Photovoltaic power station ultra-short-term irradiation prediction method based on single-photon laser radar

Abstract

The invention discloses a photovoltaic power station ultra-short-term irradiation prediction method based on a single-photon laser radar, belongs to the technical field of laser radar signal processing, and solves the problem of how to use the laser radar to obtain cloud layer information and realize ultra-short-term irradiation prediction of a photovoltaic power station under different weather conditions. An echo signal profile of the laser radar is inverted through an improved differential zero crossing algorithm, a cloud parameter data set is obtained, based on a volume scanning mode of the radar, the condition of clouds in the sky can be inverted, feature parameters of more clouds are obtained, and the integrity and accuracy of data are ensured; the method comprises the following steps: calculating a sun path, segmenting an effective scanning area so as to extract cloud layer features and reduce feature dimensions, finally combining meteorological features and historical irradiation data to construct a feature matrix, adopting a CNN-LSTM hybrid model to predict irradiation, and showing relatively high precision and stability in prediction of different weather types.

Description

Technical Field

[0001] The present invention belongs to the technical field of laser radar signal processing and relates to an ultra-short-term irradiation prediction method for a photovoltaic power station based on a single-photon laser radar. Background Art

[0002] Against the backdrop of increasing energy shortages and environmental pressures, new energy sources are becoming increasingly important in the global energy structure, and photovoltaic power generation has become one of the core components of renewable energy. As the main driving force for photovoltaic power generation, accurate prediction of solar irradiance is of great significance for optimizing grid dispatch, improving the operating efficiency of photovoltaic power stations, and achieving sustainable energy development. However, solar irradiance is affected by weather conditions, especially cloud movement, and changes frequently and dramatically, resulting in strong volatility in photovoltaic power generation. In order to effectively address this problem, it is of great significance to accurately predict the irradiation of photovoltaic power stations.

[0003] Existing irradiation prediction methods can be divided into ultra-short-term, short-term, and medium- to long-term predictions according to the prediction time. Ultra-short-term predictions focus on irradiation fluctuations within a few hours to a day, and have high timeliness and accuracy requirements. At present, ultra-short-term irradiation prediction methods can be mainly divided into the following three categories: (1) The clear sky model obtained by deducing the surface solar irradiance through empirical formulas; the derivation model based on physical models and empirical formulas has simple input, such as the ASHRAE model, Hottel model, REST2 model, and Iqbal-C model, etc., while the traditional prediction method based on physical models has low accuracy under complex weather conditions and is difficult to deal with nonlinear and multi-dimensional meteorological influences. (2) Time series prediction methods based on historical data and numerical weather forecast (NWP); There are two research trends in the method of machine learning or deep learning prediction model based on historical data and NWP. One is the development of regression models, such as the autoregressive integrated moving average model (ARIMA), which is a classic time series method, but it relies on NWP information. In order to achieve higher prediction accuracy, more and more detailed meteorological information needs to be input; the other is the development of time series prediction models, which rely on historical data and learn trend changes from more historical data, such as long short-term memory network (LSTM), convolutional neural network (CNN), Transformer, Informer and other models. Although the existing technology has achieved certain results in irradiation prediction, there are still some shortcomings. Although machine learning models can handle nonlinear problems well, their training process is complicated and highly dependent on data quality. If the data is insufficient or contains noise, it will seriously affect the prediction effect of the model. (3) Prediction method combined with cloud map; Since cloud layer is the main factor affecting irradiance, the prediction of irradiance combined with cloud changes is still a research hotspot.

[0004] At present, the acquisition of cloud characteristics mainly comes from satellite cloud images and ground-based cloud images. Ground-based cloud images are images collected in real time from the cloud clusters above the test site by the all-sky imager on the ground, and satellite cloud images are images obtained by observing the earth as a whole through meteorological satellites. In addition to satellites and optical cameras, instruments for observing clouds also include laser radars. As an advanced meteorological observation tool, laser radar can obtain atmospheric physical information by emitting laser pulses and receiving their scattered echo signals in the atmosphere. It has the characteristics of high spatial resolution and high temporal resolution, and can accurately detect the distribution and changes of clouds, providing valuable data support for the prediction of solar irradiance. The prior art, such as the invention patent with application publication number CN114296050A, discloses a method for predicting the short-term power generation of photovoltaic power stations based on laser radar cloud image detection. By dividing the effective area of ​​the photovoltaic power station solar panels into grids, the predicted values ​​of the residence time of the cloud shadow in each grid and the area ratio of the cloud projection to each grid are calculated according to the cloud boundary range and moving speed, and then the predicted value of photovoltaic power generation is obtained. However, this method only considers the position and motion prediction of clouds and cannot accurately evaluate the impact of different types of clouds on irradiance, and thus on power.

[0005] The ultra-short-term irradiance prediction methods under the existing technology mainly include ultra-short-term prediction based on satellite cloud images and ultra-short-term prediction based on ground-based cloud images. The resolution of satellite cloud images is usually low, especially in areas with thin clouds or less cloud cover, which may not provide enough detailed information. The acquisition frequency of satellite cloud images is low, usually once every hour or every few hours, which will result in the inability to provide real-time ultra-short-term irradiance change information. In the case of dense clouds, the satellite may not be able to clearly observe the ground situation, affecting the integrity and accuracy of the data. The ground-based cloud images mainly come from all-sky imagers. Although the viewing angle of the all-sky imager is wide, it still cannot cover all areas on the ground. Especially in the case of high buildings or complex terrain, there may be blind spots in the viewing angle, and the image quality of the imager is affected by environmental factors, such as atmospheric pollution, light changes, haze, etc., which may cause image blur or interference, thereby affecting the accuracy of cloud analysis and prediction; in addition, the processing of all-sky images requires a lot of calculations, including image preprocessing, cloud recognition and feature extraction, etc., with high computational complexity and high requirements for computing resources. Summary of the invention

[0006] The technical solution of the present invention is used to solve the problem of how to use laser radar to obtain cloud information and realize ultra-short-term irradiation prediction of photovoltaic power stations under different weather conditions.

[0007] The present invention solves the above technical problems through the following technical solutions:

[0008] The ultra-short-term irradiation prediction method of a photovoltaic power station based on a single-photon laser radar includes the following steps:

[0009] Step S1, setting the scanning mode of the single-photon laser radar to a volume scanning mode, scanning the sky near the photovoltaic power station at a fixed elevation angle, and obtaining echo signals in different directions;

[0010] Step S2: for each echo signal obtained by the laser radar scanning, select the echo signal within 50-100 meters of the highest detection target distance, use its mean as the background noise, and subtract the background noise from the original echo signal as the corrected echo signal;

[0011] Step S3, using a differential zero-crossing method to identify cloud information in each echo signal;

[0012] Step S4, obtaining scanning cycle data obtained by rotating the laser radar within the azimuth range, calculating the variation range of the solar azimuth angle of the laser radar within one scanning cycle, and intercepting the key area data according to the time point closest to the solar azimuth angle in the scanning cycle to obtain an intercepted data set;

[0013] Step S5, reducing the data dimension and extracting more accurate cloud features;

[0014] Step S6, selecting meteorological data and historical irradiation data recorded by the meteorological monitoring platform of the photovoltaic power station, deleting missing data and erroneous data therein, obtaining historical time series irradiation and time series meteorological characteristics, merging the historical time series irradiation, time series meteorological characteristics and the cloud layer characteristics extracted in step S5 into all feature vectors at that moment, and intercepting them using a fixed time interval sliding window method to obtain an input feature matrix;

[0015] Step S7, construct a CNN-LSTM model, input the feature matrix into the convolutional neural network for feature extraction, input the extracted time series features into the long short-term memory layer for irradiance prediction, and obtain the irradiance value of the time period to be predicted.

[0016] Furthermore, the step S1 includes the following steps:

[0017] Step S11, setting the elevation angle of the laser radar to a fixed value, at which the laser radar rotates around the current azimuth angle α at a constant rate;

[0018] Step S12: After the laser radar emits a single-photon laser pulse at the current azimuth angle α, the laser radar receives an echo signal P from the direction. α (r i ), the signal strength received by the laser radar in a single scan is Among them, r1, r2, ..., r Nrepresents the distance of the detected target, N represents the total number of echo signal sampling points, and i represents the i-th echo signal sampling point;

[0019] Step S13, after completing the signal acquisition at the current azimuth angle α, the laser radar continues to change the azimuth angle, emitting single-photon laser pulses and receiving echo signals to the next azimuth angle α+Δα until the predetermined azimuth angle range is covered.

[0020] Furthermore, step S3 includes the following steps:

[0021] Step S31, distance correction is performed on the original echo signal to eliminate signal attenuation caused by distance attenuation, wherein the distance correction is performed on the original echo signal using the following formula:

[0022] X α (r) = P′ α (r)r 2

[0023] In the formula, P′ α (r) represents the backscattered signal of the lidar at distance r, X α (r) represents the α (r) The signal after distance square correction, r represents the distance of the detected target;

[0024] Step S32, differentiating the preprocessed echo signal, and fitting the differential signal using a sliding window;

[0025] Step S33, using the differential zero crossing method to determine the positions of the cloud base and cloud peak in the echo signal profile, and determine the cloud base signal r b 、Yunfeng Signal m 、Genting signal t , preliminarily screen out candidate signal areas containing cloud signals;

[0026] Step S34, filtering the cloud area by threshold value, eliminating misjudgment caused by thick aerosol or background light according to the signal intensity ratio, and determining the number of clouds.

[0027] Furthermore, the step S34 uses the following formula to filter the cloud area:

[0028]

[0029] In the formula, thr represents the threshold value, X α (r m ) represents the cloud peak height, X α (r b ) represents the cloud base height, P′(r m ) represents the distance from the cloud peak signal r mThe backscattered signal of the laser radar at b ) represents the distance from the cloud base signal r b The lidar backscatter signal at the location is judged to contain cloud signals when the threshold is greater than 4, and is judged to contain aerosol when the threshold is less than or equal to 4.

[0030] Furthermore, the step S4 comprises the following steps:

[0031] Step S41, calculating the variation range of the solar azimuth angle of the laser radar within a scanning cycle;

[0032] Step S42, within a scanning cycle of the laser radar, based on the time point corresponding to the closest solar azimuth angle in the scanning cycle, capture the scanning data of adjacent 30 seconds, for a total of 1 minute of data.

[0033] Furthermore, the step S41 uses the following formula to calculate the variation range of the solar azimuth angle of the laser radar within a scanning cycle:

[0034]

[0035] H=15°×(T-12)

[0036]

[0037] In the formula, δ represents the solar declination angle, n represents the nth day of the year, H represents the solar hour angle, T represents the solar time, φ represents the geographical latitude, and α sun Represents the solar azimuth.

[0038] Furthermore, the cloud characteristics in step S5 include solar altitude angle, solar azimuth angle, periodic cloud fraction, cloud base height, cloud thickness, number of cloud layers, and regional cloud fraction.

[0039] Furthermore, the step S5 comprises the following steps:

[0040] Step S51, analyzing the scanning cycle data obtained by rotating the laser radar within the azimuth range according to step S3, inverting each laser radar echo signal, and determining whether there is a cloud signal. If there is a cloud signal, determining the cloud base height, cloud thickness, and cloud number;

[0041] Step S52, counting the number of echo signals containing cloud signals in the entire scanning cycle data, and comparing it with the number of echo signals in the entire scanning cycle, to obtain the cloud score in the entire scanning cycle, which is used to indicate the cloud coverage ratio in the sky in the entire scanning cycle;

[0042] Step S53, extracting the cloud base height corresponding to the echo signal in the intercepted data set, and calculating the average of all cloud base heights in the key area; wherein, if there are multiple layers of clouds in the key area, the cloud base height of the lowest layer is taken as the representative value of the cloud base height in the area;

[0043] Step S54, extracting the mean value of the cloud thickness in the key area; wherein, if there are multiple layers of clouds in the key area, the thickness of each layer of clouds is accumulated to obtain the total cloud thickness;

[0044] Step S55, counting the number of cloud layers obtained by inverting the echo signals in the key area, analyzing the mode of the number of cloud layers in the area, and using this to characterize the number of cloud layers in the area;

[0045] Step S56, counting the number of echo signals containing cloud signals in the key area, and comparing it with the number of echo signals in the entire key area, to obtain a regional cloud score in the key area.

[0046] Furthermore, the meteorological information in step S6 includes temperature, relative humidity, air pressure, and wind speed.

[0047] Furthermore, the CNN-LSTM model in step S7 includes an input layer, a convolutional layer, a pooling layer, an LSTM layer, a fully connected layer and an output layer.

[0048] The advantages of the present invention are:

[0049] (1) The present invention uses a single-photon laser radar to scan the cloud information around the photovoltaic power station, detect key cloud parameters such as cloud coverage, cloud thickness, and cloud height in the area, extract cloud characteristics, combine historical irradiation and meteorological data, and use the CNN-LSTM time series prediction algorithm to achieve high-precision irradiance prediction.

[0050] (2) The present invention inverts the echo signal profile of the lidar through an improved differential zero-crossing algorithm to obtain a cloud parameter data set. Based on the volume scanning mode of the radar, the situation of clouds in the sky can be inverted. The radar scanning range is larger than that of the ground-based cloud map taken by a fisheye lens, and the data resolution is higher than that of the satellite cloud map. More characteristic parameters of the clouds can also be obtained to ensure the integrity and accuracy of the data.

[0051] (3) The present invention further calculates the sun path through the sun position model, divides the effective scanning area to extract cloud features, reduces the feature dimension, and finally constructs a feature matrix by combining meteorological characteristics and historical irradiation data. The CNN-LSTM hybrid model is used to predict irradiation, showing high accuracy and stability in the prediction of different weather types. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1is a schematic diagram of an ultra-short-term irradiation prediction method for a photovoltaic power station based on a single-photon laser radar according to a first embodiment of the present invention;

[0053] Figure 2 is a schematic diagram of a single-photon laser radar in a volume scanning mode according to a first embodiment of the present invention;

[0054] Figure 3 is a schematic diagram of a differential zero-crossing algorithm according to a first embodiment of the present invention;

[0055] Figure 4 Schematic diagram of data heat and area capture of a single-photon laser radar in a scanning cycle according to the first embodiment of the present invention;

[0056] Figure 5 It is a schematic diagram of the CNN-LSTM model of the first embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and specific embodiments:

[0059] Embodiment 1

[0060] like Figure 1 Specifically, a method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar is disclosed, comprising the following steps:

[0061] Step S1, setting the scanning mode of the single-photon laser radar to a volume scanning mode, scanning the sky near the photovoltaic power station at a fixed elevation angle, and obtaining echo signals in different directions. Specifically, the step S1 includes the following steps:

[0062] Step S11, setting the elevation angle of the laser radar to a fixed value, at which the laser radar rotates around the current azimuth angle α at a constant rate;

[0063] Step S12, after the laser radar emits a single-photon laser pulse at each azimuth angle, the laser radar receives an echo signal from that direction;

[0064] In this embodiment, after the laser radar emits a single-photon laser pulse at the current azimuth angle α, the laser radar receives an echo signal P from this direction.α (r i ), the signal strength received by the laser radar in a single scan is The echo signal is a sequence set that decays with distance at different azimuths in space, where r1, r2, ..., r N Represents the distance of the detected target, N represents the total number of echo signal sampling points, and i represents the i-th echo signal sampling point.

[0065] Step S13, after completing the signal acquisition at the current azimuth angle α, the laser radar continues to change the azimuth angle, emitting single-photon laser pulses and receiving echo signals to the next azimuth angle α+Δα until the predetermined azimuth angle range is covered, and the specific azimuth angle range is 0-360°.

[0066] In the existing technology, lidar usually adopts modes such as horizontal scanning (PPI) and elevation scanning (RHI). Among them, elevation scanning (RHI) is mainly used to detect the vertical structure of the atmosphere, such as cloud height, aerosol layer thickness, and vertical profiles of temperature and humidity; horizontal scanning (PPI) is suitable for detecting the horizontal distribution of aerosols and clouds in a larger range at a fixed height, or detecting local atmospheric phenomena in a smaller azimuth range.

[0067] However, since the azimuth and elevation of the sun change continuously throughout the day, the impact of clouds on irradiance must take into account the dynamics of the clouds around the sun. Traditional scanning modes usually fix the azimuth or set the elevation to 0° for scanning. This method is difficult to meet the cloud information detection required for irradiance prediction. The volume scanning mode (VCP) has significant advantages over traditional scanning methods. It can not only detect cloud distribution at different vertical heights, but also obtain cloud information within different azimuth ranges. Therefore, volume scanning can provide cloud data within a larger spatial range, greatly improving the accuracy of irradiance prediction.

[0068] like Figure 2 As shown, the volume scanning mode (VCP) is used in this embodiment to track the cloud dynamics in the area of ​​the sun's moving path, rather than passive detection at a fixed angle. Compared with the all-sky imager used in the prior art, the cloud information obtained by the lidar through the echo signal is richer and more detailed, thus providing stronger support for irradiance prediction.

[0069] Step S2: for each echo signal P obtained by laser radar scanning α (r i ), select the echo signal within 50-100 meters of the highest detection target distance, take its mean as the background noise, and take the original echo signal minus the background noise as the corrected echo signal, where the corrected echo signal P′ is calculated using the following formulaα (r i ):

[0070]

[0071] In the formula, P′ α (r i ) represents the corrected echo signal, and m represents the number of sampling points within 50-100 meters.

[0072] Step S3, using the differential zero-crossing method to identify the cloud information in each echo signal. Specifically, step S3 includes the following steps:

[0073] Step S31, preprocessing the echo signal; specifically, performing distance correction on the original echo signal to eliminate signal attenuation caused by distance attenuation, wherein the distance correction is performed on the original echo signal using the following formula:

[0074] X α (r) = P′ α (r)r 2

[0075] In the formula, P′ α (r) represents the backscattered signal of the lidar at distance r, X α (r) represents the α (r) The signal after distance square correction, r represents the distance of the detected target.

[0076] Step S32, differentiating the preprocessed echo signal, and fitting the differential signal using a sliding window; wherein, fitting the differential signal using a sliding window is specifically performing 7-point sliding window fitting on the differential signal.

[0077] When using the differential zero crossing method, the calculated differential signal (i.e., the rate of change of the echo signal) may have too many zero crossing points due to noise or data instability. These extra zero crossing points, also known as zero crossing points, do not represent real physical phenomena, but are caused by factors such as noise or sampling errors in the echo signal.

[0078] In this embodiment, in order to further reduce the zero-crossing points in the echo signal change rate (i.e., the differential signal) in the differential calculation, a 7-point sliding window is used to fit the differential signal. The signal is locally smoothed by using a window of a fixed size. The window slides on the differential signal, and the data in the window is fitted each time it slides, thereby smoothing the signal fluctuations and reducing the impact of high-frequency noise on the signal.

[0079] Step S33, invert the cloud parameters; specifically, use the differential zero crossing method to determine the positions of the cloud base and cloud peak in the echo signal profile, and determine the cloud base signal rb 、Yunfeng Signal m 、Genting signal t , preliminarily screen out candidate signal areas containing cloud signals;

[0080] Step S34, screening the clouds; specifically, screening the cloud area by threshold, eliminating misjudgment caused by thick aerosol or background light according to the signal intensity ratio, and determining the number of clouds;

[0081] Among them, the following formula is used to filter the cloud area:

[0082]

[0083] In the formula, thr represents the threshold value, X α (r m ) represents the cloud peak height, X α (r b ) represents the cloud base height, P′(r m ) represents the distance from the cloud peak signal r m The backscattered signal of the laser radar at b ) represents the distance from the cloud base signal r b The laser radar backscatter signal at . This embodiment uses a threshold value thr=4 to determine the cloud area. When the threshold value is greater than 4, it is determined to contain cloud signals. When the threshold value is less than or equal to 4, it is determined to be an aerosol.

[0084] In this embodiment, since the cloud droplet concentration, water content and phase state of the cloud are different, the backscatter echo intensity is also different. This embodiment uses the differential zero crossing method based on an important observation that the density of aerosols is usually less than that of clouds, and the echo signal is attenuated before the cloud is detected.

[0085] like Figure 3 As shown in the figure, when the laser irradiates the cloud boundary, its echo signal intensity P α (r i ) will surge. According to the characteristics of the laser radar echo signal, the position where its slope changes from negative to positive is the cloud bottom signal r b , indicating the cloud bottom position of the cloud layer; when the signal strength reaches the maximum value and starts to decay, the position at this time is the cloud peak signal r of this layer of cloud m , that is, the position where the slope of the lidar profile changes from positive to negative, indicating the position of the cloud peak of the cloud layer.

[0086] When the laser passes through the cloud, P α (r i ) decreases rapidly, generating a cloud echo signal, r tIndicates the cloud top position. A cloud lidar echo signal can be expressed as a set of adjacent peaks and troughs on its corresponding first-order differential signal, while the cloud bottom signal r b 、Yunfeng Signal m 、Genting signal t That is the zero point where the differential signal intersects the height coordinate axis.

[0087] Step S4, cropping the scanning area considering the path of the incident light; according to step S1, the scanning cycle data obtained by rotating the laser radar within the azimuth range is obtained, the variation range of the solar azimuth angle of the laser radar within one scanning cycle is calculated, and the key area data is intercepted according to the time point closest to the solar azimuth angle in the scanning cycle to obtain the intercepted data set.

[0088] Specifically, the following steps are included:

[0089] like Figure 4 As shown, based on the single-photon laser radar setting the volume scanning mode in step S1, the scanning cycle data obtained by rotating the laser radar in the azimuth angle range of 0-360° can be obtained.

[0090] Step S41, calculating the sun path; specifically, using the following formula to calculate the variation range of the solar azimuth (i.e., the azimuth of incident sunlight) of the laser radar within a scanning cycle:

[0091]

[0092] H=15°×(T-12)

[0093]

[0094] In the formula, δ represents the solar declination angle, n represents the nth day of the year, H represents the solar hour angle, T represents the solar time, φ represents the geographical latitude, and α sun Represents the solar azimuth.

[0095] like Figure 4 As shown, in this embodiment, the scanning period is 11:58-13:07. Combined with the geographical location, date and time range of the laser radar installation location, the above formula is used to calculate the variation range of the solar azimuth angle during this time period:

[0096] Step S42, determine the key azimuth and intercept the data; in a scanning cycle of the laser radar, the scanning azimuth of the laser radar will almost overlap with the solar azimuth at a certain moment. The azimuth at this time is the key to extracting cloud features. According to the time point corresponding to the closest solar azimuth in the scanning cycle, the scanning data of the adjacent 30 seconds is intercepted, a total of 1 minute of data.

[0097] like Figure 4As shown in , during this scanning cycle, the angle between the solar azimuth and the laser radar azimuth is closest to 199.42°. The scanning data of the time point corresponding to this azimuth is intercepted for 30 seconds, a total of 1 minute of data, as shown in Figure 4 The range selected by the rectangular box is shown in the figure.

[0098] Step S5, reducing the data dimension and extracting more accurate cloud features; the cloud features include solar altitude angle, solar azimuth angle, periodic cloud fraction, cloud base height, cloud thickness, number of clouds, and regional cloud fraction; specifically, step S5 includes the following steps:

[0099] Step S51, according to step S3, analyzes the scanning cycle data obtained by rotating the laser radar within the azimuth range, inverts each laser radar echo signal, and determines whether there is a cloud signal. If there is a cloud signal, determine the cloud base height, cloud thickness, and number of clouds.

[0100] Step S52, counting the number of echo signals containing cloud signals in the entire scanning cycle data, and comparing it with the number of echo signals in the entire scanning cycle, obtaining the cloud score in the entire scanning cycle, which is used to represent the cloud coverage ratio in the sky in the entire scanning cycle.

[0101] Step S53, extracting the cloud base height corresponding to the echo signal in the intercepted data set, and calculating the mean of all cloud base heights in the key area;

[0102] Furthermore, if there are multiple layers of clouds in the key area, the cloud base height of the lowest layer is taken as the representative value of the cloud base height in the area.

[0103] Step S54, extracting the mean value of the cloud thickness in the key area;

[0104] Furthermore, if there are multiple layers of clouds in the key area, the thickness of each layer of clouds is accumulated to obtain the total cloud thickness.

[0105] Step S55, counting the number of cloud layers obtained by inverting the echo signals in the key area, analyzing the mode of the number of cloud layers in the area, and using this to characterize the number of cloud layers in the area.

[0106] Step S56, counting the number of echo signals containing cloud signals in the key area, and comparing it with the number of echo signals in the entire key area, to obtain a regional cloud score in the key area.

[0107] Step S6, constructing a feature matrix; selecting meteorological data and historical irradiation data recorded by the meteorological monitoring platform of the photovoltaic power station, deleting missing data and erroneous data, and obtaining historical time series irradiation and time series meteorological features. The historical time series irradiation, time series meteorological features and cloud features extracted in step S5 are combined into all feature vectors at that moment, and the fixed time interval sliding window method is used to intercept and obtain the input feature matrix.

[0108] Furthermore, the meteorological information includes temperature, relative humidity, air pressure, and wind speed;

[0109] Step S7, constructing a CNN-LSTM model, inputting the feature matrix into the convolutional neural network for feature extraction, inputting the extracted time series features into the long short-term memory layer for irradiance prediction, and obtaining the irradiance value of the time period to be predicted. Specifically, step S7 includes the following steps:

[0110] Step S71, constructing a CNN-LSTM model; the CNN-LSTM model includes an input layer, a convolutional layer, a pooling layer, an LSTM layer, a fully connected layer and an output layer;

[0111] Furthermore, the convolution operation is performed in the convolution layer using the following formula:

[0112] (X*W)(i,j)=Σ m Σ n X(i+m,j+n)·W(m,n)

[0113] Where X represents the input data matrix, W represents the convolution kernel (filter), i and j represent the position index of the output matrix, and m and n represent the position index of the convolution kernel.

[0114] Furthermore, the activation function is expressed in the convolutional layer using the following formula:

[0115] a=f(z)

[0116] In the formula, a represents the output value of the convolution layer, f() represents the activation function of the convolution layer, and this embodiment adopts the Relu activation function, and z represents the input value.

[0117] Furthermore, the pooling operation is performed in the pooling layer using the following formula:

[0118] P = max(a)

[0119] In the formula, p represents the output value after pooling, and max() represents the maximum pooling operation.

[0120] like Figure 5As shown in the figure, the CNN-LSTM hybrid neural network provided in this embodiment combines the advantages of convolutional neural network (CNN) and long short-term memory neural network (LSTM), and is suitable for processing spatiotemporal data. It has significant results in the fields of weather forecasting, image analysis, time series forecasting, etc. Among them, CNN is good at extracting local and spatial features from data, and can capture local patterns in data through convolutional layers and pooling layers. LSTM is a special RNN (Recurrent Neural Network) that can capture long-term dependencies. By adding a gate structure, that is, a forget gate f t , input gate i t and output gate o t The three gates can effectively solve the gradient vanishing and gradient exploding problems in traditional RNN. In addition, by adding cell memory units to the LSTM network, the LSTM network has good memory capacity and solves the time series prediction problem of ultra-short-term irradiation of photovoltaic power stations.

[0121] Furthermore, the following formula is used in the LSTM layer to represent the gate unit information processing:

[0122] i t =σ(w i,x x t +w i,h h t-1 +b i )

[0123] f t =σ(w f,x x t +w f,h h t-1 +b f )

[0124] o t =σ(w o,x x t +w o,h h t-1 +b o )

[0125] g t =tanh(w g,x x t +w g,h h t-1 +b g )

[0126] In the formula, g t Represents the value of the candidate memory unit, that is, the input x is processed by the activation function t and the previous hidden state h t-1 The combination of σ represents the LSTM layer activation function. This embodiment uses the sigmoid function.i,x 、w i,h 、w f,x 、w f,h 、w o,x 、w o,h 、w g,x 、w g,h represents the weight matrix, x t represents the input at time t, h t-1 represents the short-term state of the output at time t-1, b i 、b f 、b o 、b g Represents the input gate, forget gate, output gate, and candidate and unit bias terms.

[0127] Furthermore, after the gate unit information is processed, the memory module is updated using the following formula:

[0128] c t =f t c t-1 +i t g t

[0129] In the formula, c t represents the long-term state after the improved gradient transfer method, c t-1 Indicates the state of the memory unit at the previous moment.

[0130] Furthermore, since the memory module and the output gate jointly determine the output, this embodiment uses the following formula to calculate the LSTM layer output:

[0131] y t =h t =o t ×tanh(c t )

[0132] In the formula, y t Represents the output value of the LSTM layer.

[0133] Step S712, training the convolutional neural network, specifically, includes the following steps:

[0134] I. Prepare training data and split the training data into training set and test set;

[0135] II. Normalize the input signal and input it into the CNN convolution layer, where the convolution layer selects the convolution kernel size and pooling method;

[0136] III. Initialize all weight parameters in the CNN-LSTM combination model;

[0137] IV. Continuously calculate the neural network results of each layer layer by layer, and finally get the output of the neurons in this layer through the activation function;

[0138] V. Use the Adam optimizer to update the weight parameters and bias parameters and backpropagate the training error;

[0139] VI. According to the training error, calculate the gradient of each parameter, update the model parameters layer by layer, iterate until the total error converges, and stop training.

[0140] Step S72, inputting the feature matrix into the convolutional neural network for feature extraction;

[0141] Step S73, input the extracted time series features into the long short-term memory layer for irradiance prediction.

[0142] In this embodiment, the time series feature data is first input from the input layer to the convolution layer, and multiple convolution layers and pooling layers are used to extract the spatial features of the input data. The output of the convolution layer is flattened into a one-dimensional array and passed to the LSTM layer. The LSTM layer is used to capture the time characteristics of the data and understand the long-term dependencies. The output of the LSTM layer is then passed to the fully connected layer for further nonlinear combination and prediction, and finally the prediction result is output through the output layer.

[0143] The present invention uses single-photon lidar to scan the cloud information around the photovoltaic power station, detects key cloud parameters such as cloud coverage, cloud thickness, and cloud height in the area, extracts cloud characteristics, combines historical irradiation and meteorological data, and uses the CNN-LSTM time series prediction algorithm to achieve high-precision irradiance prediction.

[0144] The present invention inverts the echo signal profile of the lidar through an improved differential zero-crossing algorithm to obtain a cloud parameter data set. Based on the volume scanning mode of the radar, the situation of clouds in the sky can be inverted. The radar scanning range is larger than that of the ground-based cloud map taken by a fisheye lens, and the data resolution is higher than that of the satellite cloud map. More characteristic parameters of the clouds can also be obtained to ensure the integrity and accuracy of the data.

[0145] The present invention further calculates the sun path through the sun position model, divides the effective scanning area to extract cloud features, reduces the feature dimension, and finally constructs a feature matrix based on meteorological characteristics and historical irradiation data. The CNN-LSTM hybrid model is used to predict irradiation, which shows high accuracy and stability in the prediction of different weather types.

[0146] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An ultra-short-term irradiation prediction method for photovoltaic power stations based on single-photon laser radar, characterized in that: The following steps are involved: Step S1, setting the scanning mode of the single-photon laser radar to a volume scanning mode, scanning the sky near the photovoltaic power station at a fixed elevation angle, and obtaining echo signals in different directions; Step S2: for each echo signal obtained by the laser radar scanning, select the echo signal within 50-100 meters of the highest detection target distance, use its mean as the background noise, and subtract the background noise from the original echo signal as the corrected echo signal; Step S3, using a differential zero-crossing method to identify cloud information in each echo signal; Step S4, obtaining scanning cycle data obtained by rotating the laser radar within the azimuth range, calculating the variation range of the solar azimuth angle of the laser radar within one scanning cycle, and intercepting the key area data according to the time point closest to the solar azimuth angle in the scanning cycle to obtain an intercepted data set; Step S5, reducing the data dimension and extracting more accurate cloud features; Step S6, selecting meteorological data and historical irradiation data recorded by the meteorological monitoring platform of the photovoltaic power station, deleting missing data and erroneous data therein, obtaining historical time series irradiation and time series meteorological characteristics, merging the historical time series irradiation, time series meteorological characteristics and the cloud layer characteristics extracted in step S5 into all feature vectors at that moment, and intercepting them using a fixed time interval sliding window method to obtain an input feature matrix; Step S7, construct a CNN-LSTM model, input the feature matrix into the convolutional neural network for feature extraction, input the extracted time series features into the long short-term memory layer for irradiance prediction, and obtain the irradiance value of the time period to be predicted.

2. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar according to claim 1 is characterized in that: The step S1 comprises the following steps: Step S11, setting the elevation angle of the laser radar to a fixed value, at which the laser radar rotates around the current azimuth angle α at a constant rate; Step S12: After the laser radar emits a single-photon laser pulse at the current azimuth angle α, the laser radar receives an echo signal P from the direction. α (r i ), the signal strength received by the laser radar in a single scan is Among them, r1, r2, ..., r N represents the distance of the detected target, N represents the total number of echo signal sampling points, and i represents the i-th echo signal sampling point; Step S13, after completing the signal acquisition at the current azimuth angle α, the laser radar continues to change the azimuth angle, emitting single-photon laser pulses and receiving echo signals to the next azimuth angle α+Δα until the predetermined azimuth angle range is covered.

3. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar according to claim 2 is characterized in that: The step S3 comprises the following steps: Step S31, distance correction is performed on the original echo signal to eliminate signal attenuation caused by distance attenuation, wherein the distance correction is performed on the original echo signal using the following formula: X α (r)=P′ α (r)r 2 In the formula, P′ α (r) represents the backscattered signal of the lidar at distance r, X α (r) represents the α (r) The signal after distance square correction, r represents the distance of the detected target; Step S32, differentiating the preprocessed echo signal, and fitting the differential signal using a sliding window; Step S33, using the differential zero crossing method to determine the positions of the cloud base and cloud peak in the echo signal profile, and determine the cloud base signal r b 、Yunfeng Signal m 、Genting signal t , preliminarily screen out candidate signal areas containing cloud signals; Step S34, filtering the cloud area by threshold value, eliminating misjudgment caused by thick aerosol or background light according to the signal intensity ratio, and determining the number of clouds.

4. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar according to claim 3 is characterized in that: The step S34 uses the following formula to filter the cloud area: In the formula, thr represents the threshold value, X α (r m ) represents the cloud peak height, X α (r b ) represents the cloud base height, P′(r m ) represents the distance from the cloud peak signal r m The backscattered signal of the laser radar at b ) represents the distance from the cloud base signal r b The lidar backscatter signal at the location is judged to contain cloud signals when the threshold is greater than 4, and is judged to contain aerosol when the threshold is less than or equal to 4.

5. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar according to claim 3 is characterized in that: The step S4 comprises the following steps: Step S41, calculating the variation range of the solar azimuth angle of the laser radar within a scanning cycle; Step S42, within a scanning cycle of the laser radar, based on the time point corresponding to the closest solar azimuth angle in the scanning cycle, capture the scanning data of adjacent 30 seconds, for a total of 1 minute of data.

6. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar according to claim 5 is characterized in that: The step S41 uses the following formula to calculate the variation range of the solar azimuth angle of the laser radar within a scanning cycle: H=15°×(T-12) In the formula, δ represents the solar declination angle, n represents the nth day of the year, H represents the solar hour angle, T represents the solar time, φ represents the geographical latitude, and α sun Represents the solar azimuth.

7. The method for ultra-short-term irradiation prediction of a photovoltaic power station based on single-photon laser radar according to claim 5 is characterized in that: The cloud characteristics in step S5 include solar altitude angle, solar azimuth angle, periodic cloud fraction, cloud base height, cloud thickness, number of cloud layers, and regional cloud fraction.

8. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar according to claim 7 is characterized in that: The step S5 comprises the following steps: Step S51, analyzing the scanning cycle data obtained by rotating the laser radar within the azimuth range according to step S3, inverting each laser radar echo signal, and determining whether there is a cloud signal. If there is a cloud signal, determining the cloud base height, cloud thickness, and cloud number; Step S52, counting the number of echo signals containing cloud signals in the entire scanning cycle data, and comparing it with the number of echo signals in the entire scanning cycle, to obtain the cloud score in the entire scanning cycle, which is used to indicate the cloud coverage ratio in the sky in the entire scanning cycle; Step S53, extracting the cloud base height corresponding to the echo signal in the intercepted data set, and calculating the average of all cloud base heights in the key area; wherein, if there are multiple layers of clouds in the key area, the cloud base height of the lowest layer is taken as the representative value of the cloud base height in the area; Step S54, extracting the mean value of the cloud thickness in the key area; wherein, if there are multiple layers of clouds in the key area, the thickness of each layer of clouds is accumulated to obtain the total cloud thickness; Step S55, counting the number of cloud layers obtained by inverting the echo signals in the key area, analyzing the mode of the number of cloud layers in the area, and using this to characterize the number of cloud layers in the area; Step S56, counting the number of echo signals containing cloud signals in the key area, and comparing it with the number of echo signals in the entire key area, to obtain a regional cloud score in the key area.

9. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on a single-photon laser radar according to claim 8, characterized in that: The meteorological information in step S6 includes temperature, relative humidity, air pressure, and wind speed.

10. The method for predicting ultra-short-term irradiation of a photovoltaic power station based on single-photon laser radar according to claim 8, characterized in that: The CNN-LSTM model in step S7 includes an input layer, a convolutional layer, a pooling layer, an LSTM layer, a fully connected layer and an output layer.

Images