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the distributed photovoltaic grid-connected voltage stabilization method according to any one of claims 1 to 7.

Images