AI-based new energy power generation power prediction system and method

Abstract

The invention relates to the field of generation power prediction, in particular to a new energy generation power prediction system and method based on AI. The method comprises the following steps: dividing a photovoltaic power supply period, and determining a predicted radiation quantity curve of a next period based on predicted meteorological data and the position of a photovoltaic power supply; correcting the predicted radiation quantity curve to obtain a corrected predicted radiation quantity curve; obtaining a temperature prediction change curve, and obtaining a predicted photovoltaic power supply feed-in power curve based on the temperature prediction change curve and the corrected predicted radiation quantity curve; calculating the predicted feed-in power of the wind power supply at each moment to obtain a predicted wind power supply feed-in power curve; and based on the predicted photovoltaic power supply feed-in power curve, the predicted wind power supply feed-in power curve and the real-time feed-in power, adjusting a hydrogen energy storage strategy.

Description

Technical Field

[0001] The present application relates to the field of power generation prediction, and specifically to a new energy power generation prediction system and method based on AI. Background Art

[0002] In the context of the global promotion of sustainable energy development, the proportion of renewable energy power generation in the energy structure is increasing. However, renewable energy power generation such as solar and wind power has significant intermittent and volatile characteristics, which brings many challenges to the stable operation and efficient management of the power system. Therefore, accurate prediction of power generation is crucial to ensure the safe and stable operation of the power grid.

[0003] In this regard, patent CN115441447B proposes a new energy power generation prediction method. The solution combines meteorological forecasts with real-time cloud image analysis to predict the radiation of photovoltaic power sources on a periodic basis and adjust the radiation curve to accurately predict the feed-in power. At the same time, the wind power generation curve is predicted by predicting wind conditions and temperature changes. Finally, based on the predictions of photovoltaic and wind power and the actual feed-in power, the hydrogen energy storage strategy is optimized to improve the accuracy and reliability of new energy power generation predictions.

[0004] The prediction of wind power curve in this patent is achieved through common machine learning algorithms, such as convolutional neural networks. CNN is mainly used to deal with local pattern recognition problems in two-dimensional or three-dimensional space. When dealing with multi-dimensional time series data such as wind speed and wind direction, it may not be able to effectively capture the complex interactive relationship between different dimensions, and it is difficult to establish effective time series dependencies between different time points, thus affecting the accuracy of the prediction.

[0005] Therefore, an optimized renewable energy power generation prediction scheme is desired. Summary of the invention

[0006] This application is made in consideration of the above problems. One purpose of this application is to provide a new energy power generation power prediction system and method based on AI.

[0007] The embodiment of the present application provides a method for predicting power generation of renewable energy based on AI, including: dividing a photovoltaic power supply cycle, and determining a predicted radiation amount curve for the next cycle based on predicted meteorological data and the location of the photovoltaic power supply; correcting the predicted radiation amount curve to obtain a corrected predicted radiation amount curve; obtaining a temperature prediction change curve, and obtaining a predicted photovoltaic power supply feed-in power curve based on the temperature prediction change curve and the corrected predicted radiation amount curve; calculating the predicted feed-in power of a wind power supply at each moment to obtain a predicted wind power supply feed-in power curve; adjusting a hydrogen energy storage strategy based on the predicted photovoltaic power supply feed-in power curve, the predicted wind power supply feed-in power curve and the real-time feed-in power; wherein, calculating the predicted feed-in power of a wind power supply at each moment to obtain a predicted wind power supply feed-in power curve includes: Acquire the predicted wind condition time series parameters of the location where the wind power source is located, and acquire the predicted temperature time series parameters of the location where the wind power source is located, wherein the predicted wind condition time series parameters include wind speed time series parameters and wind direction angle time series parameters; Performing direction field calculation and feature extraction on the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter respectively to obtain wind speed time series direction field features, wind direction angle time series direction field features and predicted temperature time series direction field features; Performing interactive fusion of wind condition multi-dimensional time series features on the wind speed time series direction field features and the wind direction angle time series direction field features to obtain an interactive representation of wind condition multi-dimensional time series features; The principal component-guided feature compensation interaction is performed on the multi-dimensional time series feature interaction representation of the wind condition and the predicted temperature time series directional field feature to obtain the wind condition-temperature time series directional field compensation interaction feature, and based on the wind condition-temperature time series directional field compensation interaction feature, the wind power feed-in power value at the next moment is obtained.

[0008] For example, according to the AI-based renewable energy power generation prediction method of an embodiment of the present application, the wind speed time series parameters, the wind direction angle time series parameters, and the predicted temperature time series parameters are respectively subjected to direction field calculation and feature extraction to obtain wind speed time series direction field features, wind direction angle time series direction field features, and predicted temperature time series direction field features, including: Calculating the direction fields of the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter respectively to obtain a wind speed time series direction field diagram representation, a wind direction angle time series direction field diagram representation and a predicted temperature time series direction field diagram representation; The wind speed time series directional field map representation, the wind direction angle time series directional field map representation and the predicted temperature time series directional field map representation are respectively passed through a directional field feature extractor based on an expanded convolutional neural network to obtain a wind speed time series directional field feature vector as the wind speed time series directional field feature, a wind direction angle time series directional field feature vector as the wind direction angle time series directional field feature and a predicted temperature time series directional field feature vector as the predicted temperature time series directional field feature.

[0009] For example, according to the AI-based renewable energy power prediction method of the embodiment of the present application, the wind speed time series direction field characteristics and the wind direction angle time series direction field characteristics are interactively fused with multi-dimensional time series characteristics of wind conditions to obtain a multi-dimensional time series feature interactive representation of wind conditions, including: passing the wind speed time series direction field feature vector and the wind direction angle time series direction field feature vector through a wind condition multi-dimensional time series feature interactive fusion device based on an X-linear attention bilinear pooling unit to obtain a wind condition multi-dimensional time series feature interactive representation vector as the wind condition multi-dimensional time series feature interactive representation.

[0010] For example, according to the AI-based renewable energy power prediction method of the embodiment of the present application, the principal component-guided feature compensation interaction is performed on the multi-dimensional time series feature interactive representation of the wind condition and the predicted temperature time series direction field feature to obtain the wind condition-temperature time series direction field compensation interaction feature, and based on the wind condition-temperature time series direction field compensation interaction feature, the wind power feed-in power value at the next moment is obtained, including: Performing principal component-guided feature compensation interaction on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to obtain a wind condition-temperature time series direction field compensation interaction feature vector as the wind condition-temperature time series direction field compensation interaction feature; Based on the wind condition-temperature time series direction field compensation interactive characteristic vector, the wind power source feed-in power value at the next moment is obtained.

[0011] For example, according to the AI-based new energy power generation prediction method of an embodiment of the present application, the principal component-guided feature compensation interaction is performed on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to obtain the wind condition-temperature time series direction field compensation interaction feature vector, including: Performing feature principal component analysis on the wind condition multidimensional time series feature interactive representation vector and the predicted temperature time series direction field feature vector to obtain a set of wind condition multidimensional time series feature principal component encoding vectors and a set of predicted temperature time series direction field feature principal component encoding vectors; Constructing the set of principal component coding vectors of the multi-dimensional time series characteristics of wind conditions and the set of principal component coding vectors of the predicted temperature time series direction field characteristics into a principal component aggregation coding feature map of the multi-dimensional time series characteristics of wind conditions and a principal component aggregation coding feature map of the predicted temperature time series characteristics; Calculate the wind condition-prediction temperature time series difference embedding compensation coding weight vector between the principal component aggregation coding feature map of the wind condition multi-dimensional time series feature and the principal component aggregation coding feature map of the predicted temperature time series feature; Based on the wind condition-predicted temperature time series difference embedded compensation coding weight vector, the set of principal component coding vectors of the wind condition multidimensional time series characteristics and the set of principal component coding vectors of the predicted temperature time series direction field characteristics are compensated and aggregated to obtain the wind condition-temperature time series direction field compensation interaction feature vector.

[0012] For example, according to the AI-based new energy power generation prediction method of an embodiment of the present application, the wind condition-prediction temperature time series difference embedding compensation coding weight vector between the principal component aggregation coding feature map of the wind condition multidimensional time series feature and the principal component aggregation coding feature map of the predicted temperature time series feature is calculated, including: Performing difference embedding processing on the principal component aggregation coding feature map of the multi-dimensional time series characteristics of the wind condition and the principal component aggregation coding feature map of the predicted temperature time series characteristics to obtain a wind condition multi-dimensional time series branch weight vector and a predicted temperature time series branch weight vector; The wind condition-predicted temperature timing difference embedding compensation coding weight vector between the wind condition multi-dimensional timing branch weight vector and the predicted temperature timing branch weight vector is calculated.

[0013] For example, according to the AI-based new energy power generation prediction method of the embodiment of the present application, based on the wind condition-predicted temperature time series difference embedding compensation coding weight vector, the set of the wind condition multidimensional time series feature principal component coding vector and the set of the predicted temperature time series direction field feature principal component coding vector are compensated and aggregated to obtain the wind condition-temperature time series direction field compensation interaction feature vector, including: Calculate the position mean vector of the set of principal component coding vectors of the multi-dimensional time series characteristics of the wind conditions and the set of principal component coding vectors of the predicted temperature time series direction field characteristics to obtain the principal component representation coding vector of the multi-dimensional time series of the wind conditions and the principal component representation coding vector of the predicted temperature time series; Based on the wind condition-predicted temperature time series difference embedding compensation coding weight vector, the wind condition multi-dimensional time series principal component characterization coding vector and the predicted temperature time series principal component characterization coding vector are aggregated and interacted to obtain the wind condition-temperature time series directional field compensation interaction feature vector.

[0014] For example, according to the AI-based renewable energy power prediction method of the embodiment of the present application, based on the wind condition-temperature time series direction field compensation interaction feature vector, the wind power feed-in power value at the next moment is obtained, including: passing the wind condition-temperature time series direction field compensation interaction feature vector through a decoder-based wind power predictor to obtain a wind power feed-in power decoding value as the wind power feed-in power value at the next moment.

[0015] The embodiment of the present application also provides an AI-based new energy power generation prediction system, including: A predicted radiation curve acquisition module is used to divide the photovoltaic power supply cycle and determine the predicted radiation curve of the next cycle based on the predicted meteorological data and the location of the photovoltaic power supply; A correction module, used for correcting the predicted radiation amount curve to obtain a corrected predicted radiation amount curve; A module for obtaining a predicted photovoltaic power supply feed-in power curve is used to obtain a predicted temperature change curve, and obtain a predicted photovoltaic power supply feed-in power curve based on the predicted temperature change curve and the corrected predicted radiation amount curve; A predicted feed-in power calculation module is used to calculate the predicted feed-in power of the wind power source at each moment to obtain a predicted wind power source feed-in power curve; A strategy adjustment module, used to adjust the hydrogen energy storage strategy based on the predicted photovoltaic power supply feed-in power curve, the predicted wind power supply feed-in power curve and the real-time feed-in power; wherein the strategy adjustment module includes: A timing parameter acquisition unit, used to acquire the predicted wind condition timing parameters of the location where the wind power source is located, and acquire the predicted temperature timing parameters of the location where the wind power source is located, wherein the predicted wind condition timing parameters include wind speed timing parameters and wind direction angle timing parameters; A feature extraction unit, used for performing directional field calculation and feature extraction on the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter to obtain wind speed time series directional field features, wind direction angle time series directional field features and predicted temperature time series directional field features; A multi-dimensional time series feature interactive fusion unit, used for interactively fusing the wind speed time series direction field feature and the wind direction angle time series direction field feature to obtain a wind condition multi-dimensional time series feature interactive representation; The wind power feed-in power value acquisition unit at the next moment is used to perform principal component-guided feature compensation interaction on the multi-dimensional time series feature interaction representation of the wind condition and the predicted temperature time series directional field feature to obtain the wind condition-temperature time series directional field compensation interaction feature, and obtain the wind power feed-in power value at the next moment based on the wind condition-temperature time series directional field compensation interaction feature.

[0016] For example, according to the AI-based new energy power generation prediction system based on AI in an embodiment of the present application, the feature extraction unit is used to: Calculating the direction fields of the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter respectively to obtain a wind speed time series direction field diagram representation, a wind direction angle time series direction field diagram representation and a predicted temperature time series direction field diagram representation; The wind speed time series directional field map representation, the wind direction angle time series directional field map representation and the predicted temperature time series directional field map representation are respectively passed through a directional field feature extractor based on an expanded convolutional neural network to obtain a wind speed time series directional field feature vector as the wind speed time series directional field feature, a wind direction angle time series directional field feature vector as the wind direction angle time series directional field feature and a predicted temperature time series directional field feature vector as the predicted temperature time series directional field feature.

[0017] According to the AI-based new energy power generation prediction method of the embodiment of the present application, it uses AI-based data analysis and prediction technology to perform directional field calculation and time series feature extraction on the predicted wind condition time series parameters and predicted temperature time series parameters, and then calculates the interactive representation information between the wind speed time series directional field characteristics and the wind direction angle time series directional field characteristics, so as to intelligently predict the wind power feed-in power value at the next moment based on the principal component-guided interactive representation between the multi-dimensional time series feature interactive representation of the wind condition and the predicted temperature time series directional field characteristics. Compared with traditional convolutional neural networks, the present application can better reflect the dynamic changes of wind conditions through directional field calculation and time series feature extraction. At the same time, it can establish a closer and more reasonable association between different time points, which helps to capture long-term historical dependencies and short-term dynamic changes, thereby improving prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0019] Figure 1 A flowchart of a method for predicting new energy power generation based on AI in an embodiment of the present application is shown; Figure 2 A flowchart of sub-step S140 of the AI-based new energy power generation prediction method in an embodiment of the present application is shown; Figure 3 A flowchart of sub-step S142 of the AI-based new energy power generation prediction method in an embodiment of the present application is shown; Figure 4A flowchart of sub-step S144 of the AI-based new energy power generation prediction method in an embodiment of the present application is shown; Figure 5 A flowchart showing sub-step S1441 of the AI-based new energy power generation prediction method in an embodiment of the present application is shown; and Figure 6 A schematic diagram of the structure of an AI-based renewable energy power generation prediction system in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0020] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.

[0021] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0022] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0024] refer to Figure 1As shown, the present application proposes a method for predicting power generation of renewable energy based on AI, including: S110, dividing the photovoltaic power supply cycle, and determining the predicted radiation curve of the next cycle based on the predicted meteorological data and the location of the photovoltaic power supply; S120, correcting the predicted radiation curve to obtain a corrected predicted radiation curve; S130, obtaining the temperature prediction change curve, and obtaining the predicted photovoltaic power supply feed-in power curve based on the temperature prediction change curve and the corrected predicted radiation curve; S140, calculating the predicted feed-in power of the wind power supply at each moment to obtain the predicted wind power supply feed-in power curve; S150, adjusting the hydrogen energy storage strategy based on the predicted photovoltaic power supply feed-in power curve, the predicted wind power supply feed-in power curve and the real-time feed-in power. In particular, in a specific example of the present application, the corrected predicted radiation curve can be corrected by a first cloud layer image obtained at the beginning of the next cycle and a second cloud layer image obtained after a set time interval.

[0025] It is worth mentioning that in the field of new energy, especially photovoltaic and wind power generation, accurate power forecasting is crucial to the stable operation of the power system. It helps grid operators optimize scheduling, improve the utilization of renewable energy and reduce the need for backup capacity. The AI-based new energy power generation power prediction method proposed in this application aims to provide a more accurate and intelligent prediction method through a series of steps, so as to better adapt to the characteristics of new energy with greater volatility. The premise of this prediction method is that the output power of photovoltaic power generation and wind power generation is closely related to natural conditions. The intensity and temperature of solar radiation affect the efficiency of photovoltaic panels, while the wind speed directly determines the power generation of wind turbines. Therefore, before formulating any prediction model, the influence of these factors must be considered.

[0026] Specifically, step S110 is to divide a day into several time periods, each of which corresponds to a specific lighting condition. For example, one can choose to use each hour as a cycle, and determine the amount of solar radiation that may be received in each hour in the future based on historical data and current seasonal changes, combined with predicted meteorological information. The "location" mentioned here refers not only to geographical coordinates, but also includes factors such as the angle and orientation of the photovoltaic panel, because they will also affect the final amount of radiation received.

[0027] After obtaining the preliminary predicted radiation curve, in step S120, the predicted radiation curve is corrected. The reason for the correction is that the original prediction may be affected by various uncertain factors, such as cloud cover or other instantaneous meteorological phenomena. In order to make the prediction closer to the actual situation, the prediction value can be automatically adjusted by introducing a machine learning algorithm and using similar situations in historical data as training samples. For example, if there is a brief cloud cover at noon on a certain day, but then it returns to clear weather, the system will learn this pattern and make appropriate corrections when encountering similar situations in the future. This method can significantly improve the accuracy of short-term predictions.

[0028] Once the corrected predicted radiation curve is ready, in step S130, it is combined with the temperature prediction change curve to calculate the expected photovoltaic power feed-in power curve. Temperature has a direct impact on the efficiency of photovoltaic cells: increased temperature leads to decreased conversion efficiency. Therefore, before generating the final predicted power curve, the temperature change trend must be taken into account. In actual operation, linear regression or other statistical methods can be used to establish a relationship model between temperature and power output. Once the temperature prediction curve is obtained, the expected power output at different temperatures can be calculated based on the model, thereby obtaining a complete predicted photovoltaic power feed-in power curve.

[0029] At the same time, for wind power generation, it is also necessary to predict its feed-in power at each moment. Accordingly, in step S140, the predicted feed-in power of the wind power source at each moment is calculated. Unlike photovoltaic power generation, which depends on solar radiation and temperature, wind power generation mainly depends on wind speed. Therefore, the focus of this stage is to collect historical records of local wind speeds and future forecast information. Modern meteorological services can usually provide relatively reliable short-term wind speed forecasts, which are very valuable resources for wind farms. By analyzing these data and combining them with the performance parameters of the wind turbine itself, a prediction model can be constructed to estimate the wind power output at different times. It is worth noting that with the advancement of wind turbine technology and control strategies, it is now possible to further improve the prediction accuracy by deep learning the real-time monitoring data of a single wind turbine.

[0030] Finally, based on all the above prediction results, i.e., the predicted feed-in power curves of photovoltaic power sources and wind power sources, plus the actual feed-in power monitored in real time, in step S150, the hydrogen energy storage strategy is adjusted. As an emerging energy storage method, hydrogen energy storage can convert electrical energy into hydrogen energy for storage when there is excess electricity, and release it to supplement the power grid when there is insufficient electricity. Therefore, it is crucial to rationally plan the charging and discharging plan of hydrogen energy storage to balance the supply and demand relationship. In terms of specific practices, a set of rules can be set or advanced algorithms such as reinforcement learning can be used to ensure that energy storage plays a role at the right time. For example, when there is plenty of sunshine and more wind power during the day, the excess electricity is used for hydrogen production first; at night or during windless periods, the stored hydrogen energy is released to maintain power supply stability. In addition, it is also possible to consider using it in conjunction with other types of energy storage facilities (such as lithium batteries) to jointly build a multi-level energy management system.

[0031] It should be understood that in calculating the predicted feed-in power of the wind power source at each moment to obtain the predicted wind power feed-in power curve, the technical concept of the present application is to obtain the predicted wind conditions (wind speed and wind direction angle) time series parameters at the location of the wind power source, and obtain the predicted temperature time series parameters at the location of the wind power source, and use AI-based data analysis and prediction technology to perform directional field calculation and time series feature extraction on the predicted wind condition time series parameters and the predicted temperature time series parameters, and then calculate the interactive representation information between the wind speed time series directional field characteristics and the wind direction angle time series directional field characteristics, so as to intelligently predict the wind power feed-in power value at the next moment based on the principal component-guided interactive representation between the multi-dimensional time series feature interactive representation of the wind condition and the predicted temperature time series directional field characteristics. Compared with traditional CNN, the present application can better reflect the dynamic changes of wind conditions through directional field calculation and time series feature extraction. At the same time, it can establish a closer and more reasonable association between different time points, which helps to capture long-term historical dependencies and short-term dynamic changes, thereby improving prediction accuracy.

[0032] In one example, if Figure 2As shown, in step S140, the predicted feed-in power of the wind power source at each moment is calculated to obtain the predicted wind power source feed-in power curve, including: S141, obtaining the predicted wind condition time series parameters of the location where the wind power source is located, and obtaining the predicted temperature time series parameters of the location where the wind power source is located, wherein the predicted wind condition time series parameters include wind speed time series parameters and wind direction angle time series parameters; S142, respectively performing direction field calculation and feature extraction on the wind speed time series parameters, the wind direction angle time series parameters and the predicted temperature time series parameters to obtain wind speed time series direction field features, wind direction angle time series parameters, and wind direction angle time series parameters. Angle time series directional field characteristics and predicted temperature time series directional field characteristics; S143, interactively fuse the wind speed time series directional field characteristics and the wind direction angle time series directional field characteristics to obtain a wind condition multi-dimensional time series feature interactive representation; S144, perform principal component-guided feature compensation interaction on the wind condition multi-dimensional time series feature interactive representation and the predicted temperature time series directional field characteristics to obtain a wind condition-temperature time series directional field compensation interactive characteristic, and based on the wind condition-temperature time series directional field compensation interactive characteristic, obtain the wind power feed-in power value at the next moment.

[0033] Specifically, in the technical solution of the present application, first, the predicted wind condition time series parameters of the location of the wind power source are obtained, wherein the predicted wind condition time series parameters include wind speed time series parameters and wind direction angle time series parameters.

[0034] Next, the predicted temperature time series parameters of the location of the wind power source are obtained. In a specific example, first, the required temperature information type is clarified. For wind power generation, the most important is the ground temperature, that is, the air temperature at a height of two meters above the ground. Next, a suitable data source is selected to obtain this information, such as obtaining short-term weather forecasts through the National Meteorological Center (CMA). Here, short-term weather forecasts can include hourly temperature forecasts. Then, through the API interface or web interface, a request is sent to the selected service provider, specifying the geographic location coordinates (latitude and longitude), the forecast time period (such as the next three days) and the time resolution (such as every hour). After the request is successful, data containing temperature forecasts for each hour in the next 72 hours will be received. Then, after receiving the raw data, it is cleaned and converted as necessary to ensure that it is suitable for subsequent analysis, which may involve unit conversion (such as converting Fahrenheit to Celsius), missing value filling, outlier detection, etc. Finally, the sorted temperature data is organized into an ordered time series list, each element represents a temperature measurement at a time point, and this sequence is used as one of the inputs to participate in the subsequent wind power generation power prediction model.

[0035] Then, considering that the power generation of renewable energy is dynamically affected by multiple factors, and these factors have complex changing rules and flow trends in time, in order to more deeply understand and capture the dynamic characteristics of these variables changing over time, the present application calculates the direction field of the wind speed time series parameters, the wind direction angle time series parameters and the predicted temperature time series parameters respectively to intuitively show the flow and change trend of the parameters, reflecting the parameter information at different times, and obtaining the wind speed time series direction field diagram representation, the wind direction angle time series direction field diagram representation and the predicted temperature time series direction field diagram representation. It can be understood that the direction field diagram (or vector field diagram) is usually used to show the direction and intensity of change of a physical quantity in time and / or space, and by calculating the direction diagram of these time series parameters, the change trend of each parameter at different times can be reflected. For example, the wind speed time series direction field diagram will show the direction and magnitude of the wind speed at a point (for example, the location of a wind turbine) changing over time. The wind speed at each time point can be represented by an arrow, the length of the arrow represents the wind speed, and the direction of the arrow represents the trend of the wind speed increasing or decreasing.

[0036] Next, considering that each time series directional field graph representation contains rich time series feature information, and there are inherent patterns and trends between the data at each time point, the dilated convolutional neural network can increase the receptive field without increasing the size of the convolution kernel by introducing holes in the convolution kernel, and can better process data with spatial continuity and long-distance correlation, such as macro trends and features that may exist in the directional field graph. Based on this, the present application obtains the wind speed time series directional field graph representation, the wind direction angle time series directional field graph representation, and the predicted temperature time series directional field graph representation by respectively passing the directional field feature extractor based on the dilated convolutional neural network to capture the subtle features and complex patterns in the directional field graph, including local turbulence features, macro wind field distribution features, etc., to obtain the wind speed time series directional field feature vector, the wind direction angle time series directional field feature vector, and the predicted temperature time series directional field feature vector.

[0037] Accordingly, if Figure 3As shown, in step S142, the direction field calculation and feature extraction are performed on the wind speed time series parameters, the wind direction angle time series parameters and the predicted temperature time series parameters respectively to obtain the wind speed time series direction field features, the wind direction angle time series direction field features and the predicted temperature time series direction field features, including: S1421, respectively calculating the direction fields of the wind speed time series parameters, the wind direction angle time series parameters and the predicted temperature time series parameters to obtain the wind speed time series direction field map representation, the wind direction angle time series direction field map representation and the predicted temperature time series direction field map representation; S1422, respectively passing the wind speed time series direction field map representation, the wind direction angle time series direction field map representation and the predicted temperature time series direction field map representation through a direction field feature extractor based on an expanded convolutional neural network to obtain a wind speed time series direction field feature vector as the wind speed time series direction field feature, a wind direction angle time series direction field feature vector as the wind direction angle time series direction field feature and a predicted temperature time series direction field feature vector as the predicted temperature time series direction field feature.

[0038] Then, considering that the wind speed time series direction field feature vector and the wind direction angle time series direction field feature vector represent the important features of wind speed and wind direction angle in different time and space dimensions respectively. However, in the actual wind power generation process, wind speed and wind direction angle do not affect power independently, but are interrelated and influence each other. For example, under different wind directions, the same wind speed may produce different power generation. Based on this, in the technical solution of the present application, the wind speed time series direction field feature vector and the wind direction angle time series direction field feature vector are passed through a wind condition multidimensional time series feature interactive fusion device based on an X-linear attention bilinear pooling unit to obtain a wind condition multidimensional time series feature interactive representation vector. Specifically, the X-linear attention mechanism can assign different weights according to the importance of the features, and the bilinear pooling unit can effectively handle the nonlinear relationship between the features. The combination of the two can deeply mine the interactive information between different feature vectors, so that the generated vector integrates the multidimensional time series features of wind speed and wind direction angle and the interactive information between them, and can describe the wind condition more comprehensively and accurately.

[0039] Correspondingly, in step S143, the wind speed time series direction field feature and the wind direction angle time series direction field feature are interactively fused to obtain a wind condition multi-dimensional time series feature interactive representation, including: passing the wind speed time series direction field feature vector and the wind direction angle time series direction field feature vector through a wind condition multi-dimensional time series feature interactive fusion device based on an X-linear attention bilinear pooling unit to obtain a wind condition multi-dimensional time series feature interactive representation vector as the wind condition multi-dimensional time series feature interactive representation.

[0040] Accordingly, if Figure 4As shown, in step S144, the principal component-guided feature compensation interaction is performed on the wind condition multi-dimensional time series feature interaction representation and the predicted temperature time series direction field feature to obtain the wind condition-temperature time series direction field compensation interaction feature, and based on the wind condition-temperature time series direction field compensation interaction feature, the wind power feed-in power value at the next moment is obtained, including: S1441, the principal component-guided feature compensation interaction is performed on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to obtain the wind condition-temperature time series direction field compensation interaction feature vector as the wind condition-temperature time series direction field compensation interaction feature; S1442, based on the wind condition-temperature time series direction field compensation interaction feature vector, the wind power feed-in power value at the next moment is obtained.

[0041] Specifically, considering that wind power generation is not only affected by the interaction of wind speed and wind direction, temperature is also an important indirect influencing factor. The previously obtained wind condition multi-dimensional time series feature interaction representation vector only integrates the time series interaction information of wind speed and wind direction, while the predicted temperature time series direction field feature vector represents the important characteristics related to temperature time series. Therefore, in order to comprehensively consider the comprehensive impact of wind and temperature factors on power generation, and to explore these potential key complex relationships, the present application performs principal component-guided feature compensation interaction on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to identify the main components that best represent their characteristics, and dynamically compensates and interacts their respective characteristics based on the differences between the two, to obtain the wind condition-temperature time series direction field compensation interaction feature vector.

[0042] Accordingly, if Figure 5As shown, in step S1441, the principal component-guided feature compensation interaction is performed on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to obtain the wind condition-temperature time series direction field compensation interaction feature vector, including: S14411, feature principal component analysis is performed on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to obtain a set of wind condition multi-dimensional time series feature principal component coding vectors and a set of predicted temperature time series direction field feature principal component coding vectors; S14412, the set of wind condition multi-dimensional time series feature principal component coding vectors and the set of predicted temperature time series direction field feature principal component coding vectors are combined. The set is constructed as a principal component aggregation coding feature map of multi-dimensional time series characteristics of wind conditions and a principal component aggregation coding feature map of predicted temperature time series characteristics; S14413, calculating the wind condition-predicted temperature time series difference embedding compensation coding weight vector between the principal component aggregation coding feature map of multi-dimensional time series characteristics of wind conditions and the principal component aggregation coding feature map of predicted temperature time series characteristics; S14414, based on the wind condition-predicted temperature time series difference embedding compensation coding weight vector, compensatingly aggregate the set of principal component coding vectors of multi-dimensional time series characteristics of wind conditions and the set of principal component coding vectors of predicted temperature time series direction field characteristics to obtain the wind condition-temperature time series direction field compensation interaction feature vector.

[0043] Among them, in step S14413, the wind condition-prediction temperature time series difference embedding compensation coding weight vector between the principal component aggregation coding feature map of the multi-dimensional time series characteristics of the wind condition and the principal component aggregation coding feature map of the predicted temperature time series characteristics is calculated, including: performing difference embedding processing on the principal component aggregation coding feature map of the multi-dimensional time series characteristics of the wind condition and the principal component aggregation coding feature map of the predicted temperature time series characteristics to obtain a wind condition multi-dimensional time series branch weight vector and a predicted temperature time series branch weight vector; calculating the wind condition-prediction temperature time series difference embedding compensation coding weight vector between the wind condition multi-dimensional time series branch weight vector and the predicted temperature time series branch weight vector.

[0044] Among them, in step S14414, based on the wind condition-predicted temperature time series difference embedding compensation coding weight vector, the set of principal component coding vectors of the multi-dimensional time series characteristics of the wind condition and the set of principal component coding vectors of the predicted temperature time series direction field characteristics are compensated and aggregated to obtain the wind condition-temperature time series direction field compensation interaction feature vector, including: calculating the positional mean vector of the set of principal component coding vectors of the multi-dimensional time series characteristics of the wind condition and the set of principal component coding vectors of the predicted temperature time series direction field characteristics to obtain the wind condition multi-dimensional time series principal component representation coding vector and the predicted temperature time series principal component representation coding vector; based on the wind condition-predicted temperature time series difference embedding compensation coding weight vector, the wind condition multi-dimensional time series principal component representation coding vector and the predicted temperature time series principal component representation coding vector are aggregated and interacted to obtain the wind condition-temperature time series direction field compensation interaction feature vector.

[0045] More specifically, the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector are first subjected to feature principal component analysis to obtain a set of wind condition multi-dimensional time series feature principal component encoding vectors and a set of predicted temperature time series direction field feature principal component encoding vectors. A person skilled in the art should know that feature principal component analysis (PCA), as an unsupervised learning method, transforms a multidimensional data set into a new coordinate system in which the first principal component has the maximum variance, and each subsequent component is orthogonal to all previous components and captures as much residual variance as possible. In this technical solution, performing feature principal component analysis on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector means finding the main directions in these two vector spaces to achieve feature dimensionality reduction and feature sparsification.

[0046] The process can be expressed as follows: ;in, is the interactive representation vector of the multi-dimensional time series characteristics of the wind conditions, is the characteristic principal component analysis operation, It is through The calculated covariance matrix of the multidimensional time series samples of wind conditions is: is the principal component orthogonal matrix of the multidimensional time series characteristics of wind conditions, is the principal component coding vector of each wind condition multi-dimensional time series feature in the set of principal component coding vectors of wind condition multi-dimensional time series features, is the multi-dimensional time series characteristic diagonal matrix of wind conditions, They are and The corresponding weight value, for The transposed matrix of is the predicted temperature time series direction field feature vector, It is through The calculated predicted temperature time series sample covariance matrix, is the orthogonal matrix of the principal components of the predicted temperature time series features, is each predicted temperature time series direction field feature principal component encoding vector in the set of predicted temperature time series direction field feature principal component encoding vectors, To predict the temperature time series feature diagonal matrix, They are and The corresponding weight value, for The transposed matrix of .

[0047] After obtaining the set of principal component coding vectors of the multi-dimensional time series characteristics of the wind conditions and the set of principal component coding vectors of the predicted temperature time series direction field characteristics, the set of principal component coding vectors of the multi-dimensional time series characteristics of the wind conditions and the set of principal component coding vectors of the predicted temperature time series direction field characteristics are constructed into a principal component aggregation coding feature map of the multi-dimensional time series characteristics of the wind conditions and a principal component aggregation coding feature map of the predicted temperature time series characteristics. It should be understood that each principal component coding vector set can be regarded as a point cloud in a high-dimensional space, and constructing a feature map is to map these point clouds into a two-dimensional or three-dimensional space so that the local neighborhood relationship can be maintained. This mapping is crucial for subsequent spatial information processing because it determines which information will be retained for the next step.

[0048] The process can be expressed as follows: ;in, For the reshape operation, It is the principal component aggregation coding feature map of multi-dimensional time series characteristics of wind conditions. It is the principal component aggregation coding feature map of predicted temperature time series features. is the principal component coding vector of each wind condition multi-dimensional time series feature in the set of principal component coding vectors of wind condition multi-dimensional time series features, It is each predicted temperature time series direction field feature principal component encoding vector in the set of predicted temperature time series direction field feature principal component encoding vectors.

[0049] Next, the principal component aggregation coding feature map of the multi-dimensional time series features of the wind conditions and the principal component aggregation coding feature map of the predicted temperature time series features are input into the difference embedding unit to obtain the multi-dimensional time series branch weight vector of the wind conditions and the predicted temperature time series branch weight vector. That is, as the feature map is formed, the difference embedding unit is designed to capture the difference between the two feature maps. The process of difference embedding is not only to identify the differences, but more importantly to quantify the importance of these differences. The generated weight vector reflects the relative importance of each position, which is critical for the implementation of the subsequent compensation mechanism. From a data perspective, the role of the multi-dimensional time series branch weight vector of the wind conditions and the predicted temperature time series branch weight vector is similar to an adjustment factor, ensuring fair interaction and fusion even when there are differences in the original features.

[0050] The process can be expressed as follows: ;in, is the average pooling operation, and They are The corresponding first weight matrix and second weight matrix, and They are The corresponding first weight matrix and second weight matrix, is a nonlinear activation function, is the output activation function, is the wind condition multi-dimensional time series branch weight vector, is the predicted temperature timing branch weight vector.

[0051] In order to reduce the amount of data processing for aggregation interaction, before the aggregation interaction of the principal component aggregation coding feature map of the multi-dimensional time series characteristics of the wind condition and the principal component aggregation coding feature map of the predicted temperature time series characteristics based on the multi-dimensional time series branch weight vector of the wind condition and the predicted temperature time series branch weight vector, the positional mean vector of the set of principal component coding vectors of the multi-dimensional time series characteristics of the wind condition and the set of principal component coding vectors of the predicted temperature time series direction field characteristics are calculated to obtain the principal component representation coding vector of the multi-dimensional time series of the wind condition and the principal component representation coding vector of the predicted temperature time series. It should be understood that this step is essentially another form of data compression. Unlike PCA, this step focuses on the average of the eigenvalues ​​at the same position. The calculation of the mean vector lays the foundation for the subsequent aggregation interaction, because these vectors represent the core information of each eigenvector.

[0052] The process can be expressed as follows: ;in, is the wind condition multi-dimensional time series branch weight vector, is the predicted temperature timing branch weight vector, It is subtracted by position point. To take the absolute value operation, is the wind condition-prediction temperature time series difference embedding compensation encoding weight vector, is the first principal component encoding vector of the multi-dimensional time series characteristics of the wind condition. The principal component coding vector of multi-dimensional time series characteristics of wind conditions, is the first one in the set of principal component encoding vectors of the predicted temperature time series direction field feature The principal component encoding vector of the predicted temperature time series direction field features, is the number of vectors in the set of principal component encoding vectors of multidimensional time series characteristics of wind conditions and the set of principal component encoding vectors of predicted temperature time series directional field characteristics, is the encoding vector representing the multidimensional time series principal component of wind conditions, It is the encoding vector representing the principal component of the predicted temperature time series.

[0053] Finally, based on the difference embedding compensation coding weight vector, the wind condition multi-dimensional time series principal component representation coding vector and the predicted temperature time series principal component representation coding vector are aggregated and interacted to obtain the wind condition-temperature time series direction field compensation interaction feature vector. Here, the difference embedding compensation coding weight vector guides the way of adjusting the interaction according to the difference between the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector. The aggregate interaction not only integrates the information from the two original features, but also ensures the sensitivity and adaptability of the interaction result to the difference of the original features by introducing a compensation mechanism.

[0054] The process can be expressed as follows: ;in, is the wind condition-prediction temperature time series difference embedding compensation encoding weight vector, It is the point multiplication by position. is the encoding vector representing the multidimensional time series principal component of wind conditions, is the encoding vector representing the principal component of the predicted temperature time series, is the point convolutional coding, is a nonlinear activation function, It is the wind condition-temperature time series direction field compensation interaction characteristic vector.

[0055] Then, the wind condition-temperature time series direction field compensation interaction feature vector is passed through a decoder-based wind power source predictor to obtain a decoded value of wind power feed-in power at the next moment. That is, the wind condition-temperature time series direction field compensation interaction feature vector obtained by principal component compensation interaction using the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector is decoded to obtain a decoded value of wind power feed-in power at the next moment by utilizing the decoder-based wind power source predictor's ability to learn the complex mapping relationship between feature vectors and power values.

[0056] Correspondingly, in step S1442, based on the wind condition-temperature time series direction field compensation interaction characteristic vector, the wind power feed-in power value at the next moment is obtained, including: passing the wind condition-temperature time series direction field compensation interaction characteristic vector through a decoder-based wind power predictor to obtain a wind power feed-in power decoding value as the wind power feed-in power value at the next moment.

[0057] In a preferred example, the wind condition-temperature time series direction field compensation interactive feature vector is passed through a decoder-based wind power source predictor to obtain a decoded value of wind power source feed-in power at the next moment, including: Determine the eigenvalue mean corresponding to the wind condition-temperature time series direction field compensation interaction eigenvector and the standard deviation of the eigenvalues ; The first wind condition-temperature time series directional field compensation interactive fairness target vector is obtained by multiplying the point-subtraction vector of the wind condition-temperature time series directional field compensation interactive eigenvector and the eigenvalue mean with the eigenvalue standard deviation: ;in, represents the wind condition-temperature time series direction field compensation interaction characteristic vector, represents the mean eigenvalue corresponding to the wind condition-temperature time series direction field compensation interaction eigenvector, represents the standard deviation of the eigenvalue corresponding to the wind condition-temperature time series direction field compensation interaction eigenvector, Indicates point reduction, represents dot product, represents the first wind condition-temperature time series direction field compensation interactive fairness target vector; The point-wise subtraction vector of the wind condition-temperature time series directional field compensation interaction eigenvector and the eigenvalue standard deviation is multiplied by the eigenvalue mean to obtain a second wind condition-temperature time series directional field compensation interaction fairness target vector: ;in, represents the wind condition-temperature time series direction field compensation interaction characteristic vector, represents the mean eigenvalue corresponding to the wind condition-temperature time series direction field compensation interaction eigenvector, represents the standard deviation of the eigenvalue corresponding to the wind condition-temperature time series direction field compensation interaction eigenvector, Indicates point reduction, represents dot product, represents the second wind condition-temperature time series direction field compensation interactive fairness target vector; After multiplying the bit-by-bit reciprocal of the second wind condition-temperature time series direction field compensation interactive fairness target vector by the first wind condition-temperature time series direction field compensation interactive fairness target vector, take the bit-by-bit logarithm with base 2 to obtain the wind condition-temperature time series direction field compensation interactive information correction vector: ;in, represents the first wind condition-temperature time series direction field compensation interactive fairness target vector, represents the second wind condition-temperature time series direction field compensation interactive fairness target vector, represents the bit-by-bit inverse of the second wind condition-temperature time series direction field compensation interactive fairness target vector, represents dot product, represents the logarithmic function with base 2, A correction vector representing the wind condition-temperature time series direction field compensation mutual information; The eigenvalue mean Divide by the standard deviation of the eigenvalue The square root of the quotient is multiplied by the weight hyperparameter, and then combined with the wind condition-temperature time series direction field compensation interactive information correction vector point to obtain the optimized wind condition-temperature time series direction field compensation interactive feature vector: ;in, represents the mean eigenvalue corresponding to the wind condition-temperature time series direction field compensation interaction eigenvector, represents the standard deviation of the eigenvalue corresponding to the wind condition-temperature time series direction field compensation interaction eigenvector, represents the weight hyperparameter, Indicates point addition, represents the wind condition-temperature time series direction field compensation mutual information correction vector, A wind condition-temperature time series direction field compensation interaction characteristic vector representing the optimization; The optimized wind condition-temperature time series direction field compensation interactive characteristic vector is passed through a decoder-based wind power source predictor to obtain a decoded value of wind power source feed-in power at the next moment.

[0058] Here, since the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series directional field feature vector respectively represent the multi-dimensional interactive fusion features of the local correlation of the direction field of wind speed-wind direction angle and the local correlation features of the direction field of predicted temperature, when the feature principal component compensation interaction is performed on them, the source time series directional field image semantic feature population attributes corresponding to different data will have interactive fairness differences based on the principal component compensation level, thereby affecting the feature distribution interactive inclusiveness of the wind condition-temperature time series directional field compensation interactive feature vector, and reducing the accuracy of the decoding results obtained by the decoder-based wind power source predictor.

[0059] Therefore, taking into account the attribute level fairness differences of the data population corresponding to the sequence fusion features of the wind condition-temperature time series directional field compensation interactive feature vector, in order to improve the interactive inclusiveness under the feature distribution diversity of the wind condition-temperature time series directional field compensation interactive feature vector, the cross probability value constraint based on the wind condition-temperature time series directional field compensation interactive feature vector is used as the interactive fairness target representation to correct the group feature information interactive propagation of the wind condition-temperature time series directional field compensation interactive feature vector, and the unified statistical feature response interaction based on the wind condition-temperature time series directional field compensation interactive feature vector is used as the feature distribution multi-level fairness target bias to achieve the robust distribution fairness unified representation of the wind condition-temperature time series directional field compensation interactive feature vector, form a fair cooperation paradigm under the feature distribution framework of the wind condition-temperature time series directional field compensation interactive feature vector, and improve the accuracy of the decoding value of the wind power feed-in power at the next moment obtained by the decoder-based wind power predictor.

[0060] Based on the above embodiments, see Figure 6 As shown, it is a structural schematic diagram of an AI-based new energy power generation prediction system 100 in an embodiment of the present application. The AI-based new energy power generation prediction system 100 includes: a predicted radiation curve acquisition module 110, which is used to divide the photovoltaic power supply cycle, and determine the predicted radiation curve of the next cycle based on the predicted meteorological data and the location of the photovoltaic power supply; a correction module 120, which is used to correct the predicted radiation curve to obtain a corrected predicted radiation curve; a predicted photovoltaic power supply feed-in power curve acquisition module 130, which is used to obtain a temperature prediction change curve, and based on the temperature prediction change curve and the corrected predicted radiation curve, obtain a predicted photovoltaic power supply feed-in power curve; a predicted feed-in power calculation module 140, which is used to calculate the predicted feed-in power of the wind power supply at each moment to obtain a predicted wind power supply feed-in power curve; a strategy adjustment module 150, which is used to adjust the hydrogen energy storage strategy based on the predicted photovoltaic power supply feed-in power curve, the predicted wind power supply feed-in power curve and the real-time feed-in power.

[0061] In one example, the strategy adjustment module 150 includes: a timing parameter acquisition unit, which is used to acquire the predicted wind condition timing parameters of the location of the wind power source, and acquire the predicted temperature timing parameters of the location of the wind power source, wherein the predicted wind condition timing parameters include wind speed timing parameters and wind direction angle timing parameters; a feature extraction unit, which is used to perform directional field calculation and feature extraction on the wind speed timing parameters, the wind direction angle timing parameters and the predicted temperature timing parameters, respectively, to obtain wind speed timing directional field features, wind direction angle timing directional field features and predicted temperature timing directional field features. Characteristic; a multi-dimensional time series feature interactive fusion unit, used for performing interactive fusion of the wind speed time series directional field characteristics and the wind direction angle time series directional field characteristics to obtain a multi-dimensional time series feature interactive representation of the wind condition; a wind power source feed-in power value acquisition unit at the next moment, used for performing principal component-guided feature compensation interaction on the wind condition multi-dimensional time series feature interactive representation and the predicted temperature time series directional field characteristics to obtain a wind condition-temperature time series directional field compensation interactive feature, and based on the wind condition-temperature time series directional field compensation interactive feature, obtain the wind power source feed-in power value at the next moment.

[0062] Among them, in one example, the feature extraction unit is used to: respectively calculate the direction fields of the wind speed time series parameters, the wind direction angle time series parameters and the predicted temperature time series parameters to obtain a wind speed time series directional field map representation, a wind direction angle time series directional field map representation and a predicted temperature time series directional field map representation; respectively pass the wind speed time series directional field map representation, the wind direction angle time series directional field map representation and the predicted temperature time series directional field map representation through a direction field feature extractor based on an expanded convolutional neural network to obtain a wind speed time series directional field feature vector as the wind speed time series directional field feature, a wind direction angle time series directional field feature vector as the wind direction angle time series directional field feature and a predicted temperature time series directional field feature vector as the predicted temperature time series directional field feature.

[0063] Here, those skilled in the art can understand that the specific functions and operations of each module in the above-mentioned AI-based new energy power generation prediction system 100 have been referred to above. Figures 1 to 5 The description of the AI-based renewable energy power generation prediction method has been introduced in detail, and therefore, its repeated description will be omitted.

[0064] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.

[0065] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0066] The above is an explanation of the present application and should not be considered as limiting thereof. Although several exemplary embodiments of the present application have been described, those skilled in the art will readily appreciate that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application.

Claims

1. A method for predicting power generation of renewable energy based on AI, comprising: Divide the photovoltaic power supply cycle, and determine the predicted radiation curve of the next cycle based on the predicted meteorological data and the location of the photovoltaic power supply; correct the predicted radiation curve to obtain a corrected predicted radiation curve; obtain the temperature prediction change curve, and obtain the predicted photovoltaic power supply feed-in power curve based on the temperature prediction change curve and the corrected predicted radiation curve; calculate the predicted feed-in power of the wind power supply at each moment to obtain the predicted wind power supply feed-in power curve; adjust the hydrogen energy storage strategy based on the predicted photovoltaic power supply feed-in power curve, the predicted wind power supply feed-in power curve and the real-time feed-in power; characterized in that the predicted feed-in power of the wind power supply at each moment to obtain the predicted wind power supply feed-in power curve includes: Acquire the predicted wind condition time series parameters of the location where the wind power source is located, and acquire the predicted temperature time series parameters of the location where the wind power source is located, wherein the predicted wind condition time series parameters include wind speed time series parameters and wind direction angle time series parameters; Performing direction field calculation and feature extraction on the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter respectively to obtain wind speed time series direction field features, wind direction angle time series direction field features and predicted temperature time series direction field features; Performing interactive fusion of wind condition multi-dimensional time series features on the wind speed time series direction field features and the wind direction angle time series direction field features to obtain an interactive representation of wind condition multi-dimensional time series features; The principal component-guided feature compensation interaction is performed on the multi-dimensional time series feature interaction representation of the wind condition and the predicted temperature time series directional field feature to obtain the wind condition-temperature time series directional field compensation interaction feature, and based on the wind condition-temperature time series directional field compensation interaction feature, the wind power feed-in power value at the next moment is obtained.

2. The AI-based new energy power generation prediction method according to claim 1 is characterized in that: Direction field calculation and feature extraction are performed on the wind speed time series parameter, the wind direction angle time series parameter, and the predicted temperature time series parameter to obtain wind speed time series direction field features, wind direction angle time series direction field features, and predicted temperature time series direction field features, including: Calculating the direction fields of the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter respectively to obtain a wind speed time series direction field diagram representation, a wind direction angle time series direction field diagram representation and a predicted temperature time series direction field diagram representation; The wind speed time series directional field map representation, the wind direction angle time series directional field map representation and the predicted temperature time series directional field map representation are respectively passed through a directional field feature extractor based on an expanded convolutional neural network to obtain a wind speed time series directional field feature vector as the wind speed time series directional field feature, a wind direction angle time series directional field feature vector as the wind direction angle time series directional field feature and a predicted temperature time series directional field feature vector as the predicted temperature time series directional field feature.

3. The AI-based new energy power generation prediction method according to claim 2 is characterized in that: The wind speed time series direction field feature and the wind direction angle time series direction field feature are interactively fused to obtain a wind condition multi-dimensional time series feature interactive representation, including: passing the wind speed time series direction field feature vector and the wind direction angle time series direction field feature vector through a wind condition multi-dimensional time series feature interactive fusion device based on an X-linear attention bilinear pooling unit to obtain a wind condition multi-dimensional time series feature interactive representation vector as the wind condition multi-dimensional time series feature interactive representation.

4. The AI-based new energy power generation prediction method according to claim 3 is characterized in that: The principal component-guided feature compensation interaction is performed on the wind condition multi-dimensional time series feature interaction representation and the predicted temperature time series directional field feature to obtain a wind condition-temperature time series directional field compensation interaction feature, and based on the wind condition-temperature time series directional field compensation interaction feature, a wind power source feed-in power value at the next moment is obtained, including: Performing principal component-guided feature compensation interaction on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to obtain a wind condition-temperature time series direction field compensation interaction feature vector as the wind condition-temperature time series direction field compensation interaction feature; Based on the wind condition-temperature time series direction field compensation interactive characteristic vector, the wind power source feed-in power value at the next moment is obtained.

5. The AI-based new energy power generation prediction method according to claim 4 is characterized in that: The principal component-guided feature compensation interaction is performed on the wind condition multi-dimensional time series feature interaction representation vector and the predicted temperature time series direction field feature vector to obtain a wind condition-temperature time series direction field compensation interaction feature vector, including: Performing feature principal component analysis on the wind condition multidimensional time series feature interactive representation vector and the predicted temperature time series direction field feature vector to obtain a set of wind condition multidimensional time series feature principal component encoding vectors and a set of predicted temperature time series direction field feature principal component encoding vectors; Constructing the set of principal component coding vectors of the multi-dimensional time series characteristics of wind conditions and the set of principal component coding vectors of the predicted temperature time series direction field characteristics into a principal component aggregation coding feature map of the multi-dimensional time series characteristics of wind conditions and a principal component aggregation coding feature map of the predicted temperature time series characteristics; Calculate the wind condition-prediction temperature time series difference embedding compensation coding weight vector between the principal component aggregation coding feature map of the wind condition multi-dimensional time series feature and the principal component aggregation coding feature map of the predicted temperature time series feature; Based on the wind condition-predicted temperature time series difference embedded compensation coding weight vector, the set of principal component coding vectors of the wind condition multidimensional time series characteristics and the set of principal component coding vectors of the predicted temperature time series direction field characteristics are compensated and aggregated to obtain the wind condition-temperature time series direction field compensation interaction feature vector.

6. The AI-based new energy power generation prediction method according to claim 5 is characterized in that: Calculating the wind condition-prediction temperature time series difference embedding compensation coding weight vector between the wind condition multi-dimensional time series feature principal component aggregation coding feature map and the predicted temperature time series feature principal component aggregation coding feature map, including: Performing difference embedding processing on the principal component aggregation coding feature map of the multi-dimensional time series characteristics of the wind condition and the principal component aggregation coding feature map of the predicted temperature time series characteristics to obtain a wind condition multi-dimensional time series branch weight vector and a predicted temperature time series branch weight vector; The wind condition-predicted temperature timing difference embedding compensation coding weight vector between the wind condition multi-dimensional timing branch weight vector and the predicted temperature timing branch weight vector is calculated.

7. The AI-based new energy power generation prediction method according to claim 6 is characterized in that: Based on the wind condition-prediction temperature time series difference embedding compensation coding weight vector, the set of principal component coding vectors of the wind condition multi-dimensional time series characteristics and the set of principal component coding vectors of the predicted temperature time series direction field characteristics are compensated and aggregated to obtain the wind condition-temperature time series direction field compensation interaction feature vector, including: Calculate the position mean vector of the set of principal component coding vectors of the multi-dimensional time series characteristics of the wind conditions and the set of principal component coding vectors of the predicted temperature time series direction field characteristics to obtain the principal component representation coding vector of the multi-dimensional time series of the wind conditions and the principal component representation coding vector of the predicted temperature time series; Based on the wind condition-predicted temperature time series difference embedding compensation coding weight vector, the wind condition multi-dimensional time series principal component characterization coding vector and the predicted temperature time series principal component characterization coding vector are aggregated and interacted to obtain the wind condition-temperature time series directional field compensation interaction feature vector.

8. The AI-based new energy power generation prediction method according to claim 7 is characterized in that: Based on the wind condition-temperature time series direction field compensation interaction characteristic vector, the wind power feed-in power value at the next moment is obtained, including: passing the wind condition-temperature time series direction field compensation interaction characteristic vector through a decoder-based wind power predictor to obtain a wind power feed-in power decoding value as the wind power feed-in power value at the next moment.

9. A new energy power generation prediction system based on AI, comprising: A predicted radiation curve acquisition module is used to divide the photovoltaic power supply cycle and determine the predicted radiation curve of the next cycle based on the predicted meteorological data and the location of the photovoltaic power supply; A correction module, used for correcting the predicted radiation amount curve to obtain a corrected predicted radiation amount curve; A module for obtaining a predicted photovoltaic power supply feed-in power curve is used to obtain a predicted temperature change curve, and obtain a predicted photovoltaic power supply feed-in power curve based on the predicted temperature change curve and the corrected predicted radiation amount curve; A predicted feed-in power calculation module is used to calculate the predicted feed-in power of the wind power source at each moment to obtain a predicted wind power source feed-in power curve; A strategy adjustment module, used to adjust the hydrogen energy storage strategy based on the predicted photovoltaic power supply feed-in power curve, the predicted wind power supply feed-in power curve and the real-time feed-in power; characterized in that the strategy adjustment module includes: A timing parameter acquisition unit, used to acquire the predicted wind condition timing parameters of the location where the wind power source is located, and acquire the predicted temperature timing parameters of the location where the wind power source is located, wherein the predicted wind condition timing parameters include wind speed timing parameters and wind direction angle timing parameters; A feature extraction unit, used for performing directional field calculation and feature extraction on the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter to obtain wind speed time series directional field features, wind direction angle time series directional field features and predicted temperature time series directional field features; A multi-dimensional time series feature interactive fusion unit, used for interactively fusing the wind speed time series direction field feature and the wind direction angle time series direction field feature to obtain a wind condition multi-dimensional time series feature interactive representation; The wind power feed-in power value acquisition unit at the next moment is used to perform principal component-guided feature compensation interaction on the multi-dimensional time series feature interaction representation of the wind condition and the predicted temperature time series directional field feature to obtain the wind condition-temperature time series directional field compensation interaction feature, and obtain the wind power feed-in power value at the next moment based on the wind condition-temperature time series directional field compensation interaction feature.

10. The AI-based renewable energy power generation prediction system according to claim 9, characterized in that: The feature extraction unit is used to: Calculating the direction fields of the wind speed time series parameter, the wind direction angle time series parameter and the predicted temperature time series parameter respectively to obtain a wind speed time series direction field diagram representation, a wind direction angle time series direction field diagram representation and a predicted temperature time series direction field diagram representation; The wind speed time series directional field map representation, the wind direction angle time series directional field map representation and the predicted temperature time series directional field map representation are respectively passed through a directional field feature extractor based on an expanded convolutional neural network to obtain a wind speed time series directional field feature vector as the wind speed time series directional field feature, a wind direction angle time series directional field feature vector as the wind direction angle time series directional field feature and a predicted temperature time series directional field feature vector as the predicted temperature time series directional field feature.

Images