A big data-based distributed photovoltaic output scheduling control method and system

Abstract

The application relates to the technical field of photovoltaic output control, and discloses a distributed photovoltaic output scheduling control method and system based on big data, which comprises the following steps: according to meteorological remote sensing data and ground monitoring data, the moving path of sand and dust is predicted, and the solar radiation attenuation is analyzed to obtain sand and dust moving path and radiation attenuation data; according to the photovoltaic parameters of the distributed photovoltaic, the sand and dust moving path and the radiation attenuation data, the photovoltaic output curve is obtained; according to the real-time data of the load of a mining area and the photovoltaic output curve, the power load data is obtained; according to the load prediction data of the mining area and the photovoltaic output curve, the output load matching degree is calculated to determine whether the photovoltaic output scheduling control is triggered; and according to the power deviation of the power grid and the frequency change curve of the power grid, the output scheduling strategy is generated. The application realizes the efficient management of the photovoltaic power generation system under the sand and dust weather and the stable operation of the power grid through the dynamic matching of photovoltaic power generation and load based on big data and multi-source data fusion.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic output control, and in particular to a distributed photovoltaic output dispatching control method and system based on big data. Background Art

[0002] When constructing photovoltaic power plants in the Gobi Desert, sandstorms inevitably impact power generation efficiency. During sandstorms, the concentration of suspended matter in the atmosphere increases significantly. These particles selectively attenuate the solar radiation spectrum, absorbing and scattering radiation in different bands to varying degrees, significantly reducing the effective radiation received by photovoltaic modules. This attenuation is closely related to the particle size, composition, and concentration of the dust particles. However, existing models struggle to accurately quantify this complex attenuation process, especially as dust cloud concentration and distribution dynamically change during migration, further complicating prediction.

[0003] Furthermore, when mining operations halt due to sandstorms, energy-intensive loads drop dramatically. This sudden change in load can significantly disrupt the grid frequency. Due to the intermittent and fluctuating nature of photovoltaic power generation, the simultaneous decrease in power output and sudden load drop during sandstorms further unbalances the grid frequency. Furthermore, the movement of dust clouds is influenced by a variety of meteorological factors, limiting the accuracy of forecasts. Therefore, dynamically matching photovoltaic power generation with load under these unique climatic conditions has become a key technical challenge in the operation of Gobi photovoltaic power plants. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a distributed photovoltaic output scheduling control method and system based on big data, which can solve the problems of inaccurate photovoltaic output prediction, sudden load drop and grid frequency fluctuation in sandstorm weather, realize dynamic matching of photovoltaic power generation and load, and ensure stable operation of the power grid.

[0005] In a first aspect, the present invention provides a distributed photovoltaic output dispatch control method based on big data, the method comprising:

[0006] Based on meteorological remote sensing data and ground monitoring data, the movement path of sand and dust is predicted, and the attenuation of solar radiation is analyzed to obtain the movement path and radiation attenuation data of sand and dust;

[0007] Predicting photovoltaic output changes based on the photovoltaic parameters of the distributed photovoltaic system, the dust movement path, and the radiation attenuation data to obtain a photovoltaic output curve;

[0008] Analyze the disturbance of the grid frequency caused by a sudden drop in load based on the real-time data of the mining area load and the photovoltaic output curve to obtain power load data, wherein the power load data includes the mining area load forecast data, the grid power deviation and the grid frequency change curve;

[0009] Calculating the output-load matching degree based on the mine area load forecast data and the photovoltaic output curve, and determining whether to trigger photovoltaic output dispatch control based on the output-load matching degree;

[0010] In response to triggering photovoltaic output dispatch control, an output dispatch strategy is generated according to the grid power deviation and the grid frequency change curve to dispatch and control the output of distributed photovoltaics.

[0011] Furthermore, the step of predicting the movement path of dust and analyzing solar radiation attenuation based on meteorological remote sensing data and ground monitoring data to obtain the dust movement path and radiation attenuation data includes:

[0012] Inputting meteorological remote sensing data into a preset boundary extraction model to obtain dust boundary feature data, wherein the boundary extraction model is constructed based on a convolutional neural network;

[0013] The dust movement path is calculated using a particle swarm optimization algorithm based on wind direction and speed data, ambient temperature data, dust concentration monitoring data, and the dust boundary feature data.

[0014] Furthermore, the step of predicting the movement path of dust and analyzing solar radiation attenuation based on meteorological remote sensing data and ground monitoring data to obtain the dust movement path and radiation attenuation data also includes:

[0015] Calculating the median particle size of sand and dust based on solar radiation monitoring data, and obtaining particle size distribution parameters based on the median particle size;

[0016] Determine the extinction coefficient of the dust according to the particle size distribution parameters, and calculate the spatial distribution of the dust diffusion range using the Kriging interpolation method based on the dust concentration monitoring data and the dust movement path to obtain dust distribution data;

[0017] Calculating the optical thickness according to the solar radiation wavelength, the dust distribution data and the extinction coefficient;

[0018] The optical thickness, the solar radiation wavelength and the particle size distribution parameters are input into a preset radiation attenuation model to obtain a radiation attenuation coefficient. The radiation attenuation model is constructed based on a support vector regression model.

[0019] Furthermore, the step of predicting photovoltaic output changes based on the photovoltaic parameters of the distributed photovoltaic system, the dust movement path, and the radiation attenuation data to obtain a photovoltaic output curve includes:

[0020] Calculating the dust radiation transmittance according to the optical thickness and the solar zenith angle;

[0021] Correcting the original solar radiation intensity according to the radiation attenuation coefficient to obtain the solar radiation intensity;

[0022] According to the difference between the photovoltaic module temperature and the standard module temperature, the standard conversion efficiency is corrected to obtain the photovoltaic module conversion efficiency;

[0023] A photovoltaic output curve is obtained according to the solar radiation intensity, the photovoltaic module conversion efficiency, the photovoltaic module area and the dust radiation transmittance.

[0024] Furthermore, the step of analyzing the disturbance of the grid frequency caused by the sudden drop in load based on the real-time data of the mining area load and the photovoltaic output curve to obtain the power load data includes:

[0025] Inputting the real-time load data of the mining area and the photovoltaic output curve into a preset load forecasting model to obtain the load drop amplitude, wherein the load forecasting model is constructed based on a long short-term memory neural network;

[0026] Calculating the mine area load forecast data based on the mine area load real-time data and the load drop amplitude;

[0027] Calculating a power grid deviation based on the mining area load forecast data and the photovoltaic output curve;

[0028] The grid power deviation is input into a frequency dynamic equation to obtain a grid frequency variation curve.

[0029] Furthermore, the step of calculating the output load matching degree based on the mine area load forecast data and the photovoltaic output curve, and determining whether to trigger photovoltaic output dispatch control based on the output load matching degree includes:

[0030] Calculating the covariance between the mine area load forecast data and the photovoltaic output curve, and using the covariance as the output load matching degree;

[0031] It is determined whether the output load matching degree is less than a matching degree threshold, and if so, photovoltaic output dispatch control is triggered.

[0032] Furthermore, the step of generating an output dispatching strategy based on the grid power deviation and the grid frequency change curve and dispatching and controlling the output of distributed photovoltaic power includes:

[0033] Calculating the grid frequency deviation according to the grid frequency variation curve, and calculating the initial power adjustment amount using proportional-integral control according to the grid frequency deviation;

[0034] Calculating power deviation compensation according to the power grid power deviation;

[0035] Correcting the initial power adjustment amount according to the power deviation compensation to obtain a power adjustment amount;

[0036] According to the power adjustment amount, a distributed photovoltaic output dispatching strategy is generated through distributed photovoltaic multi-machine coordination, wherein the multi-machine coordination includes equal distribution coordination and priority coordination.

[0037] Furthermore, the initial power adjustment amount is expressed by the following formula:

[0038]

[0039] Where, Indicates the initial power adjustment amount, represents the proportional gain coefficient, represents the integral gain coefficient, represents the grid frequency deviation, and t represents time;

[0040] The power deviation compensation is expressed by the following formula:

[0041]

[0042] Where, Indicates power deviation compensation, Indicates the grid power deviation, Represents the photovoltaic regulation efficiency coefficient;

[0043] The power adjustment amount is expressed by the following formula:

[0044]

[0045] Where, Indicates the power adjustment amount, Indicates the maximum adjustable capacity of photovoltaic output.

[0046] Furthermore, the step of generating a distributed photovoltaic output dispatching strategy based on the power adjustment amount through multi-machine coordination of distributed photovoltaics includes:

[0047] When equal distribution coordination is adopted, the power adjustment amount is distributed to each distributed photovoltaic according to the capacity ratio of the distributed photovoltaic;

[0048] When priority coordination is adopted, the priority of distributed photovoltaics is determined based on the distance between the distributed photovoltaics and the load center of the mining area or the photovoltaic response speed;

[0049] According to the priority, a photovoltaic unit to be regulated is selected from the distributed photovoltaic units, and the power adjustment amount is allocated to the photovoltaic unit to be regulated.

[0050] In a second aspect, the present application provides a distributed photovoltaic output scheduling control system based on big data, which comprises:

[0051] a data analysis module configured to predict a moving path of sand and dust and analyze solar radiation attenuation based on meteorological remote sensing data and ground monitoring data, and obtain sand and dust moving path and radiation attenuation data;

[0052] an output prediction module configured to predict photovoltaic output variation based on photovoltaic parameters of the distributed photovoltaic, the sand and dust moving path and the radiation attenuation data, and obtain a photovoltaic output curve;

[0053] a disturbance analysis module configured to analyze disturbance of load sudden drop on power grid frequency based on real-time data of mine area load and the photovoltaic output curve, and obtain power load data, wherein the power load data comprises mine area load prediction data, power grid power deviation and power grid frequency variation curve;

[0054] a scheduling trigger module configured to calculate output load matching degree based on the mine area load prediction data and the photovoltaic output curve, and determine whether to trigger photovoltaic output scheduling control based on the output load matching degree;

[0055] a scheduling control module configured to generate an output scheduling strategy based on the power grid power deviation and the power grid frequency variation curve in response to triggering photovoltaic output scheduling control, and perform scheduling control on output of the distributed photovoltaic.

[0056] The present application provides a distributed photovoltaic output scheduling control method and system based on big data. The present application predicts the sand and dust path through multi-data fusion, and models the solar radiation attenuation by combining the physical optical model and the neural network model, thereby effectively improving the accuracy of photovoltaic output prediction. The present application analyzes the power grid frequency disturbance caused by load sudden drop, thereby improving the accuracy of mine area load and power grid frequency prediction. The present application performs scheduling on photovoltaic output by matching degree of mine area load and photovoltaic output, thereby realizing dynamic matching of photovoltaic power generation and load. The present application realizes efficient management of photovoltaic power generation system under sand and dust weather and stable operation of power grid through distributed photovoltaic output control and dynamic scheduling optimization based on big data and multi-source data fusion. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 is a flowchart of the distributed photovoltaic output scheduling control method in the embodiment of the present application;

[0058] Figure 2 is a structural schematic diagram of the distributed photovoltaic output scheduling control system in the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0060] Referring to Figure 1 The first embodiment of the present application provides a distributed photovoltaic output scheduling control method based on big data, which comprises steps S10-S50.

[0061] In step S10, the moving path of the sand and dust is predicted according to meteorological remote sensing data and ground monitoring data, and the attenuation of solar radiation is analyzed to obtain the moving path of the sand and dust and the radiation attenuation data.

[0062] In step S20, the photovoltaic output change is predicted according to the photovoltaic parameters of the distributed photovoltaic, the moving path of the sand and dust and the radiation attenuation data to obtain a photovoltaic output curve.

[0063] In step S30, the disturbance of load sudden drop on the power grid frequency is analyzed according to the real-time data of the mine area load and the photovoltaic output curve to obtain power load data, which comprises mine area load prediction data, power grid power deviation and power grid frequency change curve.

[0064] In step S40, the output load matching degree is calculated according to the mine area load prediction data and the photovoltaic output curve, and it is judged whether the photovoltaic output scheduling control is triggered according to the output load matching degree.

[0065] In step S50, in response to triggering the photovoltaic output scheduling control, the output scheduling strategy is generated according to the power grid power deviation and the power grid frequency change curve to schedule and control the output of the distributed photovoltaic.

[0066] The present application provides a photovoltaic output scheduling control method for the influence of sand and dust weather on the power generation efficiency of the distributed photovoltaic power station in the Gobi area. Since photovoltaic is directly related to solar radiation intensity, the relationship between sand and dust weather and solar radiation is analyzed first. In the present embodiment, the analysis includes two parts, namely the prediction of the moving path of the sand and dust and the attenuation influence of the sand and dust on the solar radiation. The prediction step of the moving path of the sand and dust comprises:

[0067] The meteorological remote sensing data is input into a preset boundary extraction model to obtain sand and dust boundary feature data, and the boundary extraction model is constructed based on a convolutional neural network.

[0068] The dust movement path is calculated using a particle swarm optimization algorithm based on wind direction and speed data, ambient temperature data, dust concentration monitoring data, and the dust boundary feature data.

[0069] In this embodiment, meteorological remote sensing images are first acquired from meteorological satellites. Histogram equalization is used to enhance the contrast of these images. A convolutional neural network is used to pre-build a boundary extraction model. The equalized meteorological remote sensing data is then input into the boundary extraction model to generate a binary dust mask. Dust boundary feature data is then obtained from the binary dust mask. This dust boundary feature data includes, for example, the area of ​​the dust cluster and the length of the boundary line. Based on this dust boundary feature data and combined with wind direction and speed data and ambient temperature data collected by meteorological sensors, a particle swarm optimization algorithm is used to calculate the dust velocity vector, thereby determining the dust movement path. Each particle represents a dust cluster with attributes including position, velocity, and concentration. The particle swarm optimization algorithm (PSO) is used to calculate the dust velocity vector, with the optimization objective of minimizing the Euclidean distance between the predicted path and the measured data. During PSO initialization, the initial concentration weight of the particle swarm is adjusted based on ambient temperature data, for example, by adding 20% ​​to the particle density in high-temperature areas. The surface wind speed is used as the initial value for the particle horizontal velocity, and the position is initialized based on the binary dust mask. During the PSO velocity calculation process, wind direction data constrains the particle swarm's movement direction. Furthermore, vertical wind profile data can be used to constrain the particle swarm's vertical velocity component. The particle positions and velocities are iteratively optimized to output the optimal path set for the particle swarm. The specific calculation steps can be referenced in the conventional particle swarm algorithm's iterative calculation steps and will not be repeated here.

[0070] Based on the dust movement path, the analysis steps of the dust's attenuation of solar radiation include:

[0071] Calculating the median particle size of sand and dust based on solar radiation monitoring data, and obtaining particle size distribution parameters based on the median particle size;

[0072] Determine the extinction coefficient of the dust according to the particle size distribution parameters, and calculate the spatial distribution of the dust diffusion range using the Kriging interpolation method based on the dust concentration monitoring data and the dust movement path to obtain dust distribution data;

[0073] Calculating the optical thickness according to the solar radiation wavelength, the dust distribution data and the extinction coefficient;

[0074] The optical thickness, the solar radiation wavelength and the particle size distribution parameters are input into a preset radiation attenuation model to obtain a radiation attenuation coefficient. The radiation attenuation model is constructed based on a support vector regression model.

[0075] In the embodiment, for the current sand weather, the solar radiance attenuation at different wavelengths is directly measured by using a solar photometer through a multi-channel filter, the optical thickness of aerosol corresponding to different wave bands can be directly obtained, the optical thicknesses of two wavelengths are selected, and then the Angstrom index a is calculated. Preferably, since the visible light of 500 nm is sensitive to the scattering characteristics of sand dust, the near-infrared light of 1020 nm has strong penetration, and can represent the extinction dominated by coarse particles, therefore, the optical thicknesses of the two wavelengths are used to calculate the index a:

[0076]

[0077] In the formula, and respectively represent the optical thicknesses corresponding to the wavelengths of 500 nm and 1020 nm. and respectively represent the optical thicknesses corresponding to the wavelengths of 500 nm and 1020 nm.

[0078] An empirical formula based on the Angstrom index and the median particle size is established in advance:

[0079]

[0080] In the formula, a, b and c are coefficients, a represents the Angstrom index, and r med represents the median particle size.

[0081] The calculated index a is substituted into the empirical formula, so as to estimate the median particle size r med Since the particle size of sand dust is logarithmic normal distribution, the median particle size is input into a logarithmic normal distribution function n(r), so as to obtain the particle size distribution parameter r:

[0082]

[0083] In the formula, and represent the geometric standard deviation, and the value is a preset fixed value.

[0084] According to the moving path of sand dust and the monitoring data of sand dust concentration, the spatial distribution of the diffusion range of the sand dust group is calculated by using the Kriging interpolation method, so as to obtain the sand dust distribution data, that is, the concentration distribution data. Further, in the Kriging interpolation, the wind direction and wind speed can be used as covariants to correct the spatial distribution of the concentration field.

[0085] The sand dust distribution data and the moving path of sand dust are aligned in coordinates, so as to ensure that the concentration value of each grid point corresponds to its movement direction, and then the optical thickness is calculated according to the sand dust concentration of each grid point, and the formula is represented as:

[0086]

[0087] In the formula, and represent the optical thickness, represents the dust concentration at the i-th grid point, represents the vertical thickness of the dust layer at the ith grid point, which can be estimated from the wind profile data in the meteorological forecast data. represents the extinction coefficient of the i-th grid point at the radiation wavelength λ.

[0088] Since the extinction coefficient is related to the particle size and radiation wavelength, the extinction coefficient can be calculated based on the particle size and corresponding wavelength obtained in the above steps through Mie theory, also known as Mie scattering theory. , and thus the optical thickness is obtained.

[0089] Based on optical principles, it can be known that the optical thickness, radiation wavelength and particle size distribution have a nonlinear relationship with the attenuation of solar radiation. Therefore, in this embodiment, the vector regression method (SVR) is used to perform regression analysis on the relevant historical data to construct a radiation attenuation model. The optical thickness, radiation wavelength and particle size distribution calculated above are then input into the radiation attenuation model to output the radiation attenuation coefficient corresponding to different radiation wavelengths.

[0090] After obtaining the dust's movement path and the data on its effect on solar radiation attenuation, we analyze the changes in photovoltaic output based on this data and relevant photovoltaic parameters. The specific steps include:

[0091] Calculating the dust radiation transmittance according to the optical thickness and the solar zenith angle;

[0092] Correcting the original solar radiation intensity according to the radiation attenuation coefficient to obtain the solar radiation intensity;

[0093] According to the difference between the photovoltaic module temperature and the standard module temperature, the standard conversion efficiency is corrected to obtain the photovoltaic module conversion efficiency;

[0094] A photovoltaic output curve is obtained according to the solar radiation intensity, the photovoltaic module conversion efficiency, the photovoltaic module area and the dust radiation transmittance.

[0095] In this embodiment, in the conventional formula for photovoltaic output, photovoltaic output is equal to the product of solar radiation intensity, photovoltaic module area, and photovoltaic module conversion efficiency, that is:

[0096]

[0097] Where G represents the solar radiation intensity, η represents the conversion efficiency of the photovoltaic module, and A represents the area of ​​the photovoltaic module.

[0098] Since the attenuation of solar radiation caused by sand and dust will affect the accuracy of the parameters related to solar radiation in the photovoltaic output formula, in order to improve the calculation accuracy of photovoltaic output, the photovoltaic output formula needs to be corrected based on the above-calculated radiation attenuation data.

[0099] First, according to the optical thickness and solar zenith angle, based on the optical principle, the radiation transmittance T is calculated:

[0100]

[0101] Where, represents the optical depth, and θ represents the solar zenith angle, which can be calculated from the geographical location and time.

[0102] Then, according to the difference between the surface temperature of the photovoltaic module and the standard module temperature under standard test conditions, the conversion efficiency of the photovoltaic module under standard test conditions is corrected to obtain the photovoltaic module conversion efficiency:

[0103]

[0104] Where, It represents the conversion efficiency under standard test conditions, β represents the temperature coefficient, S PV Indicates the temperature of the photovoltaic module, S STC Indicates standard component temperature.

[0105] In addition, dust can also attenuate the intensity of solar radiation. Therefore, the original intensity of solar radiation needs to be corrected based on the radiation attenuation coefficient. Specifically, the solar radiation is decomposed into multiple bands using a spectrometer to obtain the original intensity of radiation in each band. The original intensity of solar radiation is then corrected based on the attenuation coefficient of each band output by the attenuation model to obtain the attenuated radiation intensity:

[0106]

[0107] Where, represents the radiation attenuation coefficient output by the attenuation model, G(λ) represents the original intensity of solar radiation at wavelength λ, and G eff (λ) represents the attenuated solar radiation intensity.

[0108] Since the response efficiency of photovoltaic modules to different wavelengths is different, it is necessary to weight the effective radiation intensity of each band to obtain the total effective radiation G eff :

[0109]

[0110] Where S(λ) represents the spectral response rate of the photovoltaic module.

[0111] Then substitute the above correction value into the original photovoltaic output formula to obtain the corrected photovoltaic output P PV :

[0112]

[0113] The photovoltaic output curve can be obtained according to the above-mentioned corrected photovoltaic output.

[0114] In another preferred embodiment, the present invention further provides a method for correcting the original photovoltaic output, the specific steps comprising:

[0115] Inputting solar radiation intensity, photovoltaic module temperature, optical thickness and solar zenith angle into a preset output correction model to obtain a dynamic correction factor, wherein the output correction model is constructed based on a recursive neural network;

[0116] The original photovoltaic output is corrected according to the dynamic correction factor to obtain a photovoltaic output curve.

[0117] In this embodiment, the theoretical formula for photovoltaic output assumes ideal conditions (steady-state irradiance and no environmental changes), but in reality, dynamic interference exists, such as dust diffusion speed and transient cloud cover. Therefore, a recursive neural network model is used to model the complex relationship between solar radiation intensity, photovoltaic module temperature, optical depth, and solar zenith angle, and photovoltaic output. This allows for dynamic correction of solar radiation attenuation to compensate for the static assumptions of the theoretical model. Specifically, the recursive neural network model is fed with actual monitored time series data of solar radiation intensity, photovoltaic module temperature, optical depth, and solar zenith angle to predict a dynamic correction factor. This dynamic correction factor is then multiplied by the photovoltaic output to correct the photovoltaic output, thereby generating a photovoltaic output curve. The photovoltaic output here can be calculated using the original formula or the corrected photovoltaic output described in the above embodiment. This secondary correction further improves the accuracy of the photovoltaic output prediction.

[0118] After predicting the PV output curve, we analyze the disturbance to the grid frequency caused by the sudden drop in the mining area load caused by sandstorms based on the changes in PV output and the real-time load of enterprises in the mining area. The specific steps include:

[0119] Inputting the real-time load data of the mining area and the photovoltaic output curve into a preset load forecasting model to obtain the load drop amplitude, wherein the load forecasting model is constructed based on a long short-term memory neural network;

[0120] Calculating the mine area load forecast data based on the mine area load real-time data and the load drop amplitude;

[0121] Calculating a power grid deviation based on the mining area load forecast data and the photovoltaic output curve;

[0122] The grid power deviation is input into a frequency dynamic equation to obtain a grid frequency variation curve.

[0123] In this embodiment, since changes in photovoltaic output are closely related to weather, and the load in a mining area can be affected by weather, such as sandstorms causing a mine to shut down or partially shut down, resulting in a sudden drop in load, a long-short-term memory neural network model is used to model the relationship between the mine load and changes in photovoltaic output. Real-time mine load data and a predicted photovoltaic output curve are input into a preset load forecasting model, which outputs the magnitude of the sudden load drop and the corresponding timestamp of the sudden change point. The difference between the real-time mine load data and the sudden load drop can then be used to determine the predicted mine load.

[0124] After obtaining the mining area load forecast data, the photovoltaic output is subtracted from the mining area load forecast value to obtain the grid power deviation △P. If △P>0, it indicates a power shortage, otherwise, it indicates a power surplus. The grid power deviation is then input into the frequency dynamic equation to obtain the grid frequency change rate:

[0125]

[0126] Where f is the frequency, t is the time, and H is the system inertia constant.

[0127] The frequency change curve of the power grid is obtained according to the frequency change rate.

[0128] After obtaining power load data such as mining area load forecast data, grid power deviation, and grid frequency change curve, PV output control is determined based on this data. The specific determination steps include:

[0129] Calculating the covariance between the mine area load forecast data and the photovoltaic output curve, and using the covariance as the output load matching degree;

[0130] It is determined whether the output load matching degree is less than a matching degree threshold, and if so, photovoltaic output dispatch control is triggered.

[0131] In this embodiment, the need for PV output regulation is determined based on the correlation between the mine load forecast data and the PV output curve. This correlation is characterized by covariance. First, the mine load forecast data and the PV output curve are aligned and normalized. Then, the output-load matching degree between the two is calculated using the covariance formula. The relationship between the output-load matching degree and a preset matching degree threshold is then determined. If the output-load matching degree is greater than or equal to the matching degree threshold, the mine load and PV output are considered highly matched, and PV regulation is not required. Otherwise, the matching degree is considered low, and PV output scheduling is required.

[0132] When it is necessary to dispatch photovoltaic power, this embodiment generates a power dispatch strategy based on the grid power deviation and the grid frequency change curve. The specific steps include:

[0133] Calculating the grid frequency deviation according to the grid frequency variation curve, and calculating the initial power adjustment amount using proportional-integral control according to the grid frequency deviation;

[0134] Calculating power deviation compensation according to the power grid power deviation;

[0135] Correcting the initial power adjustment amount according to the power deviation compensation to obtain a power adjustment amount;

[0136] According to the power adjustment amount, a distributed photovoltaic output dispatching strategy is generated through distributed photovoltaic multi-machine coordination, wherein the multi-machine coordination includes equal distribution coordination and priority coordination.

[0137] In this embodiment, the grid frequency deviation Δf is first obtained based on the difference between the grid frequency variation curve and the rated frequency value. Then, the power adjustment amount is calculated based on the grid frequency deviation Δf. Specifically, the initial power adjustment amount is first calculated through proportional integral control (PI control):

[0138]

[0139] Where, Indicates the initial power adjustment amount, Represents the proportional gain coefficient, which is used to quickly respond to frequency changes. Represents the integral gain coefficient, which is used to eliminate steady-state error. represents the grid frequency deviation, and t represents time.

[0140] Then, the power deviation compensation is calculated based on the grid power deviation △P:

[0141]

[0142] Where, Indicates power deviation compensation, Indicates the grid power deviation, Represents the photovoltaic regulation efficiency coefficient.

[0143] Finally, the initial power adjustment is corrected by power deviation compensation, and the final power adjustment is determined using the maximum adjustable capacity of photovoltaic output as a constraint:

[0144]

[0145] Where, Indicates the power adjustment amount, Indicates the maximum adjustable capacity of photovoltaic output.

[0146] Finally, the output of the distributed photovoltaic is regulated according to the power adjustment amount. In this embodiment, a multi-machine coordination strategy is adopted to regulate the output of the distributed photovoltaic, wherein the multi-machine coordination includes equal coordination and priority coordination. Specifically, when equal coordination is adopted, the power adjustment amount is allocated to each photovoltaic according to the capacity ratio of the distributed photovoltaic to achieve output regulation; when priority coordination is adopted, the priority of the distributed photovoltaic is determined according to the distance between the distributed photovoltaic and the load center of the mining area or the photovoltaic response speed. For example, the closer the distance between the photovoltaic and the load center or the higher the photovoltaic response speed, the higher the priority. Then, according to the priority of each photovoltaic, the photovoltaic to be regulated is selected from the distributed photovoltaic, for example, the photovoltaic with a priority greater than the priority threshold is selected as the photovoltaic to be regulated. Finally, the power adjustment amount is allocated to the photovoltaic to be regulated according to the capacity ratio of the photovoltaic to be regulated. It should be noted that after determining the power adjustment amount of the photovoltaic, the output scheduling control of the distributed photovoltaic can be achieved through a variety of control strategies. The output scheduling strategy in this embodiment is only preferred and not limited.

[0147] This embodiment provides a distributed photovoltaic output scheduling and control method based on big data. The present invention predicts the dust path through multi-data fusion and models the solar radiation attenuation in combination with the physical optics model and the neural network model, thereby effectively improving the accuracy of photovoltaic output prediction. By analyzing the grid frequency disturbance caused by the sudden drop in load, the accuracy of the prediction of mining area load and grid frequency is improved. The photovoltaic output is scheduled according to the matching degree between the mining area load and the photovoltaic output, realizing the dynamic matching of photovoltaic power generation and load. Based on big data and multi-source data fusion, the present invention realizes the efficient management of photovoltaic power generation system and stable operation of grid in sandstorm weather through distributed photovoltaic output control and dynamic scheduling optimization.

[0148] See also Figure 2 Based on the same inventive concept, the second embodiment of the present invention proposes a distributed photovoltaic output dispatching and control system based on big data, including:

[0149] The data analysis module 10 is used to predict the movement path of sand and dust based on meteorological remote sensing data and ground monitoring data, and analyze the attenuation of solar radiation to obtain the movement path of sand and dust and radiation attenuation data;

[0150] The output prediction module 20 is used to predict the photovoltaic output change based on the photovoltaic parameters of the distributed photovoltaic system, the dust movement path and the radiation attenuation data to obtain a photovoltaic output curve;

[0151] The disturbance analysis module 30 is used to analyze the disturbance of the grid frequency caused by the sudden drop in load based on the real-time data of the mining area load and the photovoltaic output curve, and obtain power load data, wherein the power load data includes the mining area load forecast data, the grid power deviation and the grid frequency change curve;

[0152] a scheduling trigger module 40 for calculating the output-load matching degree based on the mine area load forecast data and the photovoltaic output curve, and determining whether to trigger photovoltaic output scheduling control based on the output-load matching degree;

[0153] The dispatch control module 50 is used to generate an output dispatch strategy in response to triggering photovoltaic output dispatch control according to the grid power deviation and the grid frequency change curve, and to dispatch and control the output of distributed photovoltaics.

[0154] The technical features and technical effects of the distributed photovoltaic output dispatching and control system based on big data proposed in the embodiment of the present invention are the same as those of the method proposed in the embodiment of the present invention, and will not be described in detail here. Each module in the above-mentioned distributed photovoltaic output dispatching and control system based on big data can be implemented in whole or in part through software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0155] In summary, an embodiment of the present invention proposes a distributed photovoltaic output dispatching and control method and system based on big data. The method predicts the movement path of sand and dust according to meteorological remote sensing data and ground monitoring data, and analyzes the attenuation of solar radiation to obtain sand and dust movement path and radiation attenuation data; predicts the photovoltaic output change according to the photovoltaic parameters of the distributed photovoltaic, the sand and dust movement path and the radiation attenuation data to obtain a photovoltaic output curve; analyzes the disturbance of the load drop on the grid frequency according to the real-time data of the mining area load and the photovoltaic output curve to obtain power load data, and the power load data includes mining area load prediction data, grid power deviation and grid frequency change curve; calculates the output load matching degree according to the mining area load prediction data and the photovoltaic output curve, and determines whether to trigger photovoltaic output dispatching control according to the output load matching degree; in response to triggering photovoltaic output dispatching control, generates an output dispatching strategy according to the grid power deviation and the grid frequency change curve to dispatch and control the output of distributed photovoltaic. The present invention predicts the path of sandstorms through multi-data fusion and models solar radiation attenuation in combination with physical optics models and neural network models, effectively improving the accuracy of photovoltaic output predictions. By analyzing the grid frequency disturbance caused by load drops, the accuracy of mining load and grid frequency predictions is improved. The photovoltaic output is dispatched according to the degree of matching between the mining load and the photovoltaic output, realizing dynamic matching of photovoltaic power generation and load. Based on big data and multi-source data fusion, the present invention realizes efficient management of photovoltaic power generation systems and stable operation of power grids under sandstorm weather through distributed photovoltaic output control and dynamic scheduling optimization.

[0156] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system 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. It should be noted that the various technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0157] The above-described embodiments merely represent several preferred implementations of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art could make several improvements and substitutions without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be based on the scope of protection of the claims.

Claims

1. A distributed photovoltaic output dispatch control method based on big data, characterized in that: include: Based on meteorological remote sensing data and ground monitoring data, the movement path of sand and dust is predicted, and the attenuation of solar radiation is analyzed to obtain the movement path and radiation attenuation data of sand and dust; Predicting photovoltaic output changes based on the photovoltaic parameters of the distributed photovoltaic system, the dust movement path, and the radiation attenuation data to obtain a photovoltaic output curve; Analyze the disturbance of the grid frequency caused by a sudden drop in load based on the real-time data of the mining area load and the photovoltaic output curve to obtain power load data, wherein the power load data includes the mining area load forecast data, the grid power deviation and the grid frequency change curve; Calculating the output-load matching degree based on the mine area load forecast data and the photovoltaic output curve, and determining whether to trigger photovoltaic output dispatch control based on the output-load matching degree; In response to triggering photovoltaic output dispatch control, generating an output dispatch strategy according to the grid power deviation and the grid frequency change curve, and dispatching and controlling the output of distributed photovoltaics; The step of calculating the radiation attenuation data includes: Calculating the median particle size of sand and dust based on solar radiation monitoring data, and obtaining particle size distribution parameters based on the median particle size; The dust extinction coefficient is determined based on the particle size distribution parameters, and the dust diffusion range is spatially calculated using the Kriging interpolation method based on the dust concentration monitoring data and the dust movement path to obtain dust distribution data; Calculating the optical thickness according to the solar radiation wavelength, the dust distribution data and the extinction coefficient; Inputting the optical thickness, the solar radiation wavelength, and the particle size distribution parameter into a preset radiation attenuation model to obtain a radiation attenuation coefficient, wherein the radiation attenuation model is constructed based on a support vector regression model; The step of predicting photovoltaic output changes based on the photovoltaic parameters of the distributed photovoltaic system, the dust movement path, and the radiation attenuation data to obtain a photovoltaic output curve includes: Calculating the dust radiation transmittance according to the optical thickness and the solar zenith angle; Correcting the original solar radiation intensity according to the radiation attenuation coefficient to obtain the solar radiation intensity; According to the difference between the photovoltaic module temperature and the standard module temperature, the standard conversion efficiency is corrected to obtain the photovoltaic module conversion efficiency; Obtaining a photovoltaic output curve according to the solar radiation intensity, the photovoltaic module conversion efficiency, the photovoltaic module area, and the dust radiation transmittance; Inputting solar radiation intensity, photovoltaic module temperature, optical thickness and solar zenith angle into a preset output correction model to obtain a dynamic correction factor, wherein the output correction model is constructed based on a recursive neural network; Correcting the photovoltaic output curve according to the dynamic correction factor to obtain a corrected photovoltaic output curve; The step of generating an output dispatching strategy based on the grid power deviation and the grid frequency change curve and dispatching and controlling the output of distributed photovoltaic power includes: Calculating the grid frequency deviation according to the grid frequency variation curve, and calculating the initial power adjustment amount using proportional-integral control according to the grid frequency deviation; Calculating power deviation compensation according to the power grid power deviation; Correcting the initial power adjustment amount according to the power deviation compensation to obtain a power adjustment amount; According to the power adjustment amount, a distributed photovoltaic output dispatching strategy is generated through distributed photovoltaic multi-machine coordination, wherein the multi-machine coordination includes equal distribution coordination and priority coordination.

2. The distributed photovoltaic output dispatch control method based on big data according to claim 1 is characterized in that: The steps of predicting the movement path of dust and analyzing solar radiation attenuation based on meteorological remote sensing data and ground monitoring data to obtain the movement path of dust and radiation attenuation data include: Inputting meteorological remote sensing data into a preset boundary extraction model to obtain dust boundary feature data, wherein the boundary extraction model is constructed based on a convolutional neural network; The dust movement path is calculated using a particle swarm optimization algorithm based on wind direction and speed data, ambient temperature data, dust concentration monitoring data, and the dust boundary feature data.

3. The distributed photovoltaic output dispatch control method based on big data according to claim 1 is characterized in that: The step of analyzing the disturbance of the grid frequency caused by a sudden load drop based on the real-time mining area load data and the photovoltaic output curve to obtain power load data includes: Inputting the real-time load data of the mining area and the photovoltaic output curve into a preset load forecasting model to obtain the load drop amplitude, wherein the load forecasting model is constructed based on a long short-term memory neural network; Calculating the mine area load forecast data based on the mine area load real-time data and the load drop amplitude; Calculating a power grid deviation based on the mining area load forecast data and the photovoltaic output curve; The grid power deviation is input into a frequency dynamic equation to obtain a grid frequency variation curve.

4. The distributed photovoltaic output dispatch control method based on big data according to claim 1 is characterized in that: The step of calculating the output load matching degree according to the mine area load forecast data and the photovoltaic output curve, and determining whether to trigger photovoltaic output dispatch control according to the output load matching degree includes: Calculating the covariance between the mine area load forecast data and the photovoltaic output curve, and using the covariance as the output load matching degree; It is determined whether the output load matching degree is less than a matching degree threshold, and if so, photovoltaic output dispatch control is triggered.

5. The distributed photovoltaic output dispatch control method based on big data according to claim 1 is characterized in that: The initial power adjustment amount is expressed by the following formula: Where, Indicates the initial power adjustment amount, represents the proportional gain coefficient, represents the integral gain coefficient, represents the grid frequency deviation, and t represents time; The power deviation compensation is expressed by the following formula: Where, Indicates power deviation compensation, Indicates the grid power deviation, Represents the photovoltaic regulation efficiency coefficient; The power adjustment amount is expressed by the following formula: Where, Indicates the power adjustment amount, Indicates the maximum adjustable capacity of photovoltaic output.

6. The distributed photovoltaic output dispatch control method based on big data according to claim 1 is characterized in that: The step of generating a distributed photovoltaic output dispatching strategy based on the power adjustment amount through multi-machine coordination of distributed photovoltaics includes: When equal distribution coordination is adopted, the power adjustment amount is distributed to each distributed photovoltaic according to the capacity ratio of the distributed photovoltaic; When priority coordination is adopted, the priority of distributed photovoltaics is determined based on the distance between the distributed photovoltaics and the load center of the mining area or the photovoltaic response speed; According to the priority, a photovoltaic unit to be regulated is selected from the distributed photovoltaic units, and the power adjustment amount is allocated to the photovoltaic unit to be regulated.

7. A distributed photovoltaic output dispatching and control system based on big data, characterized in that: include: The data analysis module is used to predict the movement path of sand and dust based on meteorological remote sensing data and ground monitoring data, and analyze solar radiation attenuation to obtain sand and dust movement path and radiation attenuation data. Specifically, it includes: calculating the median particle size of sand and dust based on solar radiation monitoring data, and obtaining particle size distribution parameters based on the median particle size; The dust extinction coefficient is determined based on the particle size distribution parameters, and the dust diffusion range is spatially calculated using the Kriging interpolation method based on the dust concentration monitoring data and the dust movement path to obtain dust distribution data; Calculating the optical thickness according to the solar radiation wavelength, the dust distribution data and the extinction coefficient; Inputting the optical thickness, the solar radiation wavelength, and the particle size distribution parameter into a preset radiation attenuation model to obtain a radiation attenuation coefficient, wherein the radiation attenuation model is constructed based on a support vector regression model; The output prediction module is used to predict the photovoltaic output change based on the photovoltaic parameters of the distributed photovoltaic system, the dust movement path and the radiation attenuation data to obtain a photovoltaic output curve; including: Calculating the dust radiation transmittance according to the optical thickness and the solar zenith angle; Correcting the original solar radiation intensity according to the radiation attenuation coefficient to obtain the solar radiation intensity; According to the difference between the photovoltaic module temperature and the standard module temperature, the standard conversion efficiency is corrected to obtain the photovoltaic module conversion efficiency; Obtaining a photovoltaic output curve according to the solar radiation intensity, the photovoltaic module conversion efficiency, the photovoltaic module area, and the dust radiation transmittance; Inputting solar radiation intensity, photovoltaic module temperature, optical thickness and solar zenith angle into a preset output correction model to obtain a dynamic correction factor, wherein the output correction model is constructed based on a recursive neural network; Correcting the photovoltaic output curve according to the dynamic correction factor to obtain a corrected photovoltaic output curve; A disturbance analysis module is used to analyze the disturbance of the grid frequency caused by a sudden drop in load based on the real-time data of the mining area load and the photovoltaic output curve, and obtain power load data, wherein the power load data includes the mining area load forecast data, the grid power deviation and the grid frequency change curve; a scheduling trigger module, configured to calculate an output-load matching degree based on the mine area load forecast data and the photovoltaic output curve, and determine whether to trigger photovoltaic output scheduling control based on the output-load matching degree; The dispatch control module is configured to generate an output dispatch strategy in response to triggering photovoltaic output dispatch control, based on the grid power deviation and the grid frequency change curve, and perform dispatch control on the output of distributed photovoltaics, including: Calculating the grid frequency deviation according to the grid frequency variation curve, and calculating the initial power adjustment amount using proportional-integral control according to the grid frequency deviation; Calculating power deviation compensation according to the power grid power deviation; Correcting the initial power adjustment amount according to the power deviation compensation to obtain a power adjustment amount; According to the power adjustment amount, a distributed photovoltaic output dispatching strategy is generated through distributed photovoltaic multi-machine coordination, wherein the multi-machine coordination includes equal distribution coordination and priority coordination.

Images