Photovoltaic cluster power day-ahead prediction method considering turning meteorological process identification

Abstract

The invention discloses a photovoltaic cluster power day-ahead prediction method considering turning meteorological process identification, and relates to the technical field of photovoltaic power prediction. The method comprises the following steps: carrying out weather judgment on generated power by utilizing a self-adaptive filtering method and a coding convolution scoring method, determining that the current weather of a target day is sudden change weather or sunny weather, and constructing a corresponding weather prediction model according to the weather condition, and constructing a photovoltaic cluster power day-ahead prediction model with a meteorological process and turning time point dual identification function based on the two models, and performing photovoltaic cluster power generation power prediction by using the photovoltaic cluster power day-ahead prediction model. According to the method, the turning and sudden change of weather can be taken into consideration, so that the prediction precision and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power prediction, and in particular to a photovoltaic cluster power day-ahead prediction method taking into account the identification of transition meteorological processes. Background Art

[0002] In recent years, China's new energy industry is booming. As a clean energy source, photovoltaic power generation has an output power that is significantly affected by weather conditions, especially changes in cloud cover, and is intermittent and uncertain. However, photovoltaic power prediction has limitations in obtaining high-quality data, accurately describing meteorological factors, accurately tracking and predicting cloud trajectories, and optimizing models. This characteristic poses challenges to the stable operation of the power system, and also places higher demands on the regulation capabilities of the power system. With a high proportion of new energy connected to the power system, the stable operation of the power system faces huge challenges. High-precision power prediction helps to improve the photovoltaic power generation capacity, adjust the power generation plan, and ensure the safe operation of the power system.

[0003] Although the PV power output has obvious periodicity, researchers tend to divide the data into daily units to facilitate the construction and analysis of prediction models, but this method does not fully take into account the nonlinearity and irregularity of weather changes. Weather changes do not always follow the daily cycle pattern, but are affected by a variety of factors, which vary in complexity in different regions. Therefore, the current prediction accuracy and reliability of PV power are insufficient. Summary of the invention

[0004] The purpose of the present invention is to provide a photovoltaic cluster power day-ahead prediction method taking into account the identification of transition meteorological processes, so as to improve the prediction accuracy and reliability by taking the transition and mutation of weather into consideration.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A photovoltaic cluster power day-ahead prediction method taking into account the identification of transition meteorological processes comprises:

[0007] Obtaining the power generation on the target day; the power generation includes a trend component and a fluctuation component;

[0008] Using an adaptive filtering method and a coded convolution scoring method to perform weather discrimination on the power generation, determining whether the current weather on the target day is sudden weather or sunny weather;

[0009] When the current weather of the target day is a sudden change weather, the turning point evaluation method is used to identify the sudden change point: if there is a sudden change point, a sudden change weather prediction model is constructed according to the sudden change characteristics of the earliest sudden change point; if there is no sudden change point, the current weather is regarded as sunny weather;

[0010] When the current weather on the target day is sunny, a non-mutational weather prediction model is constructed according to the static characteristics of the geographical location;

[0011] Based on the sudden weather prediction model and the non-sudden weather prediction model, a photovoltaic cluster power day-ahead prediction model with dual identification functions of meteorological process and turning point is constructed, and the photovoltaic cluster power day-ahead prediction model is used to predict the power generation power of the photovoltaic cluster.

[0012] Optionally, the method of using an adaptive filtering method and a coded convolution scoring method to perform weather discrimination on the photovoltaic power to determine whether the current weather on the target day is sudden change weather or sunny weather specifically includes:

[0013] Extracting the trend component and the fluctuation component of the generated power by using an adaptive filtering method;

[0014] The coded convolution scoring method is used to quantitatively score each component to obtain a trend component score and a fluctuation component score;

[0015] Cluster analysis is performed on each volatility score using the boundary optimization method to determine the key feature thresholds of NWP data; the key features of NWP data include the maximum daily rainfall, the maximum daily cloud cover, and the daily change in cloud cover;

[0016] Weather forecast is performed based on the key feature threshold of the NWP data to determine whether the current weather is sudden change weather or sunny weather.

[0017] Optionally, the calculation process of the adaptive filtering method includes:

[0018] Based on the power generation, the window width is increased for the period with large fluctuation frequency but smooth fluctuation trend, and the window width is reduced for the period with turning fluctuation trend, wherein the filtering formula is:

[0019]

[0020] In the formula, x n+1 (i) is the i-th value of the n+1-th filtering sequence, and the mean is calculated under the window of (id(i),i+d(i)); 2d(i)+1 is the filtering window corresponding to the i-th sequence value; x(j) is the j-th value of the filtering sequence;

[0021] Since the window length affects the degree of fluctuation of the filtered sequence, and the intensity of the sequence fluctuation is measured by difference, the adjustment length of the window is calculated using the following formula:

[0022] Δd n+1 (i) = int(kD(x n (i),2))

[0023] d n+1 (i) = Δd n (i)+d n (i)

[0024] Where D(·) is the second-order difference function; k is the adjustment coefficient; int() is the rounding function; Δd n (i) is the i-th value of the window correction value sequence after the n-th filtering; d n (i) is the i-th value of the window sequence filtered for the nth time.

[0025] Optionally, the method of using the boundary optimization method to perform cluster analysis on each fluctuation score to determine the key feature threshold of the NWP data includes:

[0026] The boundary optimization method is used to perform cluster analysis on each volatility score, and the upper quartiles of the daily maximum rainfall and the daily maximum cloud cover are used as corresponding thresholds, and the quartiles of the daily variation of cloud cover are used as corresponding thresholds.

[0027] Optionally, the calculation process of the turning point evaluation method includes:

[0028] Based on the turning score definition formula, the curvature of the fitting circle of the three data points is calculated to determine the degree of folding of the time series data points; wherein the turning score definition formula is:

[0029]

[0030] In the formula, (x center (i),y center (i)) is the coordinate of the center of the circle; xi is the i-th horizontal coordinate; yi is the i-th vertical coordinate.

[0031] Optionally, the calculation formula of the circle center coordinates is:

[0032]

[0033]

[0034] Where Δx kk≠j is the difference between the horizontal coordinates of the other two points except j, Δy kk≠j is the difference between the ordinates of the other two points except j; j is the jth horizontal coordinate; y j is the jth ordinate.

[0035] Optionally, when the current weather on the target day is a sudden change weather, a turning point evaluation method is used to identify the sudden change point, and the specific process includes:

[0036] When the current weather on the target day is a sudden change, the ideal power generation period is determined according to the radiation duration, and each power generation period is evenly divided into three equal parts;

[0037] In each of the parts, a turning point evaluation method is used to identify mutation points. When a mutation point exists, the earliest mutation point is used as the mutation point of the photovoltaic cluster, and the trend correlation is calculated according to the time period divided by the turning point. The trend correlation is used as a mutation feature to construct a mutation weather prediction model.

[0038] Optionally, the sudden weather prediction model, the non-sudden weather prediction model and the photovoltaic cluster power day-ahead prediction model all adopt graph convolutional neural networks.

[0039] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0040] The present invention discloses a photovoltaic cluster power day-ahead prediction method taking into account the identification of a turning meteorological process. The method comprises using an adaptive filtering method and a coded convolution scoring method to perform weather discrimination on the power generation, determining whether the current weather on the target day is sudden change weather or sunny weather, constructing a corresponding weather prediction model according to the weather conditions, and constructing a photovoltaic cluster power day-ahead prediction model with dual identification functions of meteorological processes and turning points based on the above two models, and using the photovoltaic cluster power day-ahead prediction model to predict the power generation of the photovoltaic cluster.

[0041] The present invention not only focuses on the transition of weather types within a day, but also pays special attention to the change in the degree of mutation under severe weather conditions. The weather discrimination mechanism of determining the key feature threshold through the inversion method enables the model to fully learn two different weather modes, thereby avoiding the loss of accuracy in the case of sudden changes in weather types. Therefore, the present invention can improve the prediction accuracy and reliability by taking the turning and mutation of weather into consideration. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 This is a flow chart of the weather discrimination mechanism for determining the key feature threshold using the inversion method in this embodiment;

[0044] Figure 2 Construct a weather recognition prediction comparison chart for the static chart in this embodiment;

[0045] Figure 3 Construct a weather recognition prediction comparison chart for the dynamic chart in this embodiment;

[0046] Figure 4 This is a power transition identification display diagram in this embodiment;

[0047] Figure 5 This is a comparison chart of the graph update prediction based on turning point identification in this embodiment; wherein, part (a) is sunny weather; part (b) is cloudy weather; part (c) is overcast weather; and part (d) is rainy weather;

[0048] Figure 6 This is a comparison chart of sunny day prediction in this embodiment;

[0049] Figure 7 This is a comparison chart of the overall method and common methods in this embodiment;

[0050] Figure 8 Schematic diagram of the logic flow of the photovoltaic cluster power day-ahead prediction method taking into account the identification of the transition meteorological process in this embodiment. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0052] The purpose of the present invention is to provide a photovoltaic cluster power day-ahead prediction method taking into account the identification of transition meteorological processes, so as to improve the prediction accuracy and reliability by taking the transition and mutation of weather into consideration.

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] like Figure 1-Figure 8 As shown, the present invention provides a photovoltaic cluster power day-ahead prediction method taking into account the identification of transition meteorological processes, comprising:

[0055] The generated power on the target day is obtained; the generated power includes a trend component and a fluctuation component.

[0056] The weather discrimination of the power generation is performed using an adaptive filtering method and a coding convolution scoring method to determine whether the current weather on the target day is sudden change weather or sunny weather.

[0057] When the current weather on the target day is sudden change weather, the turning point evaluation method is used to identify the sudden change point: if there is a sudden change point, a sudden change weather prediction model is constructed according to the sudden change characteristics of the earliest sudden change point; if there is no sudden change point, the current weather is regarded as sunny weather.

[0058] When the current weather on the target day is sunny, a non-mutational weather prediction model is constructed according to the static characteristics of the geographical location.

[0059] Based on the sudden weather prediction model and the non-sudden weather prediction model, a photovoltaic cluster power day-ahead prediction model with dual identification functions of meteorological process and turning point is constructed, and the photovoltaic cluster power day-ahead prediction model is used to predict the power generation power of the photovoltaic cluster.

[0060] As a specific implementation of the above steps, the following steps are provided:

[0061] 1) Weather classification method considering adaptive filtering and coded convolution scoring

[0062] In order to adapt to the power mutation situation, an adaptive filtering method is proposed to extract the trend component and fluctuation component of each day. For the period with large fluctuation frequency but smooth fluctuation trend, the window width should be increased, while for the turning section of fluctuation trend, the window width should be appropriately reduced to avoid turning point offset. The filtering formula (1) is:

[0063]

[0064] In the formula, x n+1 (i) is the i-th value of the n+1-th filtering sequence, and the mean is calculated under the window of (id(i),i+d(i)); 2d(i)+1 is the filtering window corresponding to the i-th sequence value; x(j) is the j-th value of the filtering sequence;

[0065] The window length affects the fluctuation degree of the sequence after filtering. The fluctuation intensity of the sequence can be measured by difference, so the adjustment of the window length can be reasonably adjusted by difference. Δd is the adjustment length calculated by formula (2):

[0066] Δd n+1 (i) = int(kD(x n (i),2)) (2)

[0067] d n+1 (i) = Δd n (i)+d n (i) (3)

[0068] Where D(·) is the second-order difference function; k is the adjustment coefficient; int() is the rounding function; Δd n(i) is the i-th value of the window correction value sequence after the n-th filtering; d n (i) is the ith value of the window sequence after the nth filtering. Through multiple iterations, the window length is continuously adjusted to reduce the number of changes in trend coding and the deviation value of peak and valley time points.

[0069] 2) Inversion method to determine the key characteristic thresholds of NWP for clear and cloudy sky

[0070] Firstly, the trend component and fluctuation component of daily power generation are extracted through adaptive filtering. Then, a convolutional fluctuation scoring method with an embedded coding mechanism is proposed to quantitatively analyze the volatility of power generation, and then the trend component score and the fluctuation component score are obtained. Finally, the boundary optimization method is applied to cluster the three key features, so as to accurately divide different weather types.

[0071] Three key features are extracted from NWP data: daily maximum rainfall, daily maximum cloud cover, and daily change in cloud cover. The quartile-based threshold setting method is selected to calculate the feature threshold from each type of data after weather classification. Specifically, the upper quartile of each key feature is used as the threshold. Given that cloud cover fluctuation is a key indicator for identifying anomalies in sunny day classification, the threshold for cloud cover change is set to the quartile. These feature thresholds are used to predict whether the weather is sunny.

[0072] 3) Mutation point identification method under non-clear sky conditions

[0073] At the atmospheric level, NWP changes relatively slowly. As NWP has a high sensitivity in identifying transitional weather processes, a transition evaluation method for discrete sequence points is proposed to measure the degree to which the sequence deviates from the straight line in a local area. The transition score is defined as formula (4):

[0074]

[0075] The curvature of the fitted circle of three data points is calculated to measure the degree of folding of the time series data points. center (i),y center (i)) is the coordinate of the center of the circle, and the calculation formula is:

[0076]

[0077] Where Δx kk≠j is the difference between the horizontal coordinates of the other two points except j, Δy kk≠j is the difference between the ordinates of the other two points except j; j is the jth horizontal coordinate; y j is the jth ordinate.

[0078] 4) Dynamic graph construction method based on mutation point switching

[0079] Select NWP search features according to step 1) and step 2), and judge sudden weather changes based on key feature threshold standards.

[0080] For sudden weather changes, the ideal power generation period is determined by analyzing the radiation duration, and these periods are evenly divided into three equal parts. For each part, the earliest mutation point in the photovoltaic cluster is searched according to step 3) as the mutation point of the cluster. The trend correlation is calculated according to the time period divided by the turning point, and the correlation is used as the mutation feature to build a prediction model.

[0081] If no turning point can be identified, a forecast model is constructed based on the static characteristics of the geographic location.

[0082] For non-mutated weather, a prediction model will be constructed based on the static characteristics of the geographical location.

[0083] 5) Simulation calculation

[0084] Simulation input: Analyze the measured data of the electric field to determine the total installed capacity of the electric field; the rated capacity of each photovoltaic field; numerical weather forecasts of irradiance, rainfall, cloudiness, humidity, and air pressure; the data sampling interval is 15 minutes; according to steps 1) to 4), obtain the real-time prediction results of the photovoltaic power of the whole field;

[0085] 6) Error analysis

[0086] Let P Mi is the actual average power in period i, P Pi is the predicted average power of time period i, N is the total time period of daily assessment, P cap is the wind farm startup capacity. Then, the normalized root mean square error is defined as formula (6):

[0087]

[0088] The coefficient of determination is defined as formula (7):

[0089]

[0090] According to step 5), input the simulation input quantity, and calculate the error between the predicted power calculated by the model and the measured power through the error evaluation standard formula (5), formula (6), and formula (7) in step 6) to obtain the prediction accuracy.

[0091] Based on the above technical solution, the following embodiments are provided.

[0092] In this embodiment, the method mainly includes the following steps: 1) extracting historical power fluctuation characteristics through fluctuation characteristics based on adaptive filtering, accurately dividing weather, and analyzing the difference in meteorological data between clear weather and sudden change weather; 2) extracting key features using NWP data such as rainfall and cloud cover, determining key feature thresholds through inversion method, and identifying clear weather and sudden change weather; 3) under sudden change weather, selecting NWP search features, dividing multi-period search intervals, and searching for turning points in each interval; 4) constructing a sudden change weather prediction model based on a dynamic switching diagram for turning point identification; 5) constructing a clear weather prediction model based on a static geographic distance map. 6) Finally, a photovoltaic power prediction model based on dual identification of meteorological processes and turning points is established.

[0093] Specifically:

[0094] In order to maximize the prediction accuracy of photovoltaic power, this paper mainly selects multiple prediction models to predict the photovoltaic power of the test set. The power data of a photovoltaic cluster in Jilin and NWP irradiance, rainfall, cloud cover, humidity, and air pressure are used for experimental analysis. The time resolution is 15min and the total installed capacity is 534.914MW. The data time is from 00:00 on January 2, 2019 to 23:45 on July 1, 2019, of which the data from January to May are used as the training set and the data in June are used as the test set.

[0095] Step 1: Fluctuation feature extraction and weather classification method based on adaptive window filtering. Figure 1 As shown in the figure, the trend component and fluctuation component of daily power generation are extracted by adaptive window filtering, and the volatility of power generation is quantitatively analyzed by the convolutional fluctuation scoring method with an embedded coding mechanism, thereby obtaining the trend component score and the fluctuation component score. The boundary optimization method is applied to cluster the three key features, so as to accurately divide different weather types;

[0096] Step 2: The inversion method is used to determine the key feature thresholds to distinguish weather types. The NWP data of clear weather is analyzed and three key features are extracted: daily maximum rainfall, daily maximum cloud cover and daily change in cloud cover. The quartile-based threshold setting method is selected to calculate the feature thresholds from each type of data after weather classification. Specifically, the upper quartile of each key feature is used as the threshold. In view of the fact that cloud cover fluctuations are the key indicator for identifying anomalies in sunny day classification, the threshold for cloud cover change is set to the quartile. These feature thresholds are used to predict whether the weather is clear. When the value of any feature exceeds the preset threshold range, it is considered to be a sudden change in weather;

[0097] This example compares two models: one is an adjacency matrix constructed under static geographical location conditions (model 1), and the other is a daily adjacency matrix dynamically updated based on NWP regional division (model 2). These two models verify the effectiveness of weather identification in forecasting.

[0098] Table 1 Forecast error evaluation indexes for weather identification effectiveness

[0099]

[0100] like Figure 2 As shown in Figure 3, it can be seen that in the case of bad weather and significant sudden changes in power generation, the prediction effect of the static model often cannot keep up with the changes in actual power. When performing power forecasting under the dynamic model, the overall prediction effect is much better than the static one. Since the daily update of the adjacency matrix may effectively identify the weather similarity between power plants every day, the improvement of the weather forecast effect is not significant. As shown in Table 1, the accuracy MAE of weather recognition prediction in both cases is reduced by 0.3% on average. By comparing these methods, it is proved that the prediction model with weather type recognition is more excellent in prediction effect.

[0101] Step 3: Identification of the turning point of sudden weather changes. Changes in the local meteorological environment are not always based on a daily cycle, but are affected by the geographical location and show varying degrees of complexity. When considering meteorological conditions, the turning point of the weather must be taken into consideration. First, select NWP search features. The key NWP features are different in different weather conditions. For example, during rainfall, the absolute value and change value of rainfall are much greater than other features for judging the location of the mutation point, while on cloudy or overcast days, cloud cover dominates. Therefore, according to the key feature threshold standard, which key feature exceeds the threshold will be used as the mutation point judgment feature (rainfall is the highest priority, cloud cover is the second priority); then, divide the search interval into multiple time periods. This study determined the ideal power generation period by analyzing the radiation duration, and evenly divided these periods into four equal parts.

[0102] Finally, the turning point is identified in each search interval. The curvature of each time point of all stations is calculated in each search period based on the trend component of each key feature. The maximum curvature of each photovoltaic power station is taken as the mutation point, and the earliest mutation point in the photovoltaic cluster is the mutation point of the cluster. Figure 4 As shown, the mutation period of a certain day in the test set is divided into four periods (ad), which are relatively accurate.

[0103] Consider the case where there is no turning point in the search interval. If no turning point is identified in a certain search interval, it means that there is no significant weather change in that period. For such a period, the prediction model will be built based on the static characteristics of the geographical location. This method ensures that those periods with little change in power generation can be accurately identified and processed, thereby improving the accuracy and efficiency of the prediction;

[0104] Step 4: Construct a sudden weather prediction model based on a dynamic switching graph for turning point identification. In the prediction of changing weather, a graph convolutional neural network (GCN) method can be used to extract similarities between weather patterns by analyzing fluctuations in NWP data. Use these similarity measures to construct links between graph nodes and assign weights to these links. In order to adapt to the intraday mutations of the weather, the division of regions is updated every day, and the moments when mutations occur are identified. After identifying these moments, the degree of connectivity between regions is updated accordingly, and the local adjacency matrix and weights are adjusted.

[0105] According to step 3, the main features for identification are selected. The fluctuation of the main feature data of NWP of each photovoltaic field is extracted by adaptive window filtering. The trend correlation is calculated according to the time period divided by the turning point. This correlation analysis will be used as the weight for constructing the connection matrix.

[0106] As shown in Table 2, under the most severe meteorological conditions, the forecast model uses three different construction methods: one is the construction of a static adjacency matrix based on geographic location (method 1); the second is a dynamic composition that is updated daily based on NWP data clustering (method 2); and the third is a dynamic composition that is locally updated when a weather turning point is identified (method 3).

[0107] Table 2 Error evaluation table of prediction models constructed with different graphs

[0108]

[0109] like Figure 5 As shown in the figure, the prediction curve updated based on the NWP turning identification diagram can effectively track the mutations and turning points of the actual power curve. Since the adjacency matrix constructed statically based on the geographical location cannot capture the dynamic changes of daily meteorology, the prediction results of method 1 are poor. On the other hand, although the adjacency matrix construction method based on NWP data clustering and daily updates has certain adaptability in dealing with daily meteorological changes, its prediction model still shows certain limitations when dealing with sharp turns and mutations in the weather. Therefore, through this method of identifying turning points, the turning point of power generation can be captured more accurately, thereby optimizing the prediction model of the photovoltaic power generation system.

[0110] Step 5: Build a clear weather prediction model based on a static geographic distance map. After smoothing the trained power data through adaptive window filtering, the prediction accuracy can be significantly improved as input data for training. Under clear weather conditions, due to the small fluctuations, it is easier to enhance the training effect of the model by filtering out noise and interference information, thereby ensuring the accuracy and reliability of the prediction results.

[0111] Table 3 Sunny day prediction error evaluation table

[0112]

[0113] like Figure 6 As shown in Table 3, the prediction accuracy after input data preprocessing is very high. During training and prediction, the peak value of the unprocessed raw data deviates from the actual observed data and cannot accurately capture the peak value changes of the real data.

[0114] Step 6: Establish a photovoltaic power prediction model based on dual identification of meteorological processes and turning points, and compare it with existing methods to verify the effectiveness of the overall method. The most commonly used prediction methods: Overall prediction (Method 1): The power is added and predicted, and the output of training and testing is the overall power; Cumulative prediction (Method 2): Single station prediction, and then superimposed predicted power. Methods 1 and 2 are used for the most basic comparison to prove the effectiveness of existing methods. As well as prediction methods that consider weather scenarios and weather identification, Method 3: Cluster analysis is performed on daily NWP data to distinguish different weather types, and a special prediction model is built for each weather type. The model selects the most appropriate prediction model for weather identification and prediction by analyzing the cluster center of NWP data. Method 4: A weather division method based on historical power data is used to establish targeted prediction models for different weather conditions, realizing the scenario-based prediction of photovoltaic power. Method 5: Clustering is performed based on the extracted power fluctuation characteristics to distinguish different weather types, and a special prediction model is established for each category. As Figure 7 As shown, the prediction results of different methods for several consecutive days are shown, and the prediction results under various weather conditions are shown in detail. The method proposed in this embodiment can perform stably and well under various weather conditions, and the prediction results are closely aligned with the trend of the actual data. The predicted power fluctuations of Method 3 and Method 5 are roughly consistent with the actual situation, but they do not closely match the actual power. This shows that the model has preliminarily learned the characteristics under different weather conditions, but the learning and recognition of these characteristics are not deep enough, and the model shows instability in learning and recognizing the characteristics under different weather conditions.

[0115] Table 4 Error evaluation table of each prediction method

[0116]

[0117] As shown in Table 4, the prediction methods that do not consider similar day and weather identification are not effective because these methods do not take into account the uniqueness of each photovoltaic field and the differences in characteristics under different weather conditions. In contrast, the method of establishing a prediction model based on different scenarios has significantly improved the effect. Compared with the other five methods, MAE and RMSE decreased by 4.96% and 7.15% on average, and R2 increased by 23.8% on average, which proves the effectiveness of the method of the present invention.

[0118] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0119] In this embodiment, specific examples are used to illustrate the principle and implementation of the present invention. The above description of the embodiment is only used to help understand the core idea of ​​the present invention; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes, characterized in that: include: Obtaining the power generation on the target day; the power generation includes a trend component and a fluctuation component; Using an adaptive filtering method and a coded convolution scoring method to perform weather discrimination on the power generation, determining whether the current weather on the target day is sudden weather or sunny weather; When the current weather of the target day is a sudden change weather, the turning point evaluation method is used to identify the sudden change point: if there is a sudden change point, a sudden change weather prediction model is constructed according to the sudden change characteristics of the earliest sudden change point; if there is no sudden change point, the current weather is regarded as sunny weather; When the current weather on the target day is sunny, a non-mutational weather prediction model is constructed according to the static characteristics of the geographical location; Based on the sudden weather prediction model and the non-sudden weather prediction model, a photovoltaic cluster power day-ahead prediction model with dual identification functions of meteorological process and turning point is constructed, and the photovoltaic cluster power day-ahead prediction model is used to predict the power generation power of the photovoltaic cluster.

2. The photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes according to claim 1 is characterized in that: The method of using the adaptive filtering method and the coding convolution scoring method to perform weather discrimination on the photovoltaic power to determine whether the current weather on the target day is sudden weather or sunny weather includes: Extracting the trend component and the fluctuation component of the generated power by using an adaptive filtering method; The coded convolution scoring method is used to quantitatively score each component to obtain a trend component score and a fluctuation component score; Cluster analysis is performed on each volatility score using the boundary optimization method to determine the key feature thresholds of NWP data; the key features of NWP data include the maximum daily rainfall, the maximum daily cloud cover, and the daily change in cloud cover; Weather forecast is performed based on the key feature threshold of the NWP data to determine whether the current weather is sudden change weather or sunny weather.

3. The photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes according to claim 2 is characterized in that: The calculation process of the adaptive filtering method includes: Based on the power generation, the window width is increased for the period with large fluctuation frequency but smooth fluctuation trend, and the window width is reduced for the period with turning fluctuation trend, wherein the filtering formula is: In the formula, x n+1 (i) is the i-th value of the n+1-th filtering sequence, and the mean is calculated under the window of (id(i),i+d(i)); 2d(i)+1 is the filtering window corresponding to the i-th sequence value; x(j) is the j-th value of the filtering sequence; Since the window length affects the degree of fluctuation of the filtered sequence, and the intensity of the sequence fluctuation is measured by difference, the adjustment length of the window is calculated using the following formula: Δd n+1 (i)=int(kD(x n (i),2)) d n+1 (i)=Δd n (i)+d n (i) Where D(·) is the second-order difference function; k is the adjustment coefficient; int() is the rounding function; Δd n (i) is the i-th value of the window correction value sequence after the n-th filtering; d n (i) is the i-th value of the window sequence filtered for the nth time.

4. The photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes according to claim 2 is characterized in that: The method of using boundary optimization to cluster the fluctuation scores and determine the key characteristic thresholds of NWP data includes: The boundary optimization method is used to perform cluster analysis on each volatility score, and the upper quartiles of the daily maximum rainfall and the daily maximum cloud cover are used as corresponding thresholds, and the quartiles of the daily variation of cloud cover are used as corresponding thresholds.

5. The photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes according to claim 1 is characterized in that: The calculation process of the turning point evaluation method includes: Based on the turning score definition formula, the curvature of the fitting circle of the three data points is calculated to determine the degree of folding of the time series data points; wherein the turning score definition formula is: In the formula, (x center (i),y center (i)) is the coordinate of the center of the circle; xi is the i-th horizontal coordinate; yi is the i-th vertical coordinate.

6. The photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes according to claim 5 is characterized in that: The calculation formula of the center coordinates is: Where Δx kk≠j is the difference between the horizontal coordinates of the other two points except j, Δy kk≠j is the difference between the ordinates of the other two points except j; j is the jth horizontal coordinate; y j is the jth ordinate.

7. The photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes according to claim 1 is characterized in that: When the current weather on the target day is a sudden change, the sudden change point is identified using the turning point evaluation method. The specific process includes: When the current weather on the target day is a sudden change, the ideal power generation period is determined according to the radiation duration, and each power generation period is evenly divided into three equal parts; In each of the parts, a turning point evaluation method is used to identify mutation points. When a mutation point exists, the earliest mutation point is used as the mutation point of the photovoltaic cluster, and the trend correlation is calculated according to the time period divided by the turning point. The trend correlation is used as a mutation feature to construct a mutation weather prediction model.

8. The photovoltaic cluster power day-ahead prediction method taking into account the identification of transitional meteorological processes according to claim 1 is characterized in that: The sudden weather prediction model, the non-sudden weather prediction model and the photovoltaic cluster power day-ahead prediction model all adopt graph convolutional neural networks.

Images