A new energy photovoltaic power prediction system and method based on deep learning

Abstract

The present invention relates to the technical field of deep learning, and specifically to a new energy photovoltaic power prediction system and method based on deep learning. It includes obtaining historical power data and meteorological data of a photovoltaic site, and performing power prediction for the current time series through a single-site power prediction model; capturing the spatial correlation between sites through establishing a multi-site joint prediction model to predict the power of the photovoltaic site; establishing a weather pattern recognition method according to the meteorological data to distinguish normal weather patterns and sudden weather patterns; establishing an adversarial weather-power joint prediction model to process multi-site power collaborative prediction. The present invention improves the site power prediction efficiency through online learning and transfer learning for single-site power prediction and multi-site joint prediction; through simulating extreme and severely changing weather conditions for adversarial training to establish an adversarial weather prediction network, and then performing joint prediction of weather and power, the accuracy of the prediction model in a harsh environment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of deep learning, and specifically to a new energy photovoltaic power prediction system and method based on deep learning. Background Art

[0002] With the acceleration of the global energy transformation process, the proportion of new energy, especially photovoltaic power generation, in the energy structure has been continuously increasing; however, the nature of photovoltaic power generation determines that its output power has strong volatility and intermittency, which poses significant challenges to the safe and stable operation of the power system. Therefore, photovoltaic power prediction is crucial for advance planning of power schemes. Traditional photovoltaic power prediction methods mainly rely on simple statistical models, regression analysis, or basic time series models; traditional methods usually establish a linear relationship model between a single meteorological parameter and power, and the prediction error rate is generally high. Especially in the case of changing weather conditions such as sunny and cloudy days, the error rate may exceed 40%; traditional method models are slow to respond to sudden weather changes, and mostly predict a single photovoltaic site, ignoring the spatial correlation between geographically adjacent sites; moreover, traditional method models mostly adopt an offline training method and are difficult to adapt to the changes in system characteristics brought about by external factor changes. Summary of the Invention

[0003] The purpose of the present invention is to provide a new energy photovoltaic power prediction system and method based on deep learning to solve the problem of high error rate in site power prediction in single-site power prediction and multi-site joint prediction, and improve the power prediction efficiency; by simulating extreme and drastic weather conditions for adversarial training to establish an adversarial weather prediction network, and then performing joint prediction of weather and power to solve the problem of improving the accuracy of the prediction model in harsh environments.

[0004] To achieve the above purpose, on the one hand, the present invention provides a new energy photovoltaic power prediction method based on deep learning, and the method includes the following steps:

[0005] Step S1, obtaining historical power data and meteorological data of a photovoltaic site; the photovoltaic site is a single photovoltaic site or multiple photovoltaic sites within the research scope; the meteorological data includes temperature, humidity, wind speed, and light intensity; performing data preprocessing on the historical power data and meteorological data to obtain standardized data.

[0006] Step S2, extracting local pattern features of meteorological data and power data based on the standardized data, and performing power prediction for the current time series through a single-site power prediction model; the single-site power prediction model includes a preset time series prediction model and a preset spatial feature extraction model; capturing the spatial correlation between sites through establishing a multi-site joint prediction model to predict the power of photovoltaic sites.

[0007] Step S3, establish a weather pattern recognition method based on the meteorological data to distinguish normal weather patterns and sudden weather patterns; establish an adversarial weather prediction network based on adversarial learning technology, and the adversarial weather prediction network is a deep learning framework that generates weather prediction data through adversarial training.

[0008] Step S4, based on the adversarial weather prediction network, establish an adversarial weather-power joint prediction model, and the adversarial weather-power joint prediction model is used to process multi-site power collaborative prediction through joint online learning and transfer learning of meteorological conditions and power output.

[0009] Furthermore, the preset spatial feature extraction model identifies and extracts local features of meteorological data and power data by learning the standardized data; the preset spatial feature extraction model uses a convolutional neural network for calculation, and the formula is:

[0010] ;

[0011] where is the value of the -th layer feature map at position ; is the value of the -th layer feature map at position ; is the weight of the -th layer convolution kernel at position ; is the height and width of the convolution kernel; is the configuration item of the -th layer; is a preset activation function; M is the number of rows of the convolution kernel, indicating the number of pixels covered by the convolution kernel in the vertical direction; N is the number of columns of the convolution kernel, indicating the number of pixels covered by the convolution kernel in the horizontal direction.

[0012] Furthermore, the method for power prediction includes:

[0013] Capture the long-term and short-term temporal dependencies of the photovoltaic site through the established single-site power prediction model, and perform power prediction for the current time series; first, receive the local feature values of meteorological data and power data as input features, and use the historical learning information as the hidden state; then, judge whether the hidden state information needs to be retained or discarded through the forget gate, screen the new information in the input features through the input gate and generate a candidate memory unit; update the memory unit by weighted fusion of the forgotten hidden state information and the new information; finally, generate the power prediction value of the photovoltaic site at the current moment according to the updated new memory unit.

[0014] Furthermore, the method for establishing a multi-site joint prediction model includes:

[0015] The multi-site joint prediction model updates the power information of the photovoltaic site to be predicted by studying the spatial correlation between multiple sites. The formula is:

[0016] ;

[0017] Wherein, is the feature representation of node at the layer; represents the neighbor set of node ; represents the number of neighbors; represents the weight matrix of the layer; is the configuration item of the layer; is the feature representation of node at the layer; is a preset activation function.

[0018] Furthermore, the weather pattern recognition method classifies different weather patterns by constructing a hyperplane, sets a preset decision boundary, and updates the hyperplane and then the preset decision boundary through data iteration; the preset decision boundary after iteration is used to distinguish normal weather patterns from sudden weather patterns.

[0019] The adversarial training is a mutual game process between a generator and a discriminator: the generator continuously improves the quality of the generated weather data, while the discriminator improves its ability to distinguish real and generated data; the objective function of the adversarial weather prediction network is expressed as:

[0020] ;

[0021] Wherein, is the generator network; represents minimizing the generator error; is the discriminator network; represents maximizing the discriminator error; represents the objective functions of the generator and the discriminator; is a real data sample; is the distribution of real weather data; is the expected value; represents is sampled from the real weather data distribution ; z is the input noise; is the prior distribution of the input noise for the samples generated by the generator; represents is sampled from the prior distribution of the input noise Sampled; Weather prediction data generated by the generator based on noise z; The probability output by the discriminator, indicating the input data The likelihood of being real weather data; Is the output of the discriminator for the generated data Indicates the probability that the generated data is judged as real weather data.

[0022] Furthermore, sudden or extreme weather pattern prediction is performed through the adversarial weather prediction network, and the weather prediction result is combined with the power prediction for adversarial weather-power joint prediction.

[0023] An adversarial weather-power joint prediction model is established by processing multi-site collaborative prediction through online learning and transfer learning; the online learning updates the model parameters using the basic formula of stochastic gradient descent, expressed as: ; where Is the model parameter at time point ; Is the updated model parameter; Is the learning rate at time point ; Is the gradient of the loss function with respect to the parameter On the data ; Is the new data collected at time point .

[0024] The Is set as an adaptive learning rate, expressed as: ; where Is the learning rate at time point ; Is the initial learning rate; Is the time step or the number of iterations; Is the square root of the time step; through the application of the adaptive learning rate, as the learning rate gradually decreases over time, the model learns quickly in the early stage and gradually stabilizes in the later stage.

[0025] The learning functional expression of the transfer learning is:

[0026] ;

[0027] Where Is the maximum mean discrepancy loss; Is the feature mapping function; Is the th sample of the source domain; Is the th sample of the target domain; Is the number of source domain samples; is the number of samples in the target domain; is the norm in the reproducing kernel Hilbert space.

[0028] Based on the same inventive concept, on the other hand, the present invention also provides a new energy photovoltaic power prediction system based on deep learning. The system includes: a first data acquisition module, a second time series prediction module, a third weather prediction network module, and an adversarial weather-power joint prediction module, and the modules are connected in sequence.

[0029] The first data acquisition module is used to acquire historical power data and meteorological data of a photovoltaic site; perform data preprocessing on the historical power data and meteorological data to obtain standardized data.

[0030] The second time series prediction module is used to extract local pattern features of meteorological data and power data based on the standardized data, and perform power prediction for the current time series through a single-site power prediction model; capture the spatial correlation between sites through a multi-site joint prediction model to predict the power of the photovoltaic site.

[0031] The third weather prediction network module is used to establish a weather pattern recognition method according to the meteorological data to distinguish normal weather patterns and sudden weather patterns; establish an adversarial weather prediction network based on adversarial learning technology.

[0032] The adversarial weather-power joint prediction module is used to establish an adversarial weather-power joint prediction model based on the adversarial weather prediction network. The adversarial weather-power joint prediction model performs multi-site power collaborative prediction through joint online learning and transfer learning of meteorological conditions and power output.

[0033] Beneficial effects

[0034] Compared with the prior art, the beneficial effects of the present invention are:

[0035] 1. The prediction model can simultaneously process time series dependence and spatial correlation to improve the prediction ability.

[0036] 2. Learn the system characteristics through a data-driven method, with stronger adaptability and further improved prediction accuracy.

[0037] 3. The online learning and transfer learning mechanisms enable the system to continuously evolve and improve the stability of long-term prediction accuracy. Description of the drawings

[0038] Figure 1 is a flowchart of a new energy photovoltaic power prediction method according to Embodiment 1 of the present invention;

[0039] Figure 2Schematic diagram of the module composition of a new energy photovoltaic power prediction system based on deep learning according to Embodiment 2 of the present invention. Detailed implementation manners

[0040] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0041] Embodiment 1: As Figure 1 shown, this embodiment provides a new energy photovoltaic power prediction method based on deep learning. The method includes the following steps:

[0042] Step S1, obtaining historical power data and meteorological data of a photovoltaic site; the photovoltaic site is a single photovoltaic site or multiple photovoltaic sites within the research scope; the meteorological data includes temperature, humidity, wind speed, and light intensity; preprocessing the historical power data and meteorological data to obtain standardized data.

[0043] For example: The team collected historical data of three photovoltaic power stations in different geographical locations in the past two years. The data includes power generation data recorded every 15 minutes, and the corresponding meteorological data (temperature, humidity, wind speed, and light intensity). One piece of data is: The record of a certain station at a certain moment shows: the power is 8.2 megawatts, the temperature is 28°C, the humidity is 45%, the wind speed is 3.5 m / s, and the light intensity is 950 W / m². After the data collection is completed, the team preprocesses the data. Since the measurement ranges of different sensors are different, such as the temperature range is from -10°C to 40°C, and the power range is from 0 to 10 megawatts, the team performs data standardization processing. Standardize the temperature of 28°C to 0.76 (calculated according to the minimum temperature of -10°C and the maximum temperature of 40°C), and standardize the power of 8.2 megawatts to 0.82 (calculated according to the minimum power of 0 megawatts and the maximum power of 10 megawatts).

[0044] Step S2, extracting local pattern features of meteorological data and power data based on the standardized data, and performing power prediction for the current time series through a single-site power prediction model; the single-site power prediction model includes a preset time series prediction model and a preset spatial feature extraction model; capturing the spatial correlation between sites through establishing a multi-site joint prediction model to predict the power of the photovoltaic site.

[0045] The preset spatial feature extraction model identifies and extracts local features of meteorological data and power data by learning the standardized data; the preset spatial feature extraction model uses a convolutional neural network for calculation, and the formula is:

[0046] ;

[0047] wherein, is the value of the -th layer feature map at position ; is the value of the -th layer feature map at position ; is the weight of the -th layer convolution kernel at position ; is the height and width of the convolution kernel; is the configuration item of the -th layer; is a preset activation function; M is the number of rows of the convolution kernel, representing the number of pixels covered by the convolution kernel in the vertical direction; N is the number of columns of the convolution kernel, representing the number of pixels covered by the convolution kernel in the horizontal direction.

[0048] It should be noted that local feature extraction is performed on meteorological and power data through a sliding window mechanism. The model adopts a multi-layer convolution structure, and each layer of convolution operation captures local spatial features and patterns in the data by combining weighted summation with a non-linear activation function. The convolution kernel, as a feature detector, can identify different scales and types of feature patterns, such as temperature change trends, light intensity fluctuations, etc. The bias term further enhances the expression ability of the model and can adapt to data distributions with different baseline levels. The activation function introduces non-linearity, enabling the model to learn complex non-linear mapping relationships, thereby accurately extracting the complex correlation patterns between meteorological conditions and power output in the photovoltaic system.

[0049] By establishing the single-site power prediction model, the long-term and short-term temporal dependencies of the photovoltaic site are captured for power prediction at the current time series; first, the local feature values of meteorological data and power data are received as input features, and historical learning information is used as the hidden state; subsequently, the forgetting gate is used to determine whether the hidden state information needs to be retained or discarded, and the input gate is used to filter new information in the input features and generate a candidate memory unit; the memory unit is updated by weighted fusion of the forgotten hidden state information and the new information; finally, the power prediction value of the photovoltaic site at the current moment is generated based on the updated new memory unit.

[0050] For example: The system receives input features at a certain time point: standardized temperature 0.74, humidity 0.46, wind speed 0.35, light intensity 0.92, and historical learning information from previous time points. Through the forgetting gate mechanism, the system determines that the data weight at the same time point the previous day should be reduced (because the cloud cover is significantly different on the current day), while retaining the data pattern in the morning of the current day. Through the input gate, the system identifies new information about the rapid increase in the current light intensity and predicts that the power at time point 1 will reach 8.2 megawatts, with a difference of only 0.1 megawatt from the actual value, and the prediction accuracy reaches 98.8%.

[0051] The method for establishing the multi-site joint prediction model includes:

[0052] The multi-site joint prediction model updates the power information of the photovoltaic site to be predicted by studying the spatial correlation between multiple sites. The formula is:

[0053] ;

[0054] Where, is the feature representation of node at the layer; represents the neighbor set of node ; represents the number of neighbors; represents the weight matrix of the layer; is the configuration item of the layer; is the feature representation of node at the layer; is a preset activation function.

[0055] It should be noted that the multi-site joint prediction model of the present invention is based on the principle of graph neural network. Multiple photovoltaic sites are regarded as nodes in the graph structure, and the correlation between sites is mapped as the connection relationship between nodes. Through the aggregation and update mechanism of neighbor node information, the modeling of spatial correlation between sites is realized. The multi-site joint prediction effectively utilizes the similarity of meteorological conditions between sites with close geographical locations and significantly improves the prediction accuracy.

[0056] For example: When analyzing the previous data, it is found that the power at a certain station 1 drops at 9:00 in the morning (from 5.6 megawatts to 4.2 megawatts). Through the correlation analysis between sites, the system identifies this as a signal of a moving cloud layer. Based on the geographical location relationship and historical weather patterns of the three stations, the system predicts that the cloud layer will affect a certain station 2 in about 45 minutes.

[0057] During the calculation process, the system assigns different weights to three stations respectively: Since Station 1 is the closest to Station 2 (15 kilometers), it is assigned the highest weight of 0.6; Station 3 is farther away (25 kilometers), so it is assigned a weight of 0.4. The system integrates this information and predicts that the power of Station 2 at 9:45 will drop from the originally expected 7.8 megawatts to 6.3 megawatts. The actual record shows that the actual power at 9:45 is 6.5 megawatts, and the prediction error is only 3%.

[0058] Step S3, establish a weather pattern recognition method based on the meteorological data to distinguish normal weather patterns and sudden weather patterns; establish an adversarial weather prediction network based on adversarial learning technology, and the adversarial weather prediction network is a deep learning framework that generates weather prediction data through adversarial training.

[0059] The weather pattern recognition method classifies different weather patterns by constructing a hyperplane, sets a preset decision boundary, and updates the hyperplane and then the preset decision boundary through data iteration; the normal weather pattern and the sudden weather pattern are distinguished by the preset decision boundary after iteration.

[0060] The adversarial training is a mutual game process between the generator and the discriminator: the generator continuously improves the quality of the generated weather data, while the discriminator improves the ability to distinguish real and generated data; the objective function of the adversarial weather prediction network is expressed as:

[0061] ;

[0062] Among them, is the generator network; represents minimizing the generator error; is the discriminator network; represents maximizing the discriminator error; represents the objective functions of the generator and the discriminator; is the real data sample; is the distribution of real weather data; is the expected value; represents is sampled from the real weather data distribution ; z is the input noise; is the prior distribution of the input noise, used for the samples generated by the generator; represents is sampled from the prior distribution of the input noise ; is the weather prediction data generated by the generator according to the noise z; is the probability output by the discriminator, indicating that the input data is the possibility of real weather data; is the discriminator for the generated data The output represents the probability that the generated data is judged to be real weather data.

[0063] For example: On a certain afternoon, the system detected that the data reported by the weather station showed a fast-moving cloud mass in the northwest direction, and the wind speed increased from 2.3 m / s to 6.8 m / s in the past 20 minutes. The system immediately identified this as a sudden weather pattern. Subsequently, the adversarial weather prediction network started to work. Through the cooperation of the generator and the discriminator, the network generated high-precision weather prediction data for the next 3 hours. The generator predicted the movement path of the cloud mass and the change in light based on the current observations and historical similar weather patterns. The discriminator evaluated the credibility of the generated results by comparing with historical real data, prompting the generator to continuously improve the prediction quality. Finally, the system predicted that the cloud mass would block the sun between 15:30 and 16:45, resulting in a decrease in light intensity from 870 W / m² to 420 W / m², and thus causing a significant decrease in power output.

[0064] Step S4: Based on the adversarial weather prediction network, establish an adversarial weather-power joint prediction model, which is a multi-site power collaborative prediction through joint online learning and transfer learning of meteorological conditions and power output.

[0065] Through the adversarial weather prediction network for sudden or extreme weather pattern prediction, combine the weather prediction results with the power prediction for adversarial weather-power joint prediction.

[0066] Establish an adversarial weather-power joint prediction model through online learning and transfer learning for multi-site collaborative prediction; the online learning updates the model parameters using the basic formula of stochastic gradient descent, expressed as: ; where is the model parameter at time point ; is the updated model parameter; is the learning rate at time point ; is the gradient of the loss function with respect to the parameter on the data ; is the new data collected at time point .

[0067] The is set as an adaptive learning rate, expressed as: ; where is the learning rate at time point ; is the initial learning rate; is the time step or number of iterations; is the square root of the time step; through the application of the adaptive learning rate, as the learning rate gradually decreases over time, the model learns quickly in the early stage and gradually stabilizes in the later stage.

[0068] It should be noted that the online learning mechanism of the present invention is based on the stochastic gradient descent algorithm and adapts to the changing meteorological environment and the working state of the photovoltaic system through real-time parameter updates. This online learning method is particularly suitable for application scenarios such as photovoltaic power prediction where the data distribution changes dynamically over time. The gradient calculation process takes into account the current parameter state and the characteristics of the new data to ensure that the update direction is towards reducing the prediction error.

[0069] The learning functional representation of the transfer learning is:

[0070] ;

[0071] Wherein, is the maximum mean discrepancy loss; is the feature mapping function; is the -th sample of the source domain; is the -th sample of the target domain; is the number of samples in the source domain; is the number of samples in the target domain; is the norm in the reproducing kernel Hilbert space.

[0072] It should be noted that the transfer learning mechanism realizes the effective transfer of knowledge between different photovoltaic sites through the maximum mean discrepancy loss function. The feature mapping function maps the source domain and target domain data to a high-dimensional feature space, and the maximum mean discrepancy measures the difference in distribution between the two domains in this space. By minimizing this difference, the model can effectively transfer the knowledge learned at data-rich sites to data-sparse sites, solving the problem of insufficient data in newly built or small photovoltaic sites; the reproducing kernel Hilbert space norm provides a strict mathematical measure of the distribution difference. The transfer learning technology greatly reduces the dependence on the historical data of the target site, enabling the model to maintain high-precision prediction ability under limited data conditions and is applicable to the actual application scenarios with diverse and widespread scales of photovoltaic sites.

[0073] Embodiment 2: Based on the same inventive concept, as Figure 2 shown, this embodiment also provides a new energy photovoltaic power prediction system based on deep learning, and the system includes: a first data acquisition module, a second time series prediction module, a third weather prediction network module, and an adversarial weather-power joint prediction module, and the modules are connected in sequence.

[0074] The first data acquisition module is used to acquire the historical power data and meteorological data of the photovoltaic site; preprocess the historical power data and meteorological data to obtain standardized data.

[0075] The second time series prediction module is used to extract the local pattern features of the meteorological data and power data based on the standardized data, and perform power prediction for the current time series through a single-site power prediction model; capture the spatial correlation between sites through a multi-site joint prediction model to predict the power of the photovoltaic site.

[0076] The third weather prediction network module is used to establish a weather pattern recognition method according to the meteorological data to distinguish normal weather patterns and sudden weather patterns; establish an adversarial weather prediction network based on adversarial learning technology.

[0077] The adversarial weather-power joint prediction module is used to establish an adversarial weather-power joint prediction model based on the adversarial weather prediction network. The adversarial weather-power joint prediction model performs multi-site power collaborative prediction through joint online learning and transfer learning of meteorological conditions and power output.

[0078] It should be noted that regarding the system in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0079] Finally, it should be noted that although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A new energy photovoltaic power prediction method based on deep learning, characterized in that, The method includes the following steps: Step S1: Obtain the historical power data and meteorological data of the photovoltaic site; the photovoltaic site is a single photovoltaic site or multiple photovoltaic sites within the research scope; the meteorological data includes temperature, humidity, wind speed, and light intensity; perform data preprocessing on the historical power data and meteorological data to obtain standardized data; Step S2: Extract the local pattern features of the meteorological data and power data based on the standardized data, and perform power prediction for the current time series through a single-site power prediction model; the single-site power prediction model includes a preset time series prediction model and a preset spatial feature extraction model; capture the spatial correlation between sites through a multi-site joint prediction model to predict the power of the photovoltaic site; Step S3: Establish a weather pattern recognition method based on the meteorological data to distinguish normal weather patterns and sudden weather patterns; establish an adversarial weather prediction network based on adversarial learning technology, and the adversarial weather prediction network is a deep learning framework that generates weather prediction data through adversarial training; Step S4: Based on the adversarial weather prediction network, establish an adversarial weather-power joint prediction model, and the adversarial weather-power joint prediction model performs multi-site power collaborative prediction through joint online learning and transfer learning of meteorological conditions and power output; Establish an adversarial weather-power joint prediction model through online learning and transfer learning for multi-site collaborative prediction; the online learning updates the model parameters using the basic formula of stochastic gradient descent, expressed as: ; where is the model parameter at time point ; is the updated model parameter; is the learning rate at time point ; is the gradient of the loss function with respect to the parameter on the data ; is the new data collected at time point ; The above-mentioned is set to an adaptive learning rate, expressed as: ; where is the learning rate at time point ; is the initial learning rate; is the time step or the number of iterations; is the square root of the time step; Through the application of the above-mentioned adaptive learning rate, as the learning rate gradually decreases over time, the model learns quickly in the early stage and gradually stabilizes in the later stage; The learning function of the transfer learning is expressed as: ； Among them, is the maximum mean discrepancy loss; is the feature mapping function; is the -th sample in the source domain; is the -th sample in the target domain; is the number of source domain samples; is the number of target domain samples; is the norm in the reproducing kernel Hilbert space.

2. The method for predicting new energy photovoltaic power based on deep learning according to claim 1, characterized in that, The preset spatial feature extraction model identifies and extracts the local features of the meteorological data and power data by learning the standardized data; the preset spatial feature extraction model uses a convolutional neural network for calculation, and the formula is: ； Wherein, is the value of the -th layer feature map at position ; is the value of the -th layer feature map at position ; is the weight of the -th layer convolution kernel at position ; is the height and width of the convolution kernel; is the configuration item of the -th layer; is the preset activation function; M is the number of rows of the convolution kernel, representing the number of pixels covered by the convolution kernel in the vertical direction; N is the number of columns of the convolution kernel, representing the number of pixels covered by the convolution kernel in the horizontal direction.

3. A new energy photovoltaic power prediction method based on deep learning according to claim 1, characterized in that, The method for power prediction includes: Capture the long-term and short-term time series dependencies of the photovoltaic site through the established single-site power prediction model to perform power prediction for the current time series; first, receive the local feature values of the meteorological data and power data as input features, and use the historical learning information as the hidden state; subsequently, judge whether the hidden state information needs to be retained or discarded through the forget gate, screen the new information in the input features through the input gate and generate a candidate memory unit; update the memory unit by weighted fusion of the forgotten hidden state information and the new information; finally, generate the power prediction value of the photovoltaic site at the current moment according to the updated new memory unit.

4. The method for predicting new energy photovoltaic power based on deep learning according to claim 3, wherein, The method for establishing a multi-site joint prediction model includes: The multi-site joint prediction model updates the power information of the photovoltaic site to be predicted by studying the spatial correlation between multiple sites, and the formula is: ； Among them, is the feature representation of the node at the layer; represents the neighbor set of the node ; represents the number of neighbors; represents the weight matrix of the layer; is the configuration item of the layer; is the feature representation of the node at the layer; is a preset activation function.

5. A new energy photovoltaic power prediction method based on deep learning according to claim 1, characterized in that, The weather pattern recognition method classifies different weather patterns by constructing a hyperplane, sets a preset decision boundary, and updates the hyperplane and then the preset decision boundary through data iteration; distinguish normal weather patterns and sudden weather patterns through the preset decision boundary after iteration; The adversarial training is a mutual game process between the generator and the discriminator: the generator continuously improves the quality of the generated weather data, and the discriminator improves the ability to distinguish real and generated data; the objective function of the adversarial weather prediction network is expressed as: ； Among them, is the generator network; represents minimizing the generator error; is the discriminator network; represents maximizing the discriminator error; represents the objective functions of the generator and the discriminator; is the real data sample; is the distribution of the real weather data; is the expected value; represents is sampled from the real weather data distribution ; z is the input noise; is the prior distribution of the input noise for the samples generated by the generator; represents is sampled from the prior distribution of the input noise ; is the weather prediction data generated by the generator according to the noise z; is the probability output by the discriminator, indicating that the input data is the likelihood of real weather data; is the output of the discriminator for the generated data and represents the probability that the generated data is discriminated as real weather data.

6. A new energy photovoltaic power prediction system based on deep learning, for performing the method according to any one of claims 1-5, characterized in that, The system includes: a first data acquisition module, a second time series prediction module, a third weather prediction network module, and an adversarial weather-power joint prediction module, and the modules are connected in sequence; The first data acquisition module is used to acquire historical power data and meteorological data of a photovoltaic site; perform data preprocessing on the historical power data and meteorological data to obtain standardized data; The second time series prediction module is used to extract local pattern features of meteorological data and power data based on the standardized data, and perform power prediction for the current time series through a single-site power prediction model; capture the spatial correlation between sites through a multi-site joint prediction model to predict the power of photovoltaic sites; The third weather prediction network module is used to establish a weather pattern recognition method according to the meteorological data to distinguish normal weather patterns and sudden weather patterns; establish an adversarial weather prediction network based on adversarial learning technology; The adversarial weather-power joint prediction module is used to establish an adversarial weather-power joint prediction model based on the adversarial weather prediction network, and the adversarial weather-power joint prediction model performs multi-site power collaborative prediction through joint online learning and transfer learning of meteorological conditions and power output.

Images